From b4532d4d8d500795412b4743b55223dd9b54d4f7 Mon Sep 17 00:00:00 2001
From: bruAristimunha <bruAristimunha@users.noreply.github.com>
Date: Thu, 26 Sep 2024 15:13:32 +0000
Subject: [PATCH] deploy:
 braindecode/braindecode@35a0fdf8823d1ce83f1f7a09c4397eee5b44ea2a

---
 .../auto_examples_python.zip                  |  Bin 259396 -> 259396 bytes
 .../plot_relative_positioning.zip             |  Bin 43129 -> 43129 bytes
 .../plot_basic_training_epochs.zip            |  Bin 18044 -> 18044 bytes
 .../plot_custom_dataset_example.zip           |  Bin 6683 -> 6683 bytes
 .../plot_split_dataset.zip                    |  Bin 9711 -> 9711 bytes
 .../plot_sleep_staging_chambon2018.zip        |  Bin 30039 -> 30039 bytes
 .../plot_sleep_staging_usleep.zip             |  Bin 27803 -> 27803 bytes
 .../plot_regression.zip                       |  Bin 21930 -> 21930 bytes
 ..._in_pure_pytorch_and_pytorch_lightning.zip |  Bin 31566 -> 31566 bytes
 .../plot_data_augmentation_search.zip         |  Bin 29399 -> 29399 bytes
 .../plot_bcic_iv_4_ecog_cropped.zip           |  Bin 37931 -> 37931 bytes
 .../auto_examples_jupyter.zip                 |  Bin 327752 -> 327752 bytes
 .../plot_moabb_dataset_example.zip            |  Bin 6683 -> 6683 bytes
 .../plot_benchmark_preprocessing.zip          |  Bin 15481 -> 15481 bytes
 .../plot_how_train_test_and_tune.zip          |  Bin 53926 -> 53926 bytes
 .../plot_mne_dataset_example.zip              |  Bin 5558 -> 5558 bytes
 .../plot_sleep_staging_eldele2021.zip         |  Bin 30169 -> 30169 bytes
 .../plot_tuh_eeg_corpus.zip                   |  Bin 22972 -> 22972 bytes
 .../plot_bcic_iv_2a_moabb_cropped.zip         |  Bin 31264 -> 31264 bytes
 .../benchmark_lazy_eager_loading.zip          |  Bin 27900 -> 27900 bytes
 .../plot_tuh_discrete_multitarget.zip         |  Bin 10630 -> 10630 bytes
 .../plot_bcic_iv_2a_moabb_trial.zip           |  Bin 27136 -> 27136 bytes
 .../plot_data_augmentation.zip                |  Bin 22127 -> 22127 bytes
 ...yperparameter_tuning_with_scikit-learn.zip |  Bin 31238 -> 31238 bytes
 .../plot_load_save_datasets.zip               |  Bin 9501 -> 9501 bytes
 .../plot_bcic_iv_4_ecog_trial.zip             |  Bin 35380 -> 35380 bytes
 ...x_glr_plot_benchmark_preprocessing_001.png |  Bin 35183 -> 34831 bytes
 ...glr_plot_benchmark_preprocessing_thumb.png |  Bin 29473 -> 29244 bytes
 dev/api.html                                  |  120 +-
 .../plot_bcic_iv_4_ecog_cropped.html          |   22 +-
 .../plot_data_augmentation.html               |   14 +-
 .../plot_data_augmentation_search.html        |    6 +-
 .../plot_relative_positioning.html            |   66 +-
 .../advanced_training/sg_execution_times.html |   18 +-
 .../plot_bcic_iv_4_ecog_trial.html            |   10 +-
 .../plot_sleep_staging_chambon2018.html       |   34 +-
 .../plot_sleep_staging_eldele2021.html        |   16 +-
 .../plot_sleep_staging_usleep.html            |   12 +-
 .../applied_examples/plot_tuh_eeg_corpus.html |    2 +-
 .../applied_examples/sg_execution_times.html  |   20 +-
 .../plot_benchmark_preprocessing.html         | 1636 ++++++++---------
 .../plot_custom_dataset_example.html          |    2 +-
 .../datasets_io/plot_load_save_datasets.html  |   70 +-
 .../datasets_io/plot_mne_dataset_example.html |    2 +-
 .../plot_moabb_dataset_example.html           |    2 +-
 .../datasets_io/plot_split_dataset.html       |   18 +-
 .../plot_tuh_discrete_multitarget.html        |    2 +-
 .../datasets_io/sg_execution_times.html       |   28 +-
 .../plot_basic_training_epochs.html           |   26 +-
 .../plot_bcic_iv_2a_moabb_cropped.html        |   98 +-
 .../plot_bcic_iv_2a_moabb_trial.html          |   14 +-
 .../plot_how_train_test_and_tune.html         |   46 +-
 ...perparameter_tuning_with_scikit-learn.html |   58 +-
 .../model_building/plot_regression.html       |   10 +-
 ...in_pure_pytorch_and_pytorch_lightning.html |  130 +-
 .../model_building/sg_execution_times.html    |   30 +-
 ...code.augmentation.AugmentedDataLoader.html |    1 -
 ...aindecode.augmentation.BandstopFilter.html |    1 -
 ...indecode.augmentation.ChannelsDropout.html |    1 -
 ...indecode.augmentation.ChannelsShuffle.html |    1 -
 ...ndecode.augmentation.ChannelsSymmetry.html |    1 -
 .../braindecode.augmentation.Compose.html     |    1 -
 .../braindecode.augmentation.FTSurrogate.html |    1 -
 ...aindecode.augmentation.FrequencyShift.html |    1 -
 ...raindecode.augmentation.GaussianNoise.html |    1 -
 ...decode.augmentation.IdentityTransform.html |    1 -
 ...braindecode.augmentation.MaskEncoding.html |   73 +-
 .../braindecode.augmentation.Mixup.html       |    1 -
 ...gmentation.SegmentationReconstruction.html |   36 +-
 ...indecode.augmentation.SensorsRotation.html |    1 -
 ...ndecode.augmentation.SensorsXRotation.html |    1 -
 ...ndecode.augmentation.SensorsYRotation.html |    1 -
 ...ndecode.augmentation.SensorsZRotation.html |    1 -
 .../braindecode.augmentation.SignFlip.html    |    1 -
 ...aindecode.augmentation.SmoothTimeMask.html |    1 -
 .../braindecode.augmentation.TimeReverse.html |    1 -
 .../braindecode.augmentation.Transform.html   |    1 -
 ...gmentation.functional.bandstop_filter.html |    1 -
 ...mentation.functional.channels_dropout.html |    1 -
 ...mentation.functional.channels_permute.html |    1 -
 ...mentation.functional.channels_shuffle.html |    1 -
 ...gmentation.functional.frequency_shift.html |    1 -
 ....augmentation.functional.ft_surrogate.html |    1 -
 ...ugmentation.functional.gaussian_noise.html |    1 -
 ...code.augmentation.functional.identity.html |    1 -
 ...augmentation.functional.mask_encoding.html |   53 +-
 ...ndecode.augmentation.functional.mixup.html |    1 -
 ...unctional.segmentation_reconstruction.html |   14 +-
 ...mentation.functional.sensors_rotation.html |    1 -
 ...ode.augmentation.functional.sign_flip.html |    1 -
 ...mentation.functional.smooth_time_mask.html |    1 -
 ....augmentation.functional.time_reverse.html |    1 -
 .../braindecode.classifier.EEGClassifier.html |    1 -
 ...ode.datasets.BCICompetitionIVDataset4.html |   10 +-
 .../braindecode.datasets.BNCI2014001.html     |    1 -
 ...raindecode.datasets.BaseConcatDataset.html |   23 +-
 .../braindecode.datasets.BaseDataset.html     |    1 -
 dev/generated/braindecode.datasets.HGD.html   |    1 -
 .../braindecode.datasets.MOABBDataset.html    |    1 -
 dev/generated/braindecode.datasets.NMT.html   |   12 +-
 .../braindecode.datasets.SleepPhysionet.html  |    1 -
 dev/generated/braindecode.datasets.TUH.html   |    1 -
 .../braindecode.datasets.TUHAbnormal.html     |    1 -
 .../braindecode.datasets.WindowsDataset.html  |    1 -
 .../braindecode.datasets.create_from_X_y.html |    1 -
 ...ecode.datasets.create_from_mne_epochs.html |    1 -
 ...indecode.datasets.create_from_mne_raw.html |    1 -
 ...indecode.datautil.load_concat_dataset.html |    1 -
 ...indecode.datautil.save_concat_dataset.html |    1 -
 dev/generated/braindecode.models.ATCNet.html  |   40 +-
 .../braindecode.models.AttentionBaseNet.html  |   10 +-
 dev/generated/braindecode.models.BIOT.html    |    8 +-
 .../braindecode.models.ContraWR.html          |    7 +-
 .../braindecode.models.Deep4Net.html          |    8 +-
 .../braindecode.models.DeepSleepNet.html      |    8 +-
 .../braindecode.models.EEGConformer.html      |   10 +-
 .../braindecode.models.EEGITNet.html          |   26 +-
 .../braindecode.models.EEGInceptionERP.html   |   51 +-
 .../braindecode.models.EEGInceptionMI.html    |    9 +-
 .../braindecode.models.EEGModuleMixin.html    |    1 -
 dev/generated/braindecode.models.EEGNeX.html  |    5 +-
 .../braindecode.models.EEGNetv1.html          |    8 +-
 .../braindecode.models.EEGNetv4.html          |    8 +-
 .../braindecode.models.EEGResNet.html         |   31 +-
 .../braindecode.models.EEGSimpleConv.html     |   35 +-
 .../braindecode.models.EEGTCNet.html          |   20 +-
 .../braindecode.models.HybridNet.html         |    8 +-
 dev/generated/braindecode.models.Labram.html  |   26 +-
 .../braindecode.models.SPARCNet.html          |    3 +-
 .../braindecode.models.ShallowFBCSPNet.html   |    8 +-
 ...indecode.models.SleepStagerBlanco2020.html |   11 +-
 ...ndecode.models.SleepStagerChambon2018.html |   15 +-
 ...indecode.models.SleepStagerEldele2021.html |   16 +-
 dev/generated/braindecode.models.SyncNet.html |    1 -
 dev/generated/braindecode.models.TCN.html     |    8 +-
 dev/generated/braindecode.models.TIDNet.html  |   14 +-
 .../braindecode.models.TimeDistributed.html   |  748 --------
 dev/generated/braindecode.models.USleep.html  |   65 +-
 .../braindecode.preprocessing.Crop.html       |    1 -
 ...raindecode.preprocessing.DropChannels.html |    1 -
 .../braindecode.preprocessing.Filter.html     |    1 -
 .../braindecode.preprocessing.Pick.html       |    1 -
 ...raindecode.preprocessing.Preprocessor.html |    1 -
 .../braindecode.preprocessing.Resample.html   |    1 -
 ...ndecode.preprocessing.SetEEGReference.html |    1 -
 ...rocessing.create_fixed_length_windows.html |    1 -
 ...processing.create_windows_from_events.html |    1 -
 ...g.create_windows_from_target_channels.html |    1 -
 ...eprocessing.exponential_moving_demean.html |    1 -
 ...essing.exponential_moving_standardize.html |    1 -
 .../braindecode.preprocessing.filterbank.html |    1 -
 .../braindecode.preprocessing.preprocess.html |    1 -
 .../braindecode.regressor.EEGRegressor.html   |    1 -
 ...code.samplers.BalancedSequenceSampler.html |    5 +-
 ...braindecode.samplers.RecordingSampler.html |   33 +-
 ...e.samplers.RelativePositioningSampler.html |    1 -
 .../braindecode.samplers.SequenceSampler.html |    3 +-
 .../braindecode.training.CroppedLoss.html     |    1 -
 ...raining.CroppedTimeSeriesEpochScoring.html |    1 -
 ...ode.training.CroppedTrialEpochScoring.html |    1 -
 ...decode.training.PostEpochTrainScoring.html |    1 -
 .../braindecode.training.TimeSeriesLoss.html  |    1 -
 .../braindecode.training.mixup_criterion.html |    1 -
 .../braindecode.training.predict_trials.html  |    1 -
 ...raining.trial_preds_from_window_preds.html |    1 -
 .../braindecode.util.set_random_seeds.html    |    1 -
 ...alization.compute_amplitude_gradients.html |    1 -
 ...e.visualization.plot_confusion_matrix.html |    1 -
 dev/genindex.html                             |    4 -
 dev/install/install_source.html               |    4 +-
 dev/objects.inv                               |  Bin 9273 -> 9273 bytes
 dev/searchindex.js                            |    2 +-
 dev/sg_execution_times.html                   |   98 +-
 dev/whats_new.html                            |  103 +-
 174 files changed, 1657 insertions(+), 2609 deletions(-)
 delete mode 100644 dev/generated/braindecode.models.TimeDistributed.html

diff --git a/dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip b/dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip
index 710dc4e833ce9367aa6b37dbb661a1118ff461d2..67d2e01d3c8a9e29af1dcc9656826cb3ba014935 100644
GIT binary patch
delta 466
zcmW;H%PWLo6vuJz`y-7Sm!dQ!o6#&NLXBRD*obk>b+AwtMk!`vWI^sVWMOeOvSDNA
z+K`mRY;5=ogmPz$F~d&z9nb39={!%*C;XZbe$BAAHX=DYNzZA(+Ot=e;woSrw3K?9
zu*TS&zNo=IW90nFiN#6lpyMG_4Ev-NO3yLwE8$>$w;J9u%&^+$jomV=uu_hVpbN_Z
zE3|%NxNMkbojn^bcGR$TevBK(e+9G5NC}oWo2oTWQnAW%H<-Rm1X){N)1QtxR<6%<
z+TdhW`^{W8Dp=kf^U;lRR^6Q$E<hG5Efx8L7@x30MZ<W@LmFp}MT`~0&)Mn`oNiDm
zhwm6rs$@sdt5g|_piilC89|p)#r1(6rOK=ZrE>kjTZBqg6#eRyjVRicDX}OzR4MhJ
zXj7VOeDWQQZw(TqImTrQWh;hm1<G#>9`%Xm3!Tc7?JxLLCz)}KDo$qN+@Vdb;`}OU
TQkdX%%48wIj}a!f2@L%KOJAzj

delta 466
zcmW;HPbkB27{_tH--krapG--~W!ixvJFH(4QPK>v{2dO;!IYA#0|^&7IXoA+%#@;N
zG!9DIfeU8`q5NlNwz(;v$M^K^+w*+;zG82MvA05-uLIfkEIkilYv0yXk4)H#bk}=3
z5oK)5T{PpGF?ssz!1<OH>3xjWqG8L57L*zf4e+osJ|p158Oy(D?748s$~iJtoY)Ur
z(Y0H{nTK80$&2x7!x(G($G9#3ua#mmUWYy2&9<1wxj1CGJ!Y^75mqQ*&J<vWRTeZI
zd1zxb&6s6w46y>+=93%!tk!!oRs|O;KNpo_C}Gu1;JpGhtny_{*TT+PJ%qyzO6A}K
zqe>Nf979T#={Sa!DwlEeD^;AI7*wh(XizFQpWGr;8WR{%r>rO7SEeKr=vAe(f1yWd
zvi`+)G%^|_N>`G@6iO(G0R_r$5?=L*_Zxl6lg)1gRVPI$Oes$0Q=Fkqu2TFeX;Pi$
QI%Tqy=En$=yEMlC0H+eT<p2Nx

diff --git a/dev/_downloads/2b3354037141fa0033174f982871d566/plot_relative_positioning.zip b/dev/_downloads/2b3354037141fa0033174f982871d566/plot_relative_positioning.zip
index 631acf91e5b11cf9a3aa6412e1ac44d59cb3ccc1..99962489510aa538df46e4eb0c7284217610e987 100644
GIT binary patch
delta 49
zcmex)f$8T3Cf)#VW)=|!5IA39wUO7#mzlTHYO|MbUlcP?VDjzd?jV85sw+YOj#&_F

delta 49
zcmex)f$8T3Cf)#VW)=|!5cs;(awD&mFSGSB%gtWCeNoInfyuX*yMqKKtF8zE0H>i5
A!~g&Q

diff --git a/dev/_downloads/36393305d195c3207520572a3b677a05/plot_basic_training_epochs.zip b/dev/_downloads/36393305d195c3207520572a3b677a05/plot_basic_training_epochs.zip
index 8c1a9cd33f9c8e08bf2da52a2a1a6b375342cc8c..c846ca5efdf4d67eea631174146af8468de5e4b8 100644
GIT binary patch
delta 49
zcmey<!}zC%kvG7bnMH&F1PaToHuBz)WiBeW+WbcLtvWMMVDcST50JoQb+=Feg%uD%

delta 49
zcmey<!}zC%kvG7bnMH&F1caAbZsffq%Pg|ga`PM6x9ZG5fysAVJwO7J)!jk?b$1Va

diff --git a/dev/_downloads/3d616473194ad5c360edcbb3e46c7a3a/plot_custom_dataset_example.zip b/dev/_downloads/3d616473194ad5c360edcbb3e46c7a3a/plot_custom_dataset_example.zip
index 08101398122f8963b578a46051fe98b99df6909c..325160f1e6e66712dd12d2790f8f5cef5d84fb68 100644
GIT binary patch
delta 47
xcmbPjGTVeVz?+#xgaHJaE37v1N^ml_R9J1+;Pew<1`15Bl=K7%Og<_Z1^^3o43_`^

delta 47
xcmbPjGTVeVz?+#xgaHKBEVbOoE5XUUcB$oN4NgA+W}v|2N=Z+Uz~rNnVE`ns4eI~^

diff --git a/dev/_downloads/497b39027218ebaf8ffa20c07a0eff8d/plot_split_dataset.zip b/dev/_downloads/497b39027218ebaf8ffa20c07a0eff8d/plot_split_dataset.zip
index 68e87959e215595969869b7e24cdde36d3031e81..8237a91a2b15ec2d0edb86fff7ae4fa0bd5438fe 100644
GIT binary patch
delta 47
xcmaFw{ob25z?+#xgaHJ)E37v1rtvZNR#<H=<9jB?3>26guj&92n7l~U7XVE|4x9i0

delta 47
xcmaFw{ob25z?+#xgaHILFSXpro5shyb*bg%GQMYG%s_$3@v06Wfys+heF0`K59|N{

diff --git a/dev/_downloads/4a2751c5805e7a17be8ee78ee1f2d520/plot_sleep_staging_chambon2018.zip b/dev/_downloads/4a2751c5805e7a17be8ee78ee1f2d520/plot_sleep_staging_chambon2018.zip
index 399c4fc5bb8a4f8743adcf0b23e6dc9240b7247c..e9ae4a472f0d8d6621995b6a1d08fc3db6837ee6 100644
GIT binary patch
delta 49
zcmccqit+j@M&1B#W)=|!5Rj_0+Q{o^%-m3EwK>u_*pV41FnN864@hA0zmiA*ZiElM

delta 49
zcmccqit+j@M&1B#W)=|!5b#=Nxslh?nEB8$%gvF-!H&#8fywJjd_V$||CK}n0E`Y1
AQUCw|

diff --git a/dev/_downloads/52f5b6b37eb9b07c97027b1eb0fadcd4/plot_sleep_staging_usleep.zip b/dev/_downloads/52f5b6b37eb9b07c97027b1eb0fadcd4/plot_sleep_staging_usleep.zip
index 85cd6dcc8d2bb7d34d33bf10d6c11539a7804747..c544bde84b56ce52772e27513b5ac4b2940e9fb9 100644
GIT binary patch
delta 49
zcmbPzlX3P<M&1B#W)=|!5NNBk+Q_?1pSh>fYV$UI7aL}vz~sN#?jV85?l~a<cJL4`

delta 49
zcmbPzlX3P<M&1B#W)=|!5IC{SawG3Dedcq^EH`h{cd=mx3QYc+?G6%{?4A<>0GG%S
A<^TWy

diff --git a/dev/_downloads/568f264ca0ecc135d137fd575c39cf8e/plot_regression.zip b/dev/_downloads/568f264ca0ecc135d137fd575c39cf8e/plot_regression.zip
index d00b833d27404519d5b8e54178c05fcf890ba0ed..2b2646e72eca6ece9625159a4769b4922c42fd36 100644
GIT binary patch
delta 49
zcmZ3rnsL=?M&1B#W)=|!5HP8*+Q_?AmD!@gYV%Rm2z_Rtz+{C`TaduygitR4NiPko

delta 49
zcmZ3rnsL=?M&1B#W)=|!5C~gpxsi9PDs$vg%gsksBlMYp0+SU&Z9xK)6GFWJU?>ja

diff --git a/dev/_downloads/5e85dd7b06a544f298bd1837eddfcbd5/plot_train_in_pure_pytorch_and_pytorch_lightning.zip b/dev/_downloads/5e85dd7b06a544f298bd1837eddfcbd5/plot_train_in_pure_pytorch_and_pytorch_lightning.zip
index f61dcb20f288886105e46f3d0316d2787c6c76b9..e3a8706fef0fed258d5e6249091276b1bb21d3a1 100644
GIT binary patch
delta 49
zcmX^2jq%(!M&1B#W)=|!5U{AQ+Q@s|oY|qmYV&jR8BWYVfyqr(aUg-okE^l)i*69k

delta 49
zcmX^2jq%(!M&1B#W)=|!5QtoAxsms}IdkGt%gxWtXE-qf1tvFD#eoDSKd#CK0HQb&
A0ssI2

diff --git a/dev/_downloads/67cf91b203bc10a20a2f8703a04849f8/plot_data_augmentation_search.zip b/dev/_downloads/67cf91b203bc10a20a2f8703a04849f8/plot_data_augmentation_search.zip
index f83abf50a9d2c123c3642b6d48d693a24770194b..75ac2ecffb4ef166a6bbe393b657ffdd3f4ed129 100644
GIT binary patch
delta 49
zcmccql=1pgM&1B#W)=|!5ZGN|wUJlXi1~bl)n;3xkM_(!fystN-XMX=^+gc?k|_}H

delta 49
zcmccql=1pgM&1B#W)=|!5O}iGawD&<5%ZU&mYZ#jKH4(_1tuF7d4mKd*B3<q0IKH_
AI{*Lx

diff --git a/dev/_downloads/6b30e1d8632bb747aae46f30c6993983/plot_bcic_iv_4_ecog_cropped.zip b/dev/_downloads/6b30e1d8632bb747aae46f30c6993983/plot_bcic_iv_4_ecog_cropped.zip
index 5b7281934db7010ff9fc715e3ee216644c9e812b..d6ce49a17891b1dfbfb7bb5b7ba8e61cdc428c0b 100644
GIT binary patch
delta 49
zcmZ3zf@$>%Cf)#VW)=|!5a_S4+Q_@zfq7Gf)#l?4`-7N)0+Tx@dx8WeU!5EV0DwIa
AiU0rr

delta 49
zcmZ3zf@$>%Cf)#VW)=|!5ZJ!dawG3{2j-hgEjJ%`*dN3U6qwvO*%Kr%`Re2_0GSFB
A*Z=?k

diff --git a/dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip b/dev/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip
index 1abf603dd4676151440886f1dc719d2bd16aae2d..1e23c87b2ffbea7ae32848dedbfbe19d829692e1 100644
GIT binary patch
delta 467
zcmW;HODM!q6vuJ@|2bKx(M%>ukt7z9=Yl_FOj$`}2;-SYHt3&{88%Zhd4!O1N?|pn
z%*IF-l%?5O$WFq-LSDOh7&Cs?U46TqbGx62&mQsFEuC$|_6&7yJ;td;bCAVroY@?Q
zZVG#hv+(|H7hNI(AL%OE@ERA(g_^60@=*_N?Yf<OsKaAztc8|Q^rmgM&<<*^Tn|;#
zy2rR^9nyQPw1PUC(GPOTk7^F+@gj1d8iV?5BdwxBPx^#~woo~r`eGh!qP8>XJC_0|
ze*yJbsSfp6LAB2RUAsv^C)MNbDom4=RDvpbp?8z!7VwIT6J=z>opp($4U~n-I_GgG
zfhuN{N0n9XqCBXqQWN80WtH6+_baP>#dttbr9F;-R8Hd90#vdSJffUpCb&m2C6eG?
zrIg|y?p8?g{@@)L<z5AdQk}#wgtC@ow*ty*k~@@7>VLUU@nrXxr~kL~6q^bs^C`^0
YCO0X36*MVLV;wT_r|~hs<T=e#f1bmvtN;K2

delta 467
zcmW;HODIHf6vuJ*o|A<djof5Il2{<GjoT<@iUo<hjrS`XbT<~*Op&rv$|;4_l`;yG
zW}}piSy5!6BqR%YEz~@W8Na{(>f66_{{258pAqsIj@Bk(BSoEW+dOn=b>!MH0~vK&
zUb?l-z|qEK8$BbI-jn5Yv1108bG7ywYDC?6wbN!gLv8J9qizbJ=v7;F(-msHSoc>@
zz&3;R1A4cU4p7_E`eqjSQMF5YG>=A5E?b{*(ILwJppQE!h|2uX=d<Y;wVFy_S+tK@
z%%L79b)oJ{smk-eYglA^s26u9M>J7J4XA=Adb7wtWwvvyh^kP|1rD23f=WB)F%N+%
zR+xvCRj$L_udGrT;X!4UwFvhrt9(YdPf?{gihxx1qSyjd(qlZNoMOeeQ!ynJ<8Gyt
z{2%U6NSXV=J21+P3J|3tj$sI8CC*+2l$SWSD4$gSa*yK4+AmN2Z|MoP6i#Lnn1M~s
X6Zk4<QkcX#WU`pV#{iSZBv1YUu-Low

diff --git a/dev/_downloads/701321eb74424104536be933ed2cbf9e/plot_moabb_dataset_example.zip b/dev/_downloads/701321eb74424104536be933ed2cbf9e/plot_moabb_dataset_example.zip
index 561d3e11f2bbbc7baff471fce6a1c9f3cd10cd7c..d4aa651d15f8136b0852b5af22ac7fca576da3c7 100644
GIT binary patch
delta 47
xcmbPjGTVeVz?+#xgaHIPDy%m0N^>%IS6FS<=JXX{1`15Bmh=D#Og<(V3IGkn47C6N

delta 47
xcmbPjGTVeVz?+#xgaHILF16gqE6vHgd8y@QZBAbSW}v|2YDo`}z~p0+p#Ub|4hH}L

diff --git a/dev/_downloads/7ec8b4809f7c475073a9b5d8ebb962dc/plot_benchmark_preprocessing.zip b/dev/_downloads/7ec8b4809f7c475073a9b5d8ebb962dc/plot_benchmark_preprocessing.zip
index d0cda9686c32e3326cc54a07dc223ec185be512b..d3b8ccd8f658dd26b9a215c3d2a613e67fd2ac7c 100644
GIT binary patch
delta 47
xcmexa@w0+Az?+#xgaHH`Dy%m0UY25RuCUttSn9n3Gf-giRckMhz+@$xZ~$%{51ar1

delta 47
ycmexa@w0+Az?+#xgaHH+ms)P*y)4DNW~t@o$5QVVn1KS5uUdP71STulgaZJD-w@yc

diff --git a/dev/_downloads/975f746daaf2fbe1dfde86e12f8d5031/plot_how_train_test_and_tune.zip b/dev/_downloads/975f746daaf2fbe1dfde86e12f8d5031/plot_how_train_test_and_tune.zip
index b61ddae47c4a1cc9e028a0f9b8e9a0964612ef86..cd032cb801bee97f16a006652eb7ea9df813b689 100644
GIT binary patch
delta 49
zcmZ3slzG`wX5IjAW)=|!5D=`e+Q=)A$gEOfwOJwYegQL3U^3GsFOa}w|4ZQjJW~z{

delta 49
zcmZ3slzG`wX5IjAW)=|!5HMb9xsg{Ok=bpj<z|J%`vuHEfyqplyg&kz{V#<B08?uZ
AK>z>%

diff --git a/dev/_downloads/9f417c6133a57e14b27122d013590718/plot_mne_dataset_example.zip b/dev/_downloads/9f417c6133a57e14b27122d013590718/plot_mne_dataset_example.zip
index 8a0f2063cf9f02f6f2f4ef8a252d5051464fb7de..eb721f18e740fcbde4148ac512579d4629fa861c 100644
GIT binary patch
delta 47
xcmdm{y-k}pz?+#xgaHKFE37v1u4QNLsIc0+mpzJ?87MGWO4JP`FgaN?7yv0%4J!Zu

delta 47
xcmdm{y-k}pz?+#xgaHILEVbOoyOy1K<5J7bd)cFSnSlb6r9|C80+W+Pg8@R14u1du

diff --git a/dev/_downloads/add1a85fee267a1849d27de66d7d8a6b/plot_sleep_staging_eldele2021.zip b/dev/_downloads/add1a85fee267a1849d27de66d7d8a6b/plot_sleep_staging_eldele2021.zip
index 5220f7898797e83f5232431e8881998073747633..6853870e3884335cc9067f128a7ee85ec6dfb1bb 100644
GIT binary patch
delta 49
zcmccln(^jqM&1B#W)=|!5NN2h+Q>WKn7OUeYV&&IMn`6#z+~f6Z;-&`#?lA?k5CYO

delta 49
zcmccln(^jqM&1B#W)=|!5ID5VawG42W9AdfEH|$=ZggY@3QRUG^#%z{ZY+%e0I(<$
AH2?qr

diff --git a/dev/_downloads/b5c94eb60270f5ff2f26d4d743e7c69d/plot_tuh_eeg_corpus.zip b/dev/_downloads/b5c94eb60270f5ff2f26d4d743e7c69d/plot_tuh_eeg_corpus.zip
index 05c9e2c1b4f5a372e9bfef5350cb4ecd94a9962a..9f0b93f5eb7bdbc72264840f5372c5f8d7241afe 100644
GIT binary patch
delta 49
zcmdn9nQ_l%M&1B#W)=|!5a_A2+Q?g_&OEWwYIB$RTtjA{z+|mRN07keyhuL)X>Sih

delta 49
zcmdn9nQ_l%M&1B#W)=|!5IDEYawBh*I`gGvmYciO=Nd8t1tx1nI)Vfy=SBJf0E#FO
A`2YX_

diff --git a/dev/_downloads/c3317f5b839dfe85c3fa27a60420173e/plot_bcic_iv_2a_moabb_cropped.zip b/dev/_downloads/c3317f5b839dfe85c3fa27a60420173e/plot_bcic_iv_2a_moabb_cropped.zip
index 5f34e8755726fa9a08e5b5c3ec9f4d035144eb4c..96177558badfb1c41a88628fc7c8f52335eeb778 100644
GIT binary patch
delta 49
zcmZ4Rg>k_bM&1B#W)=|!5GX3Q+Q=(x&dgO|wOQFb#EBUwFuAJI8zeCKL}dg3Q(6vP

delta 49
zcmZ4Rg>k_bM&1B#W)=|!5D-~vxsg}coLOh7<z{8`5GQ7!z~rh*Z;-&`6O|DFQy&hO

diff --git a/dev/_downloads/c58c35b5588d025b3e00c7e383793f93/benchmark_lazy_eager_loading.zip b/dev/_downloads/c58c35b5588d025b3e00c7e383793f93/benchmark_lazy_eager_loading.zip
index db556cac4fcf821af8686e9419c6702e3f29ef0a..41f969ced19cdd31b11a331d12326c6d7c952737 100644
GIT binary patch
delta 49
vcmex!lkv|@M&1B#W)=|!5OAol+Q|FRfEh?{{%DY54Ps1=$ngTxOLM{ji}Mg4

delta 49
wcmex!lkv|@M&1B#W)=|!5J+5Vxsmsw0W*-^{LvuA8pN0!k>drXm*#{60HVDSQvd(}

diff --git a/dev/_downloads/cec1d60200f666e0fada2d86280a2abe/plot_tuh_discrete_multitarget.zip b/dev/_downloads/cec1d60200f666e0fada2d86280a2abe/plot_tuh_discrete_multitarget.zip
index 0e7dd409075a18ef287181ecf38cb6b0e4c167cf..030d6451d0fceaae3eaaf0f74a1d634fbc32c963 100644
GIT binary patch
delta 47
xcmZn*ZVToO@MdNaVE}>N3agF0u>#Ef6;_*b1qvjXfdZ2sXn2DJChKWN001UG4T=B&

delta 47
xcmZn*ZVToO@MdNaVE}=xOD#9@#tJZRUuwBISD-+G87MIMfrd9oV6vWO1OPuP4%z?!

diff --git a/dev/_downloads/d323b5e4b5903c1466d0e7674a0bfab6/plot_bcic_iv_2a_moabb_trial.zip b/dev/_downloads/d323b5e4b5903c1466d0e7674a0bfab6/plot_bcic_iv_2a_moabb_trial.zip
index d60a8a910b6ffe88636c39218f03a6574f87446e..946be9ed4f55b4c929025ff2ed5e8c6d6d29a988 100644
GIT binary patch
delta 49
zcmZp;!q{+ykvG7bnMH&F1h^`!Hu5IwGYeK&Z7$S*WyuT_m>ies2@;sRDl-fKK0^)I

delta 49
zcmZp;!q{+ykvG7bnMH&F1ay{KZsbkWXEt7Hxw%mPl_fJ!U~*ihCrDuOs?0C|Ra*}b

diff --git a/dev/_downloads/e824ae71d652d80edc1e0be50f3fcab4/plot_data_augmentation.zip b/dev/_downloads/e824ae71d652d80edc1e0be50f3fcab4/plot_data_augmentation.zip
index 0de25bd90cb510ead4b47ed9381deccca3ecb1a3..c6b86820f3fc569c3818773b3673d675b701a79c 100644
GIT binary patch
delta 49
zcmaFAhVlIxM&1B#W)=|!5ZF{<wUPI#3iIv?tIbbU-WxCj1twn)bpZ)XmJ1660HNm*
AlmGw#

delta 49
zcmaFAhVlIxM&1B#W)=|!5V*P2awG3m73L>PEjK?^d2hfB6qtNH)CD9kSuQLP0J_5x
A<NyEw

diff --git a/dev/_downloads/e920a22508db3ee26e946faad811f57f/plot_hyperparameter_tuning_with_scikit-learn.zip b/dev/_downloads/e920a22508db3ee26e946faad811f57f/plot_hyperparameter_tuning_with_scikit-learn.zip
index 7c37efb882ec8ff66edcf7364b6d66d46f686222..4432169d81e222a4a576cee7328d76df097e31b4 100644
GIT binary patch
delta 49
zcmZqs!r1nOkvG7bnMH&F1XL=lHu7?sGn-UcZI(1wb7BSxOm?b_0trl>UzrX7IYtd$

delta 49
zcmZqs!r1nOkvG7bnMH&F1l*QdZsg@OXAWCxxmnU&&50Q(Fxjax3M4Rjeq}lUP+ks}

diff --git a/dev/_downloads/f3c7c35609f54876319e72ff42b71bb9/plot_load_save_datasets.zip b/dev/_downloads/f3c7c35609f54876319e72ff42b71bb9/plot_load_save_datasets.zip
index b7771d232bd7c25a30dc69426bbbf07fe9ab434f..6eec897788a079194a36a2b4c567ca1d3495e703 100644
GIT binary patch
delta 47
xcmbR1HP?$bz?+#xgaHIvDy%m0-sNR(udv$umUprkGf-f1vx+N7VDf2|AOJsc4$1%k

delta 47
ycmbR1HP?$bz?+#xgaHKBF16gqdzY7a!&1x5Z+Rz+F#`oAH><dU1SX$W2?79Es}LRl

diff --git a/dev/_downloads/f56b29a9031a522f5bcdaa29212f6171/plot_bcic_iv_4_ecog_trial.zip b/dev/_downloads/f56b29a9031a522f5bcdaa29212f6171/plot_bcic_iv_4_ecog_trial.zip
index 1f07592e622a51d9e2d0c31c4962e486582bbd13..370405364cc002b6ea0e2c5ef8de4955e4366a22 100644
GIT binary patch
delta 49
zcmdlog=xzaCf)#VW)=|!5a6w}+Q@s^npvvSYV%|34Zh4kfyvW4-9ZAAA9RKQ099BI
AUH||9

delta 49
zcmdlog=xzaCf)#VW)=|!5U^fmxsms>HM7?;%gv9iH~2CG1tw4HbO#Ace$W{L0B}|i
A$^ZZW

diff --git a/dev/_images/sphx_glr_plot_benchmark_preprocessing_001.png b/dev/_images/sphx_glr_plot_benchmark_preprocessing_001.png
index 2025e00668234c0d8041daee5d855351083c9e38..ec666f820aa45e01e5fdaf3bfd70b3297ba58640 100644
GIT binary patch
literal 34831
zcmc$`2{e}NyElBHA`PgBGDNc`3WW?IN=2qnM21Q!bLOEkmQaSMWQZa%mXgf#P$Y@W
zWGFJv<M%tC{on8U_WSPdd-u22yVv)u^{nS9xBI^C>pIWl_)W*@b5==V4dW(8ilWw>
zJRzq_QM6hVMH9fV0)JyE%pHpVh*}@lvQ{&@Y;AkV(wI7P$=cl1%-Yn%V9PCIODhwz
zn}_y`?mxJ9%T;S@b1Sg}2X6e27wk8)ymEk7iLMcEveNv7wiQJ&T_XR|#7Vs}p(rn>
zlXAz@?Vb&^*z25`S)w2QvG1=VKWluz_D44Ym<{6xDt-4Ead<woVXta<V7&US;4Q;y
zfk}z$X@|C5xb-l~=!A*hVDFSd?w21b7L{jS{}>xN!Zg_H^hI>YYS6MZyt>!PPlkb4
zS`PnQd!bT8!_30M!YX_^#T)<B`L1NcA0Ivu%;&>Ds)u%H{qwq#W%u#Z6Q4u%@l%#~
zj`e%VkA)5I9LJAiF8}}e%cJE!>vu+;-DTccv@$+XIYQFh+<aF`sHDfh<Wt7_7YhFP
zS<0=yKkuxK)v`1<myVEhj``uyA)a=raD{r34#)ZP=LLj?_w||AMelNEIw&RElyPG&
zrb%PhhR}n?6+2rlUpg1FF7e&<A2LyA+iPP_E$3onq50rEC*m^QL0=cALMJaTpOTt-
ztiS%v4A+8hOOEqq=h^XNGo#(9mfebpTB*^Iva^xdj#CANg>>i6ovZorLm|_$yC(M3
z#%0TvZLq$Y`6%p&u@Ww0mu3>D!_?pdFD4!~YrBYGI{LLvljRqE?yQYGqMd2EJxI~`
znAfpl-|TFOb?eth#l}vQzt6t*oqv9&H=?gO^H9#*pm<SHkv={;PA^xImX@~Wll_=7
zx7xAm%^w8Gue^DqTN7o}U*xm?EPt@p2XkJ2^|-S&9ZogPnO1_AtJv-A?DXfSM{tRy
z3v*Kz<9#Zot)Dn9Uc9)R%OGjZW|7r;P9w`z)znxxIel68oYP-gT=?L!AZB{w#;UzZ
zMMZK!yGHC|*3hrz%<C+^FV(-Tf9!~AvD~p|?f3X%RegejHuU}Z<MQb5_HEmw_4Jkk
zP4`Ic+Hg<#R$}Y-Y)9MEVF#CcdU~pA=ejJMja6jDpSLToJm=(eboJ`hbsRkk<u{IQ
z+O%o;q)QwhKR+WS*&wvbU0PLj-T3&p<T3TeQ>RW9j{pAlHTw7}PD!UDmGf23yG=I<
zUvp2+nPsGE-ka&ECu*@2dafz_Xwxs?GCxgwzu#)H*~Rak`ueEXNjjOdW@cvWn>QEM
z)G&X3B3w8#)@y8YG26l8>kEa#;$m`b0wN-w@82Izx|sdM*m-Gj?tqweA4Nw;r=_iZ
z=~vmq6G}>7REJt5wZfcfd%lF<$1RF<ni;M6`Za%}p3`mD#hIOzqZi)a^hi%XWNl-k
z^5(qoKy#*Aw~KC;?T|bc(536wS8;K11s%}i{`N{)!NK8U;>ExnXU^h<?w+2}Cf{C?
z)$_YHR`AM~XGe!@Z@oMnM(ZJSyXn2zi&KyH<MQOoA8i+Onl|6IeS7&I{tb-NGc);Z
zZ9EzY=RExU{H%X3{r>i<??*C^Vle-5e3JT`^Q;M)$szk9>>HgcL-tLNl=57<abpd>
z)7$Gm)+#?gT7GNkfL@Mo$%D<ZdU`xki_=@(e0lm87v^55$E((S|L&2Hu&4gbg~!Hi
z2bX4TEi7&)CGFq4Z(m1ucW|t>X;;aEINdA}JR$v?H~nt5d^GmyZOwKht2Ob>o2Z0@
z``BZVxFy~`J`ewJidrtiDszvI-@SUx8kKm}?Yl2;nakOU{d7Ajiubvs^S!lPVtIHz
zAt52`5)RfO)kT$$4}49~JV2gXUEPM9oSY916R#B)w6Fb0+IK36iZm*JbhR#y1s^@p
zYJ7XiSxH7#77vsuG%PIYQlV$2m?vf4QLy~&weO6VFJBfA5Rjhu^F7tPLq<EitJMF6
z$_sh?og1#`=X<k=?IlyiTix@jrIvhg-B`msXP$}_e|~y6z37oHPhzvv5Vw?zFN#fh
zj;+^Pu8K4z4N37KRGqwE<$*L5t~yQf@Y=O&uYP;E2H(V8%;t}@vN99C13h)rX_{Hj
zbwRl5^XI7KWdGTTenV`p#=)sJ*QE#XYOkWLf7c2eJXoNq=j;(0%D!#qPQxN^mXx%#
zJGeEolYi&(+XAs9nNm|z&24R~Z{-9Be|LOLfAEQ1?(CmEp--R6YHDt@`BRtwT*5J}
z&T(N@Sl*YNMqFIHudgps#)EOX`>~$Un{{SOFRLS@cqS(&YrcKE>*Ym%v-!hFzLw=E
zeoRXh6ciYBE5@!nbh%18?4WTZ9^mEAPdcz1YUj%XcgmhRwd%mdPi1LeZqv~h)YYla
zW@lUfUUyVN;?ku{G!haLN5sUU^>SU(jMMt>##YP-rO$l{J9I_hTHP+K^XCil@+dCx
zTU8<%cj=iF+m3JDy7leNmh+Rkf4;q9VmokgZ*h>Q^UZrLtcgz#n?;i+BO+45BsEX%
z+qZA8UJmD(Cql>0o@M^?J%N5p7ro(+B;D!R{^X9nKJVV@2t!oG;o)KFt5@T!!$brH
zS+K=r?d*<tuGzfe!i5W_4JkCG{ydtZFY!b>@I<F4o6Mrl?h?52h12>^-AX1N$)F^M
zziqiZx>>h8?%!X9ukF#-cXfQIjVJch<8vmPum4E$z>|=FuxYuhtSqOL3nzB2jH&5f
zmxT#U?H0V&&fY#s?UhnrZS1Oy8%>_6hNT54E3K`q*P6^I^0%CvoC4SD_db(y<<4DN
z6pw!KBGqNVK|31@v1=%I$ulB?XYby<?d|Pu_(CsS7G_mxFPoV7;BG~`E-iXLcu?%k
zvel?RRM2q62FB$jeq8tC;&$!TN}=$56i%G*9!MU3d_b?DscCb|M;qDd=MpNf)pu{(
zu_O9q;EoTjOOo^R^X<4>Z!Wx#Mjy4q67gi>*}tzX*VQ#qH;WBdI^FZsEFdJr6JMia
zer7CA?Umn#O0<)&=w?o1pAXxObS`JxcitW4qN^f!4;t%nMMXwD|A)_>`9{fl75x0U
z32$AT<2*M!J8?ZUG_<|v^HZ`NUTY@%p}rkcP@tb0YAeO6khB~4_U&88@83QS6MrrZ
zHfJ7j7~h3gdyRHi8V<MTQwLr0(5vs?-*~_Pe~i<~Ja}uUb&Z~0n@)E1&^=#YcMlJb
ziizCC+3QC{MKASKg)z%eXaBO(a;&`iROE)fq2b+*La#zx(fgY%1-PP^slR<+Ukp!9
z%A-FE7*}k-tua75!FEyrs0fiVNV|WfHs<6s`t8@(8hc31$j{He+L*RoRaI5}r-DX~
z?a0W;^l0S)fF$0(l~_y6?CiTPJm!xGA0W@6|3`A^mvHe^>))#En>Iz`d)3a1+YUxL
zP7RXvCa9lBslQfVi4CZ5cg323fB-j?s3?>$t@k&%e!jczb)zXG%COWg?MBrT;Z+U}
z4(x|-at^lT`X9f~b_{zD?a|xMuOw)<n)%|qJ$Ys*`k_K5s(z(a6%~y5g@!EK1D<QS
z7_F?Vg8gh>Vj~r_v~Xbsmwd43(%08_!@}FlC1#yB`L`*yVg0&w?HwJrUnxg)Hksuf
zZ%i|`m>kgd<&omX7t~78zipaLz7pO=z^IHFJ?BzKfd~2i77MdBLHrv0nu4@>Se}&8
zyv1lnWBL{B3_3tE`O~LY<9X2W@bKt-FsGqvP{B_>6<Kp3!}NAUM8sPiEE=*!aIZ+!
zQc+PMHyLe3@MiOo&?iqiQNbIqf9U-q_<O&dmi1ce5f;X=L;1O{f<O1A{5#8s$Hodn
z_Fae(+bm-0mYjS5D{!RpK<*Y^UK;et;{X8`-4(1yjvQ&n_bN`mQf>aLj0H7-_ebei
zAj|QxC&Jg4Q6s4HzqDTA-DOZAj@k`N^E*xsgrNwpd$9R%NX4T^kL1vzO&e2E1fpKN
z*ow!!BY2-yiZsRSy0q|KosEa*007n&$~!MlI==bG56y<ArpkJH>7c#Zs-GMt6#3h-
z9p6)1CI?&g1ZRHu;EkT*eb}t^gz-+LXUvpQf7MAD8JUnYv)qMqef|CSV`8?&R}~h@
zQp~vNk1HMp270`E_YS?(>iML&c;HTDHcBq*)?cIUHs`5uY70;be=rR*)<h?EP1;8w
zx{V?tBAs}`fx))@^=GjAPRwy)fl}VUwf7quwBlRQZ1z#!9;-H9Zd@|13@NV<%go(;
z_-0TAR=E4qr%wfhgo5fF=cg@bq*rei*;^^OCs>i!o!OsTV%?J`PYg<YInri+B<pS5
zt{4<hk*t%+N0D-J*_OeBS*9vNN{?bD{UKGUr`Hq(ST!s;Ihoorw|5n<9R7Ix@6UI!
zKLBPnQbl)`uZl?<AGaPs-?^;)>b27Iqq{dSdW0Ua=%nwz?4tD1c4+?|%?b9Gv9T)^
z6cjF*nH@mAG`2a^#>DF$r}DxRopBwIOHc*54?;phazm}zQtZm=>OnR2^=!DPkT+AM
zJgyrkcU*&d$c(+yoOtw~shh2z>}lN^-d%sJ9ugY5i(fNo?}b;`zt4;YyRss7J32bj
zNCUT*RVetf^HSa@geQ&7T0gO1qZQ=mADiX++&pyc`)dMr<8Mw4ws^=yF{5y%O?=GE
zj2~|jF{#}~BhAjv&H%6}Xjrn^0)1)kMA{s;(DnM$A3l62bD;}XjJ;YDdE4C5@=?W0
z<%s=&zeO!sw#NOOhi^Ws0m|v<=t#TKhr)<uruo_y@P$U&ms4~!d+w3F@44iQ`!0U6
z<3*d_F*($B08PbRCMw{|jj)N=>hXM7HL=|r_v_%HV-=k;zIpRzG(c|J-+_iy*-87x
zOsih{>TnsOc{YGQZHG61W`xF?n?KoGHBK1<;>xJ0seN);IM48KBvVjWn3ZnD>VO-E
z4<1y-Vk)cfTFt>HIkn-XmN3i9SFgH;I|}=1qUg{Fb_O>!G(=)^9&w%(GB7lxp~S?*
zYHDf%LL6sCW9#PEadPh6=h&V{)6mdx;%_$<2?PWP@tRW;UHsDJ%R91f0>n`#Y#$tT
zoLr3srhunu{COWYH@CTkg^I~$GrcJLv7R-Hb3;->*XkHnu3QO<mXVl*j_fcwusgfH
zzFr<p&)7CK&M=oozbt?^?FTk?aQ%`96BE-Baq&~h9?T6n&f-5aZmi;6M&8F{bbMUy
z^l9G#XIeL4*21!~6AlaCHTCjKN_JFcSX)~YN}=6|%hbPd<H2A{)+u9<ICc?J_Rh{u
z<_#N`QRMxwX6vd(GpbHCh~FA;Q;nB<ykFPI0`;V@y!_<HO%LsZJ8Gh2Pn<YWHaTs4
zF}4vz==se^cA={Q12!+@9~cc;NlR02-@X+<Z-_rFE4#IF?&WK=_3^&1bXarK9bP=6
zoUdM&4&yE}tXfqF1dukqyTVBd{G55+x;v82vt>zc>d6<m_MLxQHab(b|2YaU-}ddx
z$=4Uw_~ghs;jBK>x_sHPNFdCsKa#@LUjoxRx>DaI#qEKf7?hQj|M{9{-`~{L{`Lm9
zbj4auZ#+z1AtCj1xwb>CX^U|{&3BpkPFbmEJ4_7!DqkNH8=HOjC2*_3x0h$)w9|JG
zyc^*%yAn)V{>}M!txc;J{(Rp<aFXsv>xVAumvGBJInAtl{`~m|+aYd%ea0;>9OZEj
z^zr=XJ_(z(a{m7P`-uH$jA;uxRKUCab#E?g#OGE{rU!)s4dvI?uFJ^CxZ3hjxU;J(
z^=6CMZ$`V9XzUd?L+qxSX^c3BR&CsWLNlMr10}k3>lW}JHJsb_(0Oi>S6Emhmfgxq
z^0Sb6yL96e0sbeHl}iD=XpD4j;N68u#S#C4Di^1jd@*FtyNE1<VEt^n5n3#^IFO+b
zdyUuXw^ieVX3cg5E27x(C@Cp{``z~NSdP|Z@%N{&HjgJj<_n;0?VqmcP4Y?=A^Y|?
zhKHFRS5P?BL<Riil6c+PZ8g?&#(JQEWyg*kgmA{j#*P~<-i#oW!>Ezx(4j-SpI3!S
z-pZxP!xEbONEl{KO&*@AQ8!jZ+7DFNJnZdMgJMRY>WY_DzxrC%CJo&@6?K*XeeDd5
zkJi8U+S*CD%(LSXRcpiJK?iG{wsfiHym|B2@hLwRGd=IJXV0Fc6}j}+@7sM771no?
zFk`~GH+S%D&`neAMhqI~zQ4P!`5`N->#14Jv3S+knl~2?&o4~1@o&Enwoup_(lTdi
zXc!n9=z4K*|9yXd1)#3sp3j>HTC>GZwIxp3Pc5K;Uw*FsS|cH(>*JxetY<D8$<8Y(
zEzLdryvpX&97p=ww?PXd<C3pkhAJK(h=^^?8uCIl{$yvHd&scjcZ2a4*QTso+pzM;
z@NnG_%UIQT)hg7=QY<`XF0KcKUQD<z+#f8v8L_dS#wuTVIX5*V%WxZ-(dC)d#*4Ru
zW<>E|xgnOM)m45v*(IAROr6E8+nXya8YX12&W}^{4#D3*Uv`rN9Dr=Wv8`TTxTH(W
z-2MF4&Mz#`7|pj1HN9t&l$5OPErZAtE^b>=7q14&a~mki5RGl<FWuv(WAU#?TC;4K
zq~#;hZT%;JJy*4ySyi0G6!QA=muEh>B0`NqC7s0x1&oTi&9YTK&N*)RnKPeFD~p$=
z{!VKp>*acalKDP(Ab8`a5RnN!e*DO=c5Mm3Q2KzfOX--TsExYQlu~R}D1j=5u95HO
z{C>&1w6Vsj^MlTq11OvNPc-?ILK&)grObn8u^D<(Ny??dn8j<x6+yS3Kj%iT^#NoV
z0NbIVp=n4nUX?RHdWwiDrBmz5W}Lq;?cTk+uP%Oll5UnK%1HL%j&h}2L%FX@1*CqJ
zUXg2Q%VKiAH7dh37yixVwc*l(2M>rU^Y-djT2x4aW%uiR*rFS6f1$^$43IlrC%7^w
z>;r$WB3{B*nvewHL|s%~1MM)*+UpH}X;oF#>Ki}b-p<XH+HvNIJ5VsMsHpa>cS2S*
zwPU^2hG+&ytoxY3nZ3{j2s61hC+WPawQ9-;P%kAT1G0=22cL|F$DW`5MkXdJot>Ql
zn|4-y0@wg1m7U#l4OHUl&$qi5=f{+_v(aHH#d?1>H9^4G%q&y(=<YzqLrsukYD<>*
zHnm&ELt+-4%P!_P`GBxST6C4D&Scrf{1Vw=GcX0I&&ZV(q=`o{cJ!{TJic;4Ss4Rr
z7k}HIh?yTMJ9w7?vnQ+aT{biG2W>nSuU?U4U@Ve+IY*(p@^LA6(lAIYXR<*sp0Er9
zNb~FQ!hz0C+Kn4Go(>hDxl;YyBP&ZB0M|3Zb&*3_K2SIP^5>dF?L+fm5uu`1J6vXe
z?_9QGh0FL6HC!~q>eW>T)jjwlvQC4$<N8W~orfVTTyadR+^6Ax2^fTiI()OaY(&c_
z$5wP<zm}GklR3L*l}&S&t#ZB2XlL=N#_#U_#<*bAn!VVmt^Rn#b*ySirTeX1j)4fS
zg$m>ak=V5NN{%wVGtc~UvOp~?EbJHG(6~Y2VrvLIO7u-^iY{C?d79Vi6MeAzFUM=<
zx;WP*>+wKX$ODdU@9Me>(n<<Tx$5D=y=of9E_!bg6D92urAo6_v}q(hVGtG;{+ecd
z3M=@+t@uf(bq#M#)^8FqWiT`}j33N$6}{2&QR7-*bseZ0P{ZlTvODhX%ij69m|nkr
z9}w-*!t8|i{riCxckkRW$Nw|!kC@RcY?=#v^ytp^Qz5@Zci8;3?Rk?C212`xs?}8!
z{aRNi*ZU<r75&20%=OD)eOr~d<3X&(HK0R0&1?awxep&cOv}=(t*uSLN(RSMJSmIc
z;C0VKK}b*BIyP+!F#$a!RLtgDNOdSPEg<SLs;H#o@^4qb2HG`i*8HwrfFze@`U+A4
z6*(HfG1LX92Qej4CsUPQjXzks_5BownDwp<(?)Wkk-(rlT<are1rs$A*f_bkQuXs`
zfziZHNo;vhed56;;S{t&?Qp>Ob|A8=-(P>H?=orqBnnhPu2TExP^<1_DxpZ@zttKA
zXiuIznKng#_HX)&{b<w$#rHQ_3^t3#@0FC~-g7R|?e5*Xi9<0TA>x*0%n_-Ewk)&h
zPH-^m6Csm3Sie`Ex@RwJ2BX;cOx$)Yk-=1lCi;J9`%R!+81>!*U+*mNSjE3k|BD_V
z7)!1Fv7QT*n}C5otN~x;rUs|_WOKJ>iblMy`1WmmNl6J-^yLia{8ks`gG+t(Q;rLw
zyB}$$0O*GQ-MS7Eg&$Uv_NK#qSwlIpKI^upIL%l>9;+;Q20>vBR+A?%K=iS@D~MK&
zf^F;?PMhaOLpKcg9|`pG!D;58si`SS;EH!lr$w!LPQNv4;~pFw>}z^YNCh-e*U0nl
zuBFB75nr=O$PHA}$=O-Zv_W9k21by^ju%hn>)y4Y-UB^xefspt9JkA~`2&lD!?;^Q
zLO=cEa0y2dS~@zF<ckuk*#)RCU%uE){9(Ow_bw#%uY1eAGBZW7aJ_Mvomj^p)->Ra
z0kL<@ZxN)0d-?*R3As#w`IH+?BF{vvR;*&%8z5GF_{Pr-KwJfohy0)-<X2X%!WMs}
z6fOhU)zRBa#FDPw2-lM7k*<-xuUoDAYG`0s5TpolEeNdR%Pp}9pu`K}QVygNqLG`J
zm^7qZx*McJoA=h_oB8OklhENdp^$jryI1gN`>C@pPjhI$>iYBt;QmkjoBQ~1ZiqGt
z-4(&9SE{*xH@NgAmn~n#rVlaN+{)^1PL8C=&E{QC+fa6nuG#eZk6;}D3s%V2j2jn-
zg@O&`@!-Lln{7D{pd~2otb!2A3f6>QmW2o!duh|@)2G!p?H03IovNLFISLvbmN6?d
z`#V^FJ=c!hW12zb`{zO7F0i9h;eoaf4INlRh0VCcjW()0Mv?AF&Rx6%{hnxk5I_<y
zykCol29)j?;&T5_5agB>Yc@p!>kW^N-U$!qx|r+o0CHak_AcQuC{|%zqgcN3Xeu3@
zop)&HRz&J#TG}nni{fT_5jM7I%DgI6up#{l)6cgicLBa5p$2>V`<G$|q~ggPbr?S}
zDXAHEmIgw1QG5PfB8=fy5uG~oW2$U8HswDs3f~1(FQ_Gvj)E~zh`U~sYN$XeD%fT|
z!2Tsu)A?2@0d)y%lZFO%B5NdH%s!iNZl863{TfKk3`|U=5N10D2mK)1(@B@GJ4%<t
zO#xryjpd+uS!REBn%I3)V_yBB+49dO4x_((m}R`%+x4Nj5dq!<YC2kC{1L~=L{nW<
zh0eL5Tp}UJfDr)p-M8xfvJ&hGbd)z?ZhFM<Ym%-wwCe*9DT`2Pj!R3sRTK)%Lxk0y
zTt3vic8@zV9xq$)9!)mTzi4bJ1Bj5(c$;X;?h2lxB5*ZWaHBRts4A$hKQ}*I$kYjT
z)Y!WJ;=60#_g3a^cDxCxBkcVhFHg^V@O2c~IXG4V5o4wAgu#{0d7oF-(<tjX^ilGE
z43M|slWm9Ba2y@7=pO5y7_qSTLQ4}r^bBBh6;xCx5+04#bsu}6vi|Y6#Va=x%-V7w
zbjw_Y8?$laV^go)Cr+JO4;?W98e<w!4{&#(qKa3(=^|nUp5%rVD^@_hmWH9Iy_(~o
z9KeMF18))F=W)1Ma_FxfNl8fphYxSW(q#oA4X(EsXb}90r3cSv&)awJJl?!{)7P4v
zHE?V6nWqUnhq85!J#(WO8xLIc=9X|^fEa$sz<_Ud{P)%`&qTLU-e`|k91~kxzs%(X
zVigbRO1|QyQ<v}zQ;LuT)w{~;3kCG{?b~q|vp;IRz4|cm3q&)(hAim%q^L%tZ}EY^
zb=%c``&Nu49^2*%aOI6Q!2p#b*wf_fgyYn3hwRsnHrJzGz1j&5Qw+>-V9hHFh>P)G
zyd=d%?b`&_KuY;?D~z6r+nYQPsB?_Ey1FXhim7I8lG@=_3of>O-p@RL%+xp@aA%H>
zk2gS_hz4vdXl=a+^ML_iOeOvDnUVhF+zL;DvO&iH4o4t5B5u`y(m|YL1NdVBKnwit
zIM(xkUCQNC+}Wr*<VoNkQrQh457(xwC+5Y|!^#bfjVobpeT`Gu+E{Z)wEQ=F{P_c~
zoHxjLWAidn(Ga$@dzRDF-v`gRpJrUih!<ZnHr|dcyLG?r$88CZTkKB;kC`Y9S=?&#
zsItUzC-)wf-Eln0<8Y9TM!;`<0Mr=aIs#WqR`PC^%=O--siUiVe5~j5DluOjweC_i
zUG;^peBX`zo?79--C65Vv{WMN=s2)_cD!{;!Rpwml`G2+)^F-gHuz4TAaDvuzxInO
zd~BU;2UfTlyF(-6v`(Bp9h9vEDjI$KzP_ocFLn*<S@q%{Swjl&K0^-Zt=+kEXK=)T
zba6GQ3h*~FTmr@~9ZzFAr!tO)E(G2z;W+93=FL7*U-8}ZfBqD!jP#QGBV^ro78-ZK
z=g(`(%gezb=)XLdxDV-_t?#bO{RE|Ou_)8VG>B;{3=9lXEV|^IbDS@1>h<osfg*eS
z>eXH6618Zgq;jkO9Q%EoYki_j0dP9_eF-4lFd!pju1K5y`cMhSTOqw_Eb-sa=Y0Us
zFSX@3pHNf;7iA>?q%r+--?x$R@gn>hYPLUAKL|30xQ%^aUB|rSBcgDpNoPdS*T}Fv
zthT7aFtSqKe;YIoe)$Ia|Cmjf(~mz9uigo@8A>hx2HElTEG*9Z-I?v655cJ(vl(uz
zUb%iRD{ji(AJrOokLV?P^tk6dA{QG3@>NxOUYvb?)c#R_?;gN9)+;d7Qqt1{zr+^P
z;J1uLR&Cn6`4EXmRNU>XD}HGw<h~BCbC&s^LJ+A;Y%CA&1t}75fKhC9bhTed2%C_w
zFqTF&Bgs#&#>B*I*}HeOVr*KZEbr{zuqRJok9^d!F>>W0u?wCp?g(it!>?Sraz)d0
zh2l0<4`w1ZpbOJd5Xv@~%SF)d&|1DlWH;+bxk-xP*UEzj_;#?Y5ZkVwn4m#DWKp>V
zBnlgWg5CrLd873axd<+aY~L|$b@dI2iHQw547V(oei;O+c4W=+ecUhQe<gXn@!0ch
zCAlBnz2xukqgA_P_#8AH9K<N;3m3B7w(`z88841Jd{QyCF>hIa;C*GK!paXD+;bJB
z-?J{AN+ZAgp0$@{k)P&3mnw6_vvYY5*L}@uc<;XJ%DhXNVE$~8>FMzldwu61;UAA5
zC06?Doh;YTwsJP*){<)KktNTRGgP0Ix}awN=)3)IQEf}(>lMH5dG9)`^y~-?+-{;T
zTkqnxAMay<%>{{E{o+eFSnPrZayi9ve~OnSxHUZabIC<hQ@e3KDd}{QcU;4hgT{;-
z7>|ei2HjlF_2g$`V<RsgA1&6?p1!k|LJ(qwuGUbqv$Ow}1!3gEef`zgFX!8Asc}xk
zvhw?0t~Q^zz7v{^&m4!>WywD8Y`**Wgyy|FYk#M!y}PD?7);qqaK(+*TGw91$FID8
z{W`)BGp$t-U=x5Hn}AdH_nl?jj`wZ<yY{c~=ZRG3l&6WxY=L{Dqj$E;FWa<e$=Ra$
zyma_8Z(q*nQSwKc!+fJRo}%vEh2aPf{cM`iNwS?`GEr_w6VRj1yFrfuI3hL;I=4w9
zdPO8SW!gmS%a>?kv=D;m0|e6+61CIe?J>ZE{qXUl0p62`)e2Y{(&fIVXg{d{zvuz<
zB+QbLArC!2#^Q0>7@GRq8%=Ega>jADETGYvEW-Y1|ND0hh%-zcMuI<qeI6%hu`(_{
z_vXBZAD6fcym4qt07CwXm6w0Wv2WPmj@X3^>^%SoVq4YL{yKaV+E#vbH4~Jsl$4Y_
z7>T?^OY0^;Y9MW`gtoCu<MoD|**^(7f4?=oR0_ZMaH|45)9uy$yS{|#I~%YF`e=*2
z{gH9Fx^_f@&+{akiVBPQR@%FVS8V0maq=8DN1%KD=DTCt%kO!6OGAwRnye?){Ly9=
z{1s_n<e0z_;E{G%D@a>(K{bHnE(48=h*XrDzdsY4nfo6;95D$8i@`dh6}vUSK!pll
zXRA-v^G7A^fU&|ZYPk&(vrlB?784Fx*}^F$Sa+%>u87G9I?q~@QVvt505TNxmI%&%
zCXR#4P;H@OZcEb3_0w~iA;}WT4Xe5f78UV9EPmH+hsV&4iU(WxRFa=yz(aS4v&$id
z%i{V7JB9|??H~bKaGYFl@kYINNCsLTt^W})=I6(%(;R>s2^}&Y={&wy=L2)@!sKQ=
zo#oUASn`0to?u5Ez^x1n3<0_ePr-ZW+x#Jk>Xa%q&N(HYVN*dNIa@1WxHtU0_}eSD
zoQ5(wk1B4uRw(UdwnjxIAZbJB$HN;Mg;y|AjFj4xXS7GUu#j+_?NdioE!3Twc(t7{
zyy)Bp6pK*!cPHdRkOVy7+qH{<h&g~1a5hq`dX>iid|ySSn0(toGACGp$kCKkg&iXK
zqYs&xG!*)p7oO0+EPTq1=~gEeQAl=<%fiPX1{ycSY4%_I<PG3{(iqsHkdUDRIn%Vz
z9@1vRkh}VtX?4XUq7pvD=eaI_sk1;ERnJ7#_%CET2oDSlm`@Grg7=JM3+BGT9R&;%
zck^A=1F%yH@{1@-?5LQV?;d4H#?$z91j^24S{f540$yx!%*nu*SM<Ofmlo$|&hFX(
zEqEPyvUqxipqYT-Ubk=409()j!{LU!Ky;v11WaQ*e_L&Ry@;lT+7~;vr6OOOcPUAF
zEv5>V?}fh?hM4tRZL^K$`(@COuvaswbq6I^w5`LSVb6!)1MwMuu{WZ@gkXM<`*=RX
z)Q6;;uumzH4KOTlUkRgZS#)%C!1L#RkUf4g%3~>z(Ao6d+zTuo!bt#sQtihsQ+cok
zAA<cr=qSs0`sfj#csv*iucn3OYxR@$RWDz>prZ);MB3;MqzOJTvGWc)j1Zo979O6S
zcm-UM{ivP5S{_MX?1vYC^T3>96j_i&c@hzH9Bx0Bv@WsAhSm*t0_tU3lXX}iQa|~h
zKc5i^34)dd?PC~^EgE=(a)XXn`3Fz_61+Hw@Cx_Y_US`;0!JYH7I8GyvF#KRErrd^
zM}MTMw5Ir^Q0)EJx{rJbe&E9$xF?!#+n+OE$~7+jiC0upTd&~9nV)}`zGGm(7e0BE
zYOEsYFC8^KJIl9i+cH=JMZgLy@Jc|kV2m6;?}e?88s-U`W#H#K;<MKVhgH2S#BJKT
zZJXQ^M2L(RQY@R~;@-S@z{tvfA`oN|mIHXxN{COm!$jZ8$KIlmW*chCnd#X~(mkY3
zg59XRQsUZs{_Tl-*+AfFA7o`@%z<`wY~y~^K3clCXTv>O$1NWoK4gJBF!Dps6?W4K
zBuVZhBqRt~FMrA)weKRpM}@*U`H$D$Jl@RcK?|h<5rtB$Lvoj(J{y2jAF=9L9kN&Z
z4t6{ZMc_<qpe+iM{*^0U`z~a(gL#s0OssoBV<QL17*^@yCv@q7O*;w(fbup&mMR)(
zOb7Cy-|`~&s~1_`HIc{QOEH)D^Z0|p8GsVUL2$}2Yg<cC?^WHiKZjrAwf@}XUuKyT
znsFd0WW6JbApeg;*=QNI(0edqK{HxzCFx<HFQo`YUAlJd9?4lj!!qTYFOu|EW@Axd
z(fIL|Q)I_SZ{L#@89X7hZtr~d{}Frr{&x>_qa(Kl*s<PM?%A`4WCvh&NC)$4P!zgN
zZMZ$a8vCKkzT<hV?<e4pA<|X|JAefyckpHoj!TeRNWBIsBYF#BR76Pu85*9LSROEk
z?;f=80^84@KS7vSutVKJhV+5lhjcF^YekYF#rIfQ;46UYnY6*}yn`DNP0|~%;Yh*_
z<^sX3T0jK1kH$?ykSc_cEdZR2ARZ~Up-1fxLf6|qkxPqYmcoNg9&q>BkRl<Uh}}a^
zHM}?D;g)pr2AC)WoJN?ExQ4Nc!PKuDAAzGsIl=N}u=l{)VvRC^p&Lb#A8|fq@bMmf
z_|lU$u<7zRi^Ka>jy?V5H^RUF%;zfmaL}4aI7q8NS1)p3xn97m^{AbrBOOJ=ZaD>o
z7g!{H-xD?xU1ZOmguVR$7{>tb6(8?kV{2>M_z9sw!_Fcf()r*a(;hf*fOrEio36EN
z1OXyJlYhk;FIPW*01G+CHVi19FyVU%2F3TZ(u`KR`6dW~-yZ{zB##eLwlBLN?aP-h
zRS%{^BT=3;%|@^5%DYYX!ES^PJWB9t%@z``TEF9T!1w-^tivGqgjV8Rmw{N9;*~TM
zexL9b;!nVWTTY%gv?C8NiJsjA6h@)gl6#K&LaP4nFQ;Y&JnS5)H5Dp|W&t=cuV4S7
zcKhF{q&>TZo0JBnO9a*q{8AdXKM8)KrNs_8H7eoh`<I{GHnX7Jsn>V3l*nxiY!WL>
zc=F(*%y!{0y!jmn$hbXD+Dq7cq%{!Le4plwB>m9b^SCk2^I99GSrZY^Ae=h|Twf+C
zk7%J|5mK&x(1`LtWC1;)Iu#J}zy`q*lBYpTWF4RZ2}?ega^0V>o}1ebN(ISbB1ep6
zemaDvS<<5+MtwRd$2+MqeeJH<0UHA2ncBW@WO*7iTW+{DdcI5J^NLrcE<U*{>Pic4
z3J?Eqn>`{id1{AdL_9#L0XFJP+8{c@C4fTsjUlr^Dqq#w{|VmWDZuFK+&kvZOaw5p
zEU}wNvMc5N`^OLDS5sRR{EA?Xr`q(NTef_82MQ^Cp+F%i2?;Lf0`kc55K0LWcnR4K
zB#~-&HkQ6G-ubG-SVu8LrKyd(Wx-g7u`^K0c~n7e=9HQ&&HK^qUvuP5NSm9yd`vY0
zlsy{hP5X;3s6V2u@juYZN!kyBSFmSPWOQ%(H9qxS8yaBekTfp!!EtIo3K7}5CvKEM
z42AViED=(Lk&e!Tq5vQA5%)^-xyc)3%|M@*h5T=UCIz)~1r#Y+c$pMM))Lm%2#73{
zAXfnqn~SYZQ!1ikSsx94g(ReXZJDXL5?$>j_Jkqc&gb4eWc^Gt#?al;{|=pNNcB0J
zl$WfZt!!y|kSc541z{grM>_(_)WH=Ip!!56h!sQqkSDP!D8^JCHcoqIC*O8WsvV*f
z@;Jy{94ft0T2fN6!={|`oy6GJBjJyq8(JQhQ+G$^xV&V{!IA%7Ijix6_D-!ZpIV5#
zq&gvcGLI0}Gyn{;{38QNh%VqOARw!rVT$j@%)znyyS;d3#j^;}1L6?I?)dol2*qcG
zH`l8(;p<gY^w`=M<5T3+mpRq1gxbY+YoOsaES!SoW=^bBv~~CQ@86s11k58yZHL=>
z;v1HC-N!}nM?uR<4eiFVeVXakPCG%a3wqO)QYfN>B9@U4J_5FU+s%!F*{|wg{_5R3
zVKC$v1sWp<=%`TYV#S79H9}{^(!XROWC6)z@6)>O7D=rp`mB?mJ<M$X?M;8DE2kU`
z3k@aD6Ue?0Dp3v8G>T(oC@vS>d&l=|tKPK$f3Z71Wo2e|092&Wn{y*#jC$WFxlKsw
zcu`qk!e_ev7a7@^iOS~)X=N$g1~DNng@0I~yQsMMpI~c0;$80U?s@p?fc(YSftL`v
zglyD_w<J<CmYo~CINGukpJu0q{E-~U$7}H^>@aDXo14$(x;RtPSWX0iAZv38Th80p
z_n%5^R2HD@azF95(#jyAst?ykKn=sV+Opmp@qgs`Q=n$|@Ow{qYNLu9QqXc}wp9M=
z?}v(NfS6r0^6@e#zUWxzU<w{1jz|4NM3%@H0Ex_uPfQ#y_2a@*bWi*O`azx;(f%Nr
z{UhW;iQ_NjSic@xBEmcVt-YZ|8%73fWHJc<XBPC?&6B-`Pc;IuewIy}_)&aUiEXGj
z)|0tSOzdN%tjb9(tx$x_bTXqy4<d$RFg@Hc!}hJzp>0Yoytk&HGkp_%ztuU;(%~)9
zt2ycWzhRn!5ftu8?0nh7t!YtqX;u)rgkWEM{rXjVkbj9Y7KtIiZ4g0epLMU_X`xsw
z6TViLhXy)&_y`3`T7cbSf$W)_ygcM#HV8OH%2EqKT@4R8=}-CnJu4?S<6F(6p-Xrw
zxPx|BW~M#O@jzEdC{~}!|5%Y7k7x#|9<2Q8d0??5RfDvF>+rFrpr{&a%bk4uzKo+Y
zFa9IvZZs@eoayBu{xxo%fS}-QnDBsSvBr+$eYa7`E9xIZ_FT1URia)lw{%IMFuKli
zWG0|3=YRjsig%lf3q2LIiw3elV+=qeB;!cPYY?dJVEsFc_wi;~{MPm7k&?%2@$gn4
zfKRgd=>7pcZ67S?V1^)iCr3gS$V$#*XJ_8ih&ro}uiDp;x)sm5<JT{D+>yAq19;Y;
zC<y=X1utK|JPO5=q)_0m08%{e4$FkSgM8#&AD@*F>IE!1<vz7AzcVUdhm`Cwq%8q8
z9z8dIbOAV9EB*2s!YzQjqhN#}axa8J@bJ|Hs{&EGMpceUxC%i=K~qqG&TWpY$g?9B
zwBcelkCaN_Q{09b06F>rJbJ{PRuVT6gqxxel^{V>H02l@ZZT^T*COA-&6g$&H26Pb
z)?v?{mp&GS`*tFB;pCY!#bhN+{Lvur91BARlB{K-6v?3O+}Q<KNt`~HneL5nU}-60
z;~dDHUnhLMz6fQ4nVI>Y{4^R!rdSCjVDm@)zmr=_BSH{s4CFJDKehGf(W9m8h6V=r
zetj=;QcKazWAyKAIOgwt(8+Y?)T^&6qrV;~^;l?dCjTvtRXAXr93g+j^;=~r=vNxG
z1>#PO>H?6}B_pG4BsS{K%!l9-EL3k0i&HivqV)0BUw-`c?%gLzW)#uZiu!K|aDPRx
z?DquVMXR`k>!QwUar;ptgiLrr!DD{kKaf)<(h5aMfnp|MMj4~OzXs8XK=>a0O#}7b
z2+j}`EMY$?M={$DHmh`-ujF;7w(K|^x+UB1{{8h-5eSylhXJ$@*ZC0zGP)6^&L1m=
z=FJ8O!zUr3%kc1Pc{XxJX<{JFtcXgn$S}Z3zXcy_FA{<2Ej<{6keYV+Wj*!-m+1~9
zua#<W+;6T(Y0z@u?s2)G>Q-*g?PD`9sL_d;7qC;V)+ci4=;)AMiSpZ-keqV|)~uUv
ze#p+#p>FGUDs91-5Mmby*99c$2kla!MbeC<4iMt;n4Y#H*%vIw6;v~_8d!o?zeanQ
zW+B>wxZ2C{kAT*h_p-ni(=KOJMOp916wGe5mxR?KW9_LLzl?JC^134ayaUFufZeb@
z@-ggSH44BJD%lP;RNnUlO+q|$zdAGlXdzT|Jh<z#&Q1!lcwR%pboQCYqM0`RZ0Hc!
zt}zFJv`NcB0+$4>X(&9=$KNfitO^m;AuJy3Jg>Et8v@7O$B#F{W{&AOwdKWu3m225
zC7fqBV7n4VhYY!!&H+80RG$FvzV*{})jZ$p>WZM7A^LNS$m&Sq5QPHTAVtC8BRv_c
zisZV{<cJM<;^fJP^&OCy@SJ#Y2ccfwK`00xNJ(E4!@ZJ%6c)1^)=@pvp7&?mL6_3#
zw>CjgML+=VBFU`bCX<SZ>8ACR(MZl;<T&zy*}tN8>Eya_kuen588Hp0c6;uNgN37o
z2MWi>qoKK2-9cRSQLgf5gl0gDreO<_tUkazYN>`p?a7Nz7$PJbJz?w<>xV27ngNZD
z;yuvJBczq8c|Ira(ULAHZ$+>j)EJ<1-N4_!snD57gbf=ppO~o-eyKcQmNe_pn>CR%
zP=Qj6E7>@Y+L0lgcR^=yt7IWo!rO!-Rwn5AUfkk}Lhyx2c!LixL}4&F&<Iz6F5qih
zpDcb^0AywLCLsoJ*;2q`K`=h#PFBGl^g>>uLU!A)_y1dVj5dX=p*=?KM4ucs^TRw1
z8EJwqsQ|4K9}vkjc_{teyWqtoV(XxD5~~GC_0a{6yyKsHN6Mj`7qmJr_CfS!&+L9(
zHzFbRC=vQbJ76pc&_nSjvreCoS;YRMp-}Ko+V&Kelo-IXuK8BENfxy<#kBEYbGG9~
zScj^akRhN2Kfv;liC2%tFaqYZ@?j7Gm95s()1xxY_^On!S}|Gp0NM(X2rx&m0;%Q2
zR%0?>gn$Q06rjfgGX_mMBY3NYQAQLhKOUE9nx38>GI%0l*6NE9wUgx)uf|(!+em_+
zU?<F@nD>6+I{o}82V$U)wu|6tunS+?kh3s(VHrI=S<0b@&A2Ij_(^ut!@Qdg-&_qd
znDdA^1>6r+fHoj&M*&n<GT;KnQVLs^z<HC_-lLz2uEa))-)3biPQA;`VmuwHG+2Fc
zr%_YXLW|#!s6-2IGE^RqSFc{BynVZYxYeMsWEiA&9x^+Ta4@{K2MNg{;6ab<?Cek}
zSC^0piWw=1v@hRf7*PI-fm{f2cL#tb?}EJn?Q@s1AW2q3g}*FrhL8qHjT0C2@ZrNG
zJfXdF#8y0WZf3>@$qh0L2(Y;u1#A01kz{AYRag-@+W_86TzKL)gGS5zEJbtkW(wz{
z@dgF0r~t7o!pe~Rklgs-mkWT_2oz$58#iuXxNjc@gZA`W55l!4P?6AVQiGAPEAp3G
z+*R!Kr*1c~^zj$&xMboVBLY}SZ&<F>vv}ojw|jVV_mM|g_wIG=dMg*yVJL4|4SYxV
z+#ZcE%?v2ShPt^QIZek89Yl{ItPr~XOxhwDbODe+xcB+_q*3R!c#nU{7O6>W^%DtC
z|DG7kc<InEdc)c8*CL0Q-SC!0$gNJ=Q_vhq>IE}?r<^O|`YvJWIH($OspaX&G)Jek
zte?<kT<S(4ZxsOIq=!!tIUEfMa(KMZ>gB8w|5$T%rqEykVXXflY4Cd|e6~g_KOh6o
z51(jjYYY1D_Z*2^4tDZi8h?&<62gcOls4J!S!^2=t?Bl=X}`z*8I@*ycK0qF{3bs&
zAQMKhqNAGuoj^*?)m-|u3xEm9AZbWR|4Mmous(5|wiK$~ta{MzysmWVW~;oE4f<^q
zqIP|8lB<^H$Cx1Z&`=2e9Y=eyz^3?}Y2)B9$})sJepIZ+5$*#<SFbX_ez>!Cs{-r=
zthayoh3n${owcvZ+FAGVMJw}KGo?gsN=aIilI>cOyXv)ZP;Vd<iF{0<LF3$|owkkC
z9dt&ps53-##n9gR_3JSeyyeIdt@9bkEx?gYFm(oXAbt(_4-MIAgh68d1rAmFpFj8T
zj@`S@fthF_<c{eo>~T=u{<pA|U|63%b0!sq7Vjwythu<j*eH^XnHdUGk!fkD0a1Vm
z7%M%FHkXQKq*I)6>+g9o@`D^moN6p1aw!nxJ-odcf<s&nD`Bh{HbxY<5HRjBWZi)7
z0*o_JcVD14kT*hb1Y!JbpYNk-L)S%$0bvGuc;;}#c4*E8m*?lxphlAM5SaXrUfG;I
z_Ybzc(8t|A)G9r2$ll&mPTpQ}n>JPku?Fz1y`XlHRZTLm?#z@MhIaCP{Md*}Qv%hW
zAaN*aWQvfYFyb`OlC=?5M6DPTBJj}SNw%9JgMNf95S0Nh6tw(xVtk-cErh}7Vs^R7
zCglGs=7ccqw3<hf6Iq=*s6>jDP?ilbfJO%Vfa*O^hz+1SAy6A$(X`wRZ(S8Gz7Zo&
zdFUN1+}zK*UYJW7fh&?KNd}T(4CaFYLW(IQLem7sb?%bzmS&R9?Wa#SBO-kty^WUI
zq4dnVrsgc^hGaGlx*QTFy!$TTUQTh_nwbq9EmnGMxSp3q#YOcc9gQK4x9MfLKwI=V
z&t|?m|8&(>K0Y!f2!@jn#6l5K<MR>}3F8S(BnGf#Q58stYj}Jd5fz$SgUvqR#Wa-2
zji2t&3G&hTv4)9i<Hs$*h{{MwV<gXfcHD$;H?U1=IN$GQ*crFiFnyO{iZ;g5nIbYD
z6x5yjdNIR@t0yl7z~N8ci8&SAX4!vIt}ZSvp&~cVCmECr*$(RXa*4BHEQF3CdI>rd
z89Pcrv_1Yg;&5WNgR3cGsUaLbj0|0;7mtfHlvfg3#b;8|AqlrY(4?<jyXGhOsp*&E
zpHdu?uuDop^65lHurFm0ak<XQG$!No|5vjHxRQ=i4BB-YVH7f|0OLRgWAK=6e1N4w
zN0Es?JZ$h$nT!^QJ#~rNY7V+lGRxonRl9sJ>NR#Srqw9e6{Uzd#*89UrgPZicYpt>
za#j)?050a&?5EtIFcA|AASulf=o40@#<`HN540RZ3ZQU=%~5%%qr^Q!yL|!mgQ$R5
zn_IqDpMD+RE<lV3WsB<X7nF}9(|W}67XwlI0Q5*}p8owRg1`;LmkY2th@$|Yi9szU
zbTzm;y#H>sfD|#avU)&DB*W0au^b(XuHT6EqVmz&q%p(B+B#;*HO|Tw(p)OgN$_Mj
z#E{AJu%EAuR*g?;Jgs8K3MONs<$p}B^$cF?$m06L3b+4;t0IWA-TbuRTFxVG_<%@w
zX6y%z7_b>uZF%7{JknJvy1xxMAuRP_HIEB>$+;I5%AT=x7Y=MhxS+YEh2-Z5_QXO)
z2P;Av#=NJBW3P7FGSFFC>ZtwbvZaNo2-6w(1$ke-ti=o?ahpaEF+1hsNhbZRt(m#G
z_Y2csRtP`iK9u(MtsK~!J2R|8?F=|<yBmJ~?8G#{@W@E{*sZ#9g!wSV0{_N$;6pg<
z35ch`-@)0A5_q$v>va?Ipd|11`Tg6sm|Z)7EGkJl`EneRS4?S;(;6m+bad~WTj7>^
zL*8rBbnepbgFQ`$%PwDR)rDaKNk|sE0sRkCe*4>@xRA0+5yKsoLmCgBdGqG`7)>*B
zto{4-1wBcbL;2$q5ID<^L9YS?C`hq_jv{2*z$_>zNSr39p0SH({+RMPX~L@_*&q0~
z^m@({tk^q*d1%*)fM;W5a5cPs2;DM}MX|cwF%}I}&fjL>7=e$}AN^InOE2f>wYs?5
z05n@b4A3Fc9MIoA0|VE?d$@!8x>ZbU69ij2>hu$#f5wR*f{+*`Qluw`_7NMWsz_-6
z{<Xv!I&p#l=>`aI^A_S4o~=|piGeO^3*t<SVjK8oi=b*D#}tQ*RaFz?%|SMUwDKk8
z60<W)dbh0J&)!*ZMTai<_Dv0QG$bUZ0<MvY#FB}Nxp@j1enx{~h4EwntDU6TF!Uo;
z=|GYE9Ppp<Sdd~YnUV$HdPI_JBsPdQL-BJ~9{|3lbpw-RlVM<CW7|P_@6k*$iqFDm
zFibb%jFXO3jHl`jbeZUvo106f8cF62E^jo_tOj_JwN4~|+28-v@aXmWL^3gymIeUG
zsG%GMZo>wWT-y)1KoCfU>?M+ggr;AN^%*-8HkSp<oj58$@B3io7GpQWiV?O?*g45y
zHaF`a3VrdY)AZR`yR^H$19~Faj+|1zoZA9B?bd2AsJJ~S^EmN8jFd5z$8UY&hX3!@
z3A~eF_rdZHPlx}m9V&^XNp5tr5}#P6Xm0?k5<@yYO;_=${$ySU<^4A-l-|yNdv{~B
zm#?qdoA(>;S^+$$ooPR|1F*Ix%hv2&@&$(5m|E!suSpZ%6K|&vL^vLQ_3CSzT`Oko
zfFg=PjU=ye4P~hv#Hc@J9Ld2JQr9-CPm`L(H_L#Zq(SxhWSAUkKn}4PXBiz+I?4ZO
zdan$A{=b}TlbE;uKl5+8Iy>8uvBqE)sa%M4Yd^p6J?7+k<iZ<~C)%PNK0ItrveVGa
zF^^h+#*Mxh(w3!wyioDk+qRbe{{CJd5(HDATN;N+;V1+$69@Og9T1Xu>O(nmYspyK
zk3rYFV`~r}2Wber*pF(y1O}jhr3X;|074J0n-*=|6Z$s>io$ZmPmoVhx~-Q#IyqTF
z4y^zJy)3>2Ul)Goacop_lmI!Y0jn4})1dF)e*Ex4>QX3MLUjNY3A*n+h@{alEa82Y
zKy&+N>?^R#2PXyHs0i9kR%FElkA%ZA51EmCdgE`sZ*ZfSOhBl?kM9Bx$uQhTttNbu
zC`jMOrl!0QSb{z0iO0T`m-pBc$Vs9Y^odlDUy^v!3UmVD=L1p+8BJ%Dl;llK6HVbE
z%y+c62gD|nHmSKtl=P?(A@W~n`YLt-gc~wp2Nts$Sb<Z_Ixe!1f1L4?&#){xi~!$|
zh~>LfqL*O~I0dKj09a|g{)SUP5XUIQjzX@6SUm(+V+@v#A_fT#4>^$x2RprG5J(X!
zVV%>@J$(G<9vQg(I+7P-U2iX_Ov5EB{o~iS(g_Y63E&EmX6=?2-6YTa!K&A<Zqvx1
zemI~qw*KrdiyoW~(c!4zc;M<z<>zuh*8&(c0I)Sc;OA;n#y*Th<tfZNxmPbT)<YX1
z1N?YU^uS{!5P*mu$SL8V{`wFi`*zrx!0b>_wQ^k~2zo;L_LqGYHj)DBn-J0IxUyvB
ziqEL7PDwqKlEKP6mh5z~Dwm^sv-p)dwe<f+&>w%FOfyh<IBo#O8&aNkaCQnNRcKMD
zaQaU{TboqV%lAmU=YjX0%fRtP#DfDuBIh?Cu<$6Mp*~4>6)+;6BLkVJgh&bP38z#=
z)s7C8#H;iFGyAq%Z3S34$)=Lgy}h=O_DO<|ywSNgo8ZXC*h6$cPrZ$rN0<pfIa<oE
zYq<vr-H@6erpuY`T=lP$ArSm3fQ>o!R<dFkRvPRuQZPnvI6xHc6^XMzi>Sf0BLMc{
z(r##g^b`>;s5}rH9M|ypd$|+Xb@*Sgf48i>y)E~NuJv}Mk&~jW&sfxZ#5!hH(%+}R
zF&5ZW_puTD#d@ff3vH|rJ}Ei7ikvbc!$9TzR}yJU#WsC4yxX>IJK=o!3JxNHRA>kl
z2HR$bydS3zM!zf8-L6VFEP7_Bb!0&j3Undz_!a<kSURuY`a+%~b95YsF1JIzAUK;K
zegKX5Pr4N3(mV(yBoX-RsQo&kxqvh$)ju@(?_d&~U6^P>H1|PJpK7a9{TUqo6My2&
z84pj-qfB*mb?&P1RTi05ezy_$qA2WcC{=Vg4+7PcmLlf`!DchRb?Zw+yN|b<@8x{S
zxuwUa-`rSZtwS@w89MT_ir3KP)@LssUereT9)z$#45Xp<@84fL4^u$(oGW-ZIj00C
z$B>K`N-FeOeXwkjh@kXQY{^s)!t?=v7+_qT06>^ap`(KKXs#uU4>}F*5l#C-^>4a>
z1gVQS7~tXGmY$(QP(P}WMnC`M>sJ=w2(26^QD8NVi^|uo@e@>qUj*@(pEt5i>Mg+?
z7rZr~MP@gsVRBT3fB-W_e8@psu?`?DBn3d}<LD>E_41G|@*(mWJ{MZ`jz4wrbd+||
zPc8^wxP77}!#TZM5jG*LlLQE#Px>F+V0VXg<Hnu3CbVw<!O!%7l?56|hhQj*;Z|hx
z;Lw&Ll(K@d8*Zl|j0{|soI&#8*56HJbwOfz0jNz8&y%EwNURAl8q`dmmFstq(Rxtv
z-2n?bq78~-e2<o&UsyW)`$V}0$2+rHG#ZpU5@*G@8JXU5n)t3MaOe<SfCa1T{}NjJ
z-|(QatGrmN(kP`yO=lolPc*6YTFo8|T&Yo9TG|DS)7O?OwPH2<mf%;2nHFucb#8@E
z7W<2_Y?@B;{|E)Lx{l?6Q9gc9vwgY&k)L)CFYCt*CsQ-y4$y`u3Mwgy$6!~J5iBCB
zBWgj&1STB=_V0lq*o6f}M!par1M>62b0hJ+S~1Kwk_n2{+(+2~V8|&{$;oEVmu9!{
zRR{+j<j_nymuo|BUCKK1NQZ_a*O8>$5WldP9=?Qh8H3cq_<FPy3N9pqZk^x^<h(bm
zeVkN6hkevoBaHq*PDDZ!97E2uSO7Snh{mnX8imazX#c+4*~v+sB%VLbEx;Cg?<({b
z{b#Iew+&Z$3>ICj$f4|}sEbi&jT$Fk{rda&0d#8;<{_jIN~9;IaZa>cd42B9J^Y~e
zgA)YZe|SM7DEr9g!)^M&F;|iI%PG<0{Ixru5yMMpXGkSdP?BJU3Ri31!GPgtD^vWt
zcN31{gGg|f|D3ZTI1&ft{n{<h7wykBW+tEB-gIki)q7X~^6T0M2iJnw5}p8EmPAAV
zWjqdD`9dbs$OIYH4y9xo5{OadVRR1!Jjt~4TJEFX$ZVfi6ap&7{kjVj7cVLxPWa7Z
zv=hFqTY25xWTMK_vSAP913=(-D0hE<<>&8TD4`%B;!})DVO07TEGX{6`=rD{(3V*7
zo^Q3a<};(l$by|5!=Y6G?yImq$bl7xCB6^WB{qw&EP^+Z1KNlrj@s-x?xMPXT_TjX
zOW6Aj$b&2{OzCN>5)&EU<x+dzZE^rih@={z-p?kkpPxB@Ij7WTe0jXB|NlKKhtwt=
z3ddb??8}~#EO^kjNun8<P@>dVJn;1ua2UUeV@1|M;e%g|qcB#JP#>ADbqy4I%FsrT
zF7XnqdaCltsbt7>fJUDUd3z>Yj1?nt#9>C~CUp~DD=$)`*92$kh~|Ww{sPAqknUZd
zsC_pefEmhG<sY0|LJlM#e6*)J!k-+k)&GNu62O@$bxFFLf$NWhHe!5uXZCyP!6ytD
zeq4t8N5aiG1|rb&07TMC8#Vsy<8k^>Dhlw`oE9d27@*5`;<xxjM9#&$e0h%yhr!$O
zft%+IujW3`C>ct9o%T~^`;Hy*6d|?blt*U+-~cirg&CP1myRDxjH!_ynFAjjT6A9c
zwNx4LNo_Ityy4n4Ygi$Z7u43OLdN&Th}k_jAt%RR`y2<Eb_WLox>yIrkQHmt02yKJ
zdOB&;+EuZtyPv-Lf3gYsUKlW~UcG^mv$lSVsXWwd8fnZLZa>um3!4#hZI|@*w_uuj
z-{q=MvaOA6Fxh$>0;oH<0xIfy0CzSVITFz0XlKWOL$Nr!pnW_*c;R92UmQ9ZXUE9;
zf1Dz=cEdNIjKW%NPp6IL44t$%>c#IqZN7CBrB4v635mARyDKl?M3Z&v)>%5gD(&4b
zBEkmN3R|foV2xbyX(+^SCds6Nu5OFY{`sXY{o>p*hgklxijdpeYpfhoc}(9%;_ew@
z?aqjt#}Hqa1q_R4I5t7Aeks$gZ7Sx-b6JgRe9wfhhg9sT8lX;MG~>h*hnv+d+iU|5
zN=MLfmS<BfpX}G;bNgDd-v9iu&pi*C6&c9$^S-#+d0f{WCNON!nM58sX*u;s>ob;0
zk#$EGS-X`;v;^|0|M}9nFRoY~KmvtuO{P_vA`5nEuB=C?W5(f_;B$qgrSyc^qLq5S
zeJkWN)BPCRH(l|wH(1&6;<>?~y}BRA9qA`xqEB@%yN+!^WL*eOsbJ;!I-AJU00L=|
zI0*utFc)HwWMp>i&_(c}YDJgU-6uUBSFEhZh|~zk2T7rlU_YR#SMJi{g-s>7m=w!&
zc)0<xwTepYsGA1R!c`n`<>p(;O3ZM4mB1b}Bi-(u_t&$q%JVl{pHVl>9^%L^epsQI
zg82pG7w^!YD!IANBD5Rx>Q%yFF?_Te_$8z<oH0a$(ri*^&Q~#AxOMyX<<MK)JUv%H
zZ&@W4Q!SGumWe4%#jT$hc}ei*x3=<-q`__PxHvL?io*j*-kTicwVZ41*DEIxYDD?z
z{-(1Sp-A_DmV@bg)$fjwux>_==(3B&{C;<1SRU#)ILtam49TnOm|VLSE$6dN^kU0C
zzuvRK$@)0zt@{cm3}A^fXU<%`c8$%NT~3`L?wNjfPyR#PaJk|z#g+9?1;|;NSFc`m
zGB0YvtxDJ~0M;B`pcuO>0p%2_EO!jDLw*`*&Cxpk4kKJ}gI=pEreIO(!-!jmKpM;2
z@}=sXiCas1CX0zy;2;$&o*8k}UNzPMd+v*s0QtD%w<}hj1H+CP*=M;)?7s6qr|Vii
z)DH^_BkDFeAr?7a7%UGXEbtjDtmpatukaukN9I8QJ_$r3VKTH{lreTJ)mrkl>do=b
z^i8f`e*q<*oOnSd`tUUhF+)R!6QH;feIdevOr)`H;+MKFAP(i8;2<y}BFiB)pKvIn
zTG7JE53hMBwxQJOY7&oqIBGQXcyfjkp-;#KrMNCF@`dY=YwPx`2ye#2^#*^^M`{sg
z;Yq`B9YF}`Q0hN-z^menJI)!~bs=Lf5UvVVE@waPwbG4zXQg{x-DmJ3n_YgrH9Fh1
zcyzQ`xakv)xE#TatcxOh^(LP>fA9<kJw8h1;lqBVLGn$<UHG?ap;Bwwdmx%Y1cB#t
z<g@q(@H7BFmjkGqwtQqoRJpN!<(f6c*oEF?*d6~~Tk{BS9w(p@&vXtk=8*lm_kc{v
z@l$bHseG6LBnOY8yO5wefyjs+L1<ZxS>JiTr})jj^x*!7%?BV)lDQxV70?H9nBa0E
z{3CV1_FFLZUKbZLuJX@W&gv-sw&S7kP;VdzD!CNNkjJ!bc)tv}+W+~4<o~LUq?KVB
zmZ*ec=!uLu;tB;g^Ax&X34&C{He{d$Gr5TO6oO>~IUK`r8!kiSOg>gwo?!j$+qXMg
zQ@AnaHa5lJ59#4VRl-1#K8WB4Bu<DiFC`@fc|qazA!xb8phABl6bRIj*fuA}aP%Vi
z5X>mH<8|cB7SQth5W=0U=gITY_SR8UR^ABwyB-aP91BJc$ivJt^5tZZ(=tnpgEGKM
zPD>;G6((JI1rFWVPEIDlfpIv=h7DIugwxu2eD+GJ6EFtnQbVZULQZQlGKx{Z0?0#}
zI6_?s8!r62ayy!K9iLx(4$Y-!ma(4bT3Bl&#|&{aq#^;@5|BdtzLCnh$YXRwL%~cB
zCMO}dl58*upZ_z>f&%vy=bD*>0Rz0i+{qE!K~Ab2SAn4#a+*<$7}`1x)%-k?DhW3V
z{}+6QeDl|3Hh12+EI8n3XIemLGNoUEiDwJcxOXe)DbSHSQ2n8f(LoUaq`rj6!Brf<
zOl`rzfe6chYzFTmx<6u!iZ-oENe6qce5w2bkx3sz#{XAwXCBsL{`UQ=O-YtCSwqDj
z6_pr5DIt3j6`?3=mLj{65~*a*PDLanWlD%bQuZaLL8<I}8vAy?&M&_?e)n<zp8I%?
z<N4#6e`bdIF4y(BKA-b^Z|4A><4Gm$Wu+$vZSxUj4_d`@ZYl0<R&U;%92-}X0RSx#
zp#=QoQr24|<`+pkt9$6@jFOK3rpJ8~j1|k-edhgnEoP4&KYpuSu&&4x-T-NcE`CxC
zJp}-~5=)cZD9O!I;&`+~62xVYivxu#J3DtPc4Xd9eXg1Uu!BZFA>i(&*$v0toV$S>
zBw&vlM;+wdy56_TrBJWSMj&}2@B{*>f%4^YC`v=~M>WKfk!X=8OgPu>FgrQY5_N^V
z-kOxeMqOs<vCz?EWz7)rjjGcYD-h=+zE_DEQSKoi6_HVTdiwCOExA&K!J$QHe`Oi7
z9>ZW11>NBI^94c&9PF8*5fK$7_MOCAY=?Zm#b8uqZ`A;l0%5NP){Q)*H|t-FeWkyD
zuBmV@LSdlB(!^ogUv}t_wZvx9I7v#4a)s6vg^(DjHntyMi-y43_mn2LVTs3HHV~H=
zzc}d(UZo~tNVe6BZZDDIu}Do>0a6oytyU6#CS?o-yf{)gP(z|CkDU1aZT=TJ032{j
z@pXZRnNH?UK3G?)-833STMiMqaGE%(JN8}YYME~lGe{kcwc9e_c+1zC`%+uSG^@oG
z`LWynroVa9ram4qCA(c)OH?mbr8x1o-OfBXT)l-Xv4A%>3Knu{#o7W7s-^$~J5!#?
zwnND&y(g$i11q19zcl1Zf4cL)F4v9>zu&)o9FN|~W!MSARz&#*<KCMhypo6rl{q?L
zjM*)X6^J`s-g$2BPt$)I54WO-1e99K!QPHnOK@s^t9mTA0x9E`#0A_eF15A@atYge
zT(J`x*|g1)pu5g^*_`FGh$gAoesR7^#yFxB#ZRyNNm*HZi3^Z)gzoaLHLnXh_XY3{
z2)33IM}H<tA~?&qcZx&(yvlk*cu~1Lt}$VW3FRNkjDKFfi@^qEw{c#q!vAJ&-c~z?
z7i`@s>*f9J^q}mP=<Rd4`j9Va@?J?t&IgBfATwRidfFS}wQB*CghOPAHW?7*^2!FP
z54GO=H+{OQ`utIEDgsFjl#Y+5I)o&5s&+tuwatDW*;yw-xr*k3Ep_j;2;s{pHASpS
zl<LV;Uq7$eFxc=q_3Bkq1T_8j?ejFHp+^SFilRnFa)|n_d!{KN7DQpUQGD(k3G_TZ
z$C~s4;q8Pbe4(bQ4>~sMR_i9qkqAnEa^Tg_D|&c%@7Pw}X(?y1sy2AsdqtR*!lpsr
z;9F(Pi(mbIo(lzX77C#6auB{s&L;_{cDrsOZyp%?Omi||q)HuE>G}xPRorH*uyM^)
zQv>eDFSjBvvTrIa*)ll5IO;wrDZr6#G?lj)?7Q}vxhEHT&YSzy6=P##$uHJcbW8x)
zQ%W9l@gsEOy+`NL0T|G>s-fkO;6RvOB?J;J4&mmc+N<Oqr513H7JXYFL9g_j@~EO8
zQB!!64=<0s`q$f4U9Ipjte+RCSNrGMxWcOsN6<X~5xT@KmvdDk612EC{^;uGZ)5v{
ze#cRP6=(Fk4>JZ2F-o8I&##vDY|x~M<rc)vB3=`cbP);Azn>8{#yyGMu`mWMQ;bq<
z1N+7X^T*ENn}^r6P=ul20N$Na#0R7#WbvIq5>`CfM3YySxT2i9cSlZHtoqwwSp!pX
z9vII*;M$tfbh#*;Db9v?c&lD;Sc-u~qT8lsfvV5maMCjrwEWZXf1luB!Se|1B$-KI
z9)D=6vVSmubHqbeODbx>32={DpV*`Pt+Tr<g62tk>wRoiO*+p|qTfXdNo4jPX9n?R
zf2Vl2@@(EKItQ-CHO0HL2<QRAdIbdqZP$qS!F-YHz4gTx;PB$Z^WIK^IGg$Mj@Phh
zK(T4_B%xB|i4xc$@;y#F2?-g)*($2f?G>uce>qjdn>3&4)2*aJA*Q7UnqM$AZ6Vb-
z1Riv25Uvh&f5B$sliT9eK&>N+NViRVQ%WJp+4DPgf!?a}`XC3BABVIO0>kPHFC;Od
zeGeJtw_0q#;ENtobY#`$LI2}5J6#2Uo5)V&!571^*cB+pSLYvpk&R_5h7)Heb+p&R
zi`%<3#?>z7ZuthLmX-rl#Fr3JeN&ViXfIAkM|%CgD%hA4$}Mj-&l=wsp*wKkp>Y=*
z3DgbB-<vd~O6i+e3uow^q*n|+8wqkRU4`iG*Vl$)N2e3Ywkl!_q1nK`#r&-*KqMj3
zAC1+o7g0){Pdjk`zMt3i@z89;-y^Duh?H9<c0`o_-#$HSN2??eS*RQBB?`Cb3AM8D
zCV$}iW_J=r6&s8H1JP%G8;$Ilr=mhKl__W9cJ5reX9{1r28Hq0q&e({NplL>J!BXH
z?W!PJb3XlTh8V*fwk-#koHJ<1h*ipTI(jJpO34)0es*)8M{Q1_IpjV3PrgOmsQ5S~
zy{I7ng*@4YjkAu1u17G<ezp_WLUG4^{x()tIiiQOJCgYosxFC{1n}Svp1+|mpm9;L
z2~-(ndv^Tp1UipkMo|D%9Z_!v-9fLit?THoviX)<dU&Lw)2)1wSz6Bhm{h|Up@E5s
z2{nb9LXQ9`<J|GmFeveisdqQODB1@ZC~{WWim}h>ELyZkAT^8{>(=Z+&QGL9W6|lb
z!-*^oD9iQcVc98mwat1NHk4)+^4+T6p3387cGlh8aY~!)Oa13jTOC3cr{n;hnk<oI
zgLI37;FP?|SRM|k9?;_f)|>U)4re|cOjt@pDv+hLF;X1Ci6;9uldZHQ_E}&m9GV!p
z`tPuBB0t1A8}R$!CZ!3TV#*x(EVc3~jW$2i?AN1W(Sb<aaHmfv>!@Qq<~e&B^|HO2
zkprFgk6tKiswvWi3oE6&i-?S7F`?G_sQ<IK+q3!(5tl0*zJD=5SEjCr#RYH<pm6!{
zFx6=v9n|g0V-POa6AR`_gepz)Dc0F*Vd6jx$-2Ds&#^i?Xd0owB&CIj3)gvhbPe{w
zi4sx&n%E+^E1S{kmJ?L^-hXwv1{T2F0;8R;2t?m2I$l_`qz*Zkdj@`)&Q|&32|v30
z3T;Qn!g;&lYIAVUSvsor+;Qx=_$wl%FhoNm=M&cIP%gVFsc_b=VAUdNd26=5&@Wsf
z_;>;!8!6pMXU7C^mUg7*pF_^xa}ziik(?Szcf@H#XC1tmWB*&;p|2aMA)7>2bhaH-
z;iDEpei}Z98x3plAqKBr^-R;;%&a<nh7%AV7XLVrnslxwScTziKB3?S)L0c5BAg`i
zxb_0sClk81@Wh;bnmZ3HzP(wc>R_0c)pU0}hquuyA~GT#ccbOt+tij^11f{6=1t`{
zo!Z?Ruml3!k%p9JNt?i?2@@w4JUmH;`IKDMmFXo{22nSJ*cg)CCAXtX7CWYXcJo`+
zZwfCVH2=|~4|{iIsW^v^O8M+Fl<7O%`H%Yle6PtICm#?x2f~NSk&YDLU&Yqjbe#^i
zHbH5#KaZ+zf?q;vffJAIo99(_?)%T;dl_cfpuxs}oq2pDq-AfKOF^7q+WgkSROOyT
zxfQ3kq8<$4qpB+%1O5!5$=}zZll;&r>d~8&C1T`fp&)u|-nnx_1&?qTcz$xX?y4VZ
z$qz}_$*JUvOf_vVpxs?Y;_Sb9PgcF|PFB6_=5*WX>$WiBfQ{m5gsNzCrD*g=t$|N`
zyqN=aG?#NvY@F)X()l&wv~z^1MK;G#DB?WyPoj39{@>cnT2;2S;g<PQ)G@+G95Ae)
zD@Ovyf<60)yWMW)gnvqnc`e@e2gwwonrh_U^XGa<=7RIzd6~uRyuxe!SnQv4hqa_r
zrJdQ=zMkq*IX=+b$8*}Ih<uFT?O|}IrfqcH2c`-!kF*K7p~2jMp{fR=9)B#oi5$Cv
zG?AD{7)tdSGpfEsui$GXxw_5WxD=6@97006Q|i|My=KX25vo#dXesZQd4H0T1^OzX
z#AVwBv=OFAlrQ{4?{<EOBB}{7#}UdF?zEVFz2G5P2?2YsYYa`UqGtZ^;RCjs1}Njf
zyB5XHk#JftJ+ZXWQ&am5++O}G@AhexcWv7?mPzqy;ZABMns5eHM%|HD{xmxWJVKmv
zZa0TV5Au@PzTKLj;l+uo%8?+VQEDPRqfV}yo1v2v4iqv^R2ncwkx&Xg@X2#kFcRHE
zBW-gQ5HP%y1%c>S#bGRIhd6j_ZQpF&_qE-R;>4MY5w!n$d=G8J9@WsaXebg?gQVyK
z;I1qCl+vBPjB+NNsGa)MV<JoyFa;EW@dS;#pAFe7i1CZtnL{HF{M){r95hTk6%r!>
znAl4)n2F~W=!_!9tzS^0@F8QVE4XSW-4T;?MwHSQp{S%Za5f&9UKZ-UM<Q;6v=k5#
z>8l9Ebm;S($Ig90(t`SBG-9q90bbIyI66A&=;{_`lu+{BsCVZW6qYt38pI8K+C-_)
z)%E*FkwhY43GAzTV|MP`xqqObEpsXOy)xDVL{gGG38o_X>s=TtD6->vgZ*eTxEuG!
zTQrj@kvole{I}9f07;Af+w3}&X7=F2^c<8@t&yb*W|>n!2x8~)%EDdA4(aDF^#hTc
zDtqxyy~Z}LM<b;fhlSd8i=Bps<@4jOw1Wu=uddJB?iMD;l$?enZ|uKAMj9x{SxV5v
zG=8fGb{HhfZrf<g#DbSRg8>rmfI7DyIvS64(S;=|<|8@pic}wz%EMQOcoAqWr8}7d
z*r!AgTC|*jEnFXAKmEK;P?Jdj0D@f!?2%jwVf}9&XbfJdrbv`%Mn*^3+Nq$&aQHyy
z#y{6JWQ$#WH0h4>#?d0Dq;T(hu>IPm^d)<}f@lZoILUC4;*`_Kh<QEPFhJL?py>U=
zK6`Be@_y;wdo0y+gx25*UJS%naJG==#MEtr_lmHgTMhHAyK)~?SZ$5t*vfdSlf;9;
zxBLG(`Hc_qp9a>24|UV4Q)T-ZeOCL296^H@`-Bc{@N1sZxQoW*5o*@o3m@fu*)sUV
zq4sO(M-$XfY3{S?8>3M^TDiJ1<c|a2H~8__m3E&7pZ#+GNN6-ra?+n;c!f>ts(pH{
zeZlD42EXvpA4UiHKU`&9x@%_cSqLWg{?@r|_V+J5w|0M#Woe(3!e0UwaDDO`80<fF
zVVB;O!0_YyD|B0W@Ml`l)ra}kt7?}zBkp*>qn!QZigEC+<sCe;@5bM~p!RsSXGyE5
zJ{;$R7yI(Qd0j956`viD%}>r~)Czlg#2Z6i)+N7=RqBPm;=jI#c~vd8;amG^+U?oi
z3fI=vYN9+?oKhXK>})5GSGDqd+^RjEVcb0HT8Dzq9c{GRuUNGDZOWMo5Bq4GkM3kY
zt_vTkXPtvShQp4w?7VV@zuTvZwM}b{<5XQYzJF@#`9>GkfrMP%=rj0Ir;TQOs_j;}
z3GXX>cJq5#X9-)|Wv+Fp+nnWhO$G(N%<Z?!yr<)`b=`ivz~tjmsfy;Eh@2bQ@evVy
z))WTxpJ|<Sp#AaW;$M9HUd@?pbv?%1X3f3}_Fe%kIZz6Rp;ojb8cW775L(9}h{e~u
z-!>p(aUcUjP@Aer2ZA`HU)2`diOfGU*@E`E#faW$^M_|ntx0(z1KCgtk=uFx)!p-^
z#H&@CrWZ@FLY*IxV5EeVugza)`SWXPZTCSkavF6CJn*Gi->B5Cr26)d@qk2y<**5e
zO&a-H;ZqS{^2}W$%fx8nC<!ykoGO6}Tf5D#2bg^tI?j6HwOtGDX3kDD*V_HEX3tqG
z7H{$=AM4??8Syqvbh>DHm&R5ewCVPF-i}FDpiv2?E+$Jp1lWC-FN<MPW*Zcel~xTn
zR7TR|KagN$2HE-0M-*Rjz!yb#9EKMt9_gGCB4r2=tBhWPdUI$n;vYROTz!T23y<A1
zYL80zTv*j?|9i4Orkjtp8FYKj!7JUm=Xe^wEB;;>Jw@%{Xywr?uV=0D{2Vr#tqOeb
zbgV3<gfWgyu=4Mg9E+81d(TkziUL~XhY%0oROd4qUS(s!6fdliv|`{Q6HESMj>YXM
z;55yl;5#ndpY&UwW-05U=4I7As{P?uX4fnxu0%w?xzf#RL&2-u{yY$oNtf+%BMH^;
z_BH}4sY&FF>{D3ZoY~*S&{On`7N1yQ8LlG}iA21PK_Ky?L~!5N4f)&7#>VFMl*_cA
z!k+n!AOHU9=du2~K9}{)O4?)NKkw}NeeXLAtQLJfD@*pYpa<zEqFe=vX42bA9FJhq
z$j~`6$AD(Zs0c;R=)*~0O-ga`qXM9pp)o?PzF>O>qZH<#WA8h!N#n+!ul5->viFQX
zH$FDCX=!%by|-G<U(WS|n_P65)WxgofA@xzOksmE?6Kpmp#|vy!pd^ur@g@{dhR7!
zdLS`HAz4{l0f?_aLy~5<=^#O|=_8i`HzK<Czn*{XhO1A|?dXMrkGF4E_4a<or7Jh)
z%zoKBa{jk6yR5w;G=3%NAP^59%A?u|B<1xHzdk;U9Th=zu8PulOSE+&E@VQ`gPnW!
z>=P_<AeN3r!HD0hlE;N5cAK30mvf2UgeeJ8{P%;)ojjK&+IzS9?JZm51h=;XXMBoN
zpJp0OmU@b<+RqbC4tVMUahBp4Gsn9S&EaGUn8$gP$FKvS+lo}+3&|w{8aX2m8TcfK
zNCRpwZRK!4aa}HksPJeg!YCFb`ksSoaZJpmR;A+)PU<+JEMP^H@4-56TUH;|tKr4a
zNhgEW7o2cBdpGou{<#y)Vok@MSQz%D*q(IGZ$b0-bk6ozT>H9cEiup9_RGRMAr-CS
zNeUcyQ&m`D8a+jiAi=yUd+?R?@q?(fHDJ@I4|-6T3DEDAUP29Ejp<tuezJejQ|Hmz
z4Nh1xsq?t_lX<pPZJm@iEuMW}d$jGdk6P5vDZ6HzIcBza-X;C;Z$_K7*>Mc(^(;TV
z`o-v0qKYS^G9uF4-!3)oulZA#e)>KvM*o&t&5K>9B)DwtF=KDe7M&*sK~uHer)~?(
z^tn?NZSV1}=9@3!ChQ&|vo}Ag(b6+-#nP51jRD;pj$iLOdcn=v`c(LX?JKrD{1_@8
zM}XP6d*;UKH)?NY^Xb`}fmPnBGu(aa#0lf{@)YBI-_-1J=_jYQRgHda^K$ELf4w}P
zFPD67oy{;h+iK;X1>1N^=IqJ(F&j2P@A!4^DStYvu!?cVLx*<1w!Zv&w<vj(?9C*V
zlucK*Kj;2y+{cYgh$4-uZ0N;@-TKML^37>^YLLZ$+LjYSOa%xC_6>bo{l^A+@y-6A
zdy6i&+d<mklfL$gU}%%9#`4!A_2#dCP*`+ZGbCbT3va#oZ=Zxp+46_{UC-=-&RK>1
zy7B*?x{^7%WPkL`qTws$!wu@6Y9D_z<{^2h3rj0(eaEh`_S0ZXHyp)Zm<*_?)iN`<
z+Nz2QTREumPxA_G?n~I@sG@+>!{aSIx18Iec3{BFL;QD)fU54A)8nqH-y>zoa_fQ4
zYr63D^d*CI!lc&shMn+pTn2*T{4r#}68_~p>Hl()?rGa37acVP($Vss3!hqd!-W~+
zA7&ly<P(~h0D!3|Ag#Kc>T-OXdP2v}!D#l_%D#Gd>w!=1_og+JVI_!G<6M(Eme1ov
z;K!xz$3y#Q#*%f*^Rs<kAE|HD^mAx#MT(t?CdxYv&f5tSepy-4=XhwMDS1U?x3wH}
zp0wMl^B&5aJ2k4UoS$2Es9l4uFO$vMdZgGGuCx`N{jq_{L7^%J->ha|Vh)=gkeLkJ
zEen(%*IJf;g15W=Idv^p2YYR$u7DN)i_P}IT3W`_I5S1h?QyUv@s6HXObpF%nw|nZ
zRHLQfh=)<CB})7M15;k3b$P->5CxEHY=TSN&sJ<-Br`;T*b~sRl7%BG3(Dpe7wbFu
z;HzYeuZ%wt6D*sQq0gD{(H!tdqji2{xd;Na(SG64=bPqreYuW^*pEIG;^Ih`(R291
z0XQ)D7@$wqYBGGaKAES;9`6w>Dk@0fo1qP1xB3N(juvQ0=x^GkQyem+W$sarJ~}~+
z1Tw&YiA^JiU8>mbK(B=bt(I`3*fG%&i<uK|_AWco-GK$iPynFJt|1ChI728bU8^^z
zUJ$vNE0{J&v5357yr&@Zl02Avx?*5)-CeVQjSbmQSC7J6D%F-X9wPPV<Oxxck#!Yk
z1~MQ#Bafv9?=1medoLkX*Hl1qvO;y!&xvSTlx;NZcukv10FaYT)AwJ9i1EBiCWg@?
zX2Xf!Tn1q7eGUlX#AOtAbBE~})4ja8Y7}T1a)au0*e04QyF7^YNWEbJ;Y>f>OY*U7
zSccMvLQk9LoQuo==~Y6+UvLkZ2Qu;X*|mQrXnnL#%3WpB;|iLE;!3SKcdD*)o273S
z1t9pY6F9UCWS;mt9T<GAe}2iCGn&*e6^Fj-kSmkJYy!yvRmFBlr!E0`_X789t@OP-
z=^X+r6C%wd8fX0mB5yONm9~vbitLE}81?{GrU_~)4drJq4g`^Ql%I9-^Yc@4_L?a}
zlqJc6Tbp*FBJi>Ua?vx~8*5}4U$D5#Usy3tLNdCT5@>g#`0KmZe?GcPl!AEiz=(Pf
zV+q<S3b6$X7APV4+k(z$M(JkD@<NZzRJECo%iQi`{7^;XQN6(Tj<{0xi#g&=N!vh(
zs;1B`pFyG|2@hz3>rJ28^A=yMCYUtV`066B#4ab|5Y|G|+4I_U)KA_7UJTxyey79R
zFCRq?P~X+P=LXENLf%n%Nxoy7Osw4`y^*tHx$pA(vI_4L3mWnaNIImrSnK}U*BD(n
zs<bZhzfiK3M;;k8Zrm8i>3pG>`rw+BRWa=r&A&03dO^~GrT!%%P?BLKVh%Pzd3|IE
zp}%`K(FP+HSOG-Y$DeP<ksP*V%Luhz!w&11h#QOEzZ_NI^qDi)T|5ZT518-w>NI~!
z(|zfES##UTH&qklTwEe-i-<f%!*T8V+&fjvjvbpH8}IV6BwIi(B?JT=xWGT(9*H6Y
z^X{=uP$Dt2ZbuuW+4%d^*wW_zGPB+1gbA!wS==bShcT!*5{y+BMT~yKhF(|V4I9!<
zh{zGEwgIP!(`F#MU3R1u)aA)FL=Ih_nQ(Q{coW2aK-t-La|wm0JV`+S0fUj=spbT}
zD(P0nKnoP?dED_tJNArvEVMCz|K&6t37|@+u3jCCR<)kb{qQYd$*o5oJxrS94$@8y
zfS@3Z>xqSV)l;tItc^Yo)}m9D95Y?eKd}K4>;Eyd)?OF2RWA-hIqe-dW=w+6q)QO3
zF?YJY<W8_{Yt^5r|8{C<9=oYT5TWjAiTcACBoyS!+^>r9g&R8sCIA7i!w4XAc7@wA
zi<=O&6i{7;Qx66#lK2c3b}NCfFmGBEl?Cp3-g?QL$(@FCjZ8mHkjS6^Cxl_g3WyFL
zay#>;-c|%6Ws&zuJjy<l&*H7>%$qd8=^x3C{;4~<^-XA%b?t0_j+2-1v|b-Uv8>SQ
znI3zwRfI$`m=)r}J=uXGFuL(?1Lxhd(qH&HoT{NCzGV)>RRe_VbzJt=k=O%h?l!Y-
zBiJsz3h9r}^xayNx+{c#gc1K})KLF{p@9YcA3-x{YSIeG`|N(!(1`niR;O>W1N$|{
zTp5MG5(54iht2@?P&gZ)^e8BP3Nj9XhY5{>8A^^Xo=oK)#2{xLt9A8LB9a?HLr51Z
z3Dk!t4pC%&4RRCQmKw&B+mD<%(-s+VP1ryYlrbAvqIe$i;K=F{jUf-HI=Hb})`fvn
zGhW~r#C_6Ge1;ga_&O3=A}Vlz$7TG9%<<)87G%gCDmn+z)}*JO=0K>^tl5r=`EOAn
zie>^4()z+BbtD!}lsKTj_@Kw2O24)M38!=g09}^?vz^^j<@&bYwA>joNT7H)ejkZF
zU=RYJSvX1}=}6%}1^EM~-*pBBoR*S`l~!0U+yQ5}>GC;IIXEW1xLsV_=j$>~G2lfV
z7&oiiN4dwjuuiG`j0`Pu(vkPa)!?@6e}pQ;aCH~`ouTH#(;~6EoIi5t$WA3>4=pHE
zKs3kGPIyx$4l7N&&QWMz;k6rz&k)2|f(*<)UbsZ8DxA+sx;+<v^fUPs3WqrQNe`_J
zlp7iq6%~-hMp(GU&-Bv;9n&^$@P6Uk6;Aq91H?b_6lGi#$Up=|j1CGf86Z5dgcw&<
z><ps_i*8Yl04>*b(vdkMJZyUcGU?ZU*o|HMvB;^1p!Y|vBvDmL1ggm5w0}->6E;J0
zB?7~QOO?!LBsrtiH{>P=_{46koDoTtD&&jPuCVe$QrZ-gB{22%h2I=S@2R6mK!ux3
z71b2jgkO|V)niaSrM=zG8i!wwAU-mnVw1z76RkZ`w(jS!oGW2FBr*S*|MgEM<T7!r
z4u@aon<fdNLlW+}bule$hpH-%6V%_I$L!j7Jge-DD@6$l7>`JD!^4r}uG2YRzSax|
zq<Zb9UB%}@NwAbo@4+*B0oR#PE25KKX(C|ZR6-gV>%N;C!p-Y<a7sV`sRW6!4Or1_
zzn&DR#rW8obzb!h4Yg23d-M9-&M<u0?!9%?C<M?;6%S4B52J-EeEs@`)E#2$5yFhy
zFAIt#-*b80@1F~9QhE~Vi<tpu;*GSE&b#boCo<O12&>((cpFfX@)|~i8Ns?Vmr4j3
z^cWyU#J2DwJ>ZK^@8=gjmVe)JQ8~By?;8UUVZR$5?|LrdKuR!-h|zhQR}Wb_r!z}`
zH-FY{{a&Pv#Zyl+3V@rPW&`&k%sP8V9#z6?n1M1vrjdTGI{fv*`{)A0tB;nWR*sCv
zQtHFNS4nH)x@v<coAr?s9VwGG*~{`Mb=*Y$CeIxl4XMnY8P75fAJ$a7dRJw3Ij+&r
z<BDPoiI(4BA16Etc+#33+c56+SDrkL@#7zLeUX`b`_eur4d#g2o)6r|NSDKRXBWXP
z0pWP95vo>(4@lj><cGyjF%sf=?F-)MIFT=wYMZ*%W>Q8^S1zQKbl0Iqw2hk|5{6Iw
zWo)_>4%OtTgH=(*4obQtET~upVCyBrMFzHtr$))4mXTy+0mfwlDFKh-^;a4$cZ8$1
zp8qaD77YZ)Ml0V?3wvq=0qhw3C^-XwLa_^}hMjnEc?w0qk9eym+kqJGanajf&hNE;
z%A+Fj856dK2MDcz<er`8ik99k$mT0asE%x4X@DW+P>fQo370Ly#C~WLH#`*;C(<kT
z5zn1>(XmEE#^Jjm)Z^T4o_lo#JIG>63dzb>Y(7~WK%^?p0U#CGYG5lQVqI*IQg;F9
zHRtKTvZOMq$%yiPu@;WhvR8KxXk7fdI@G(+*HUj$=iZ}Ejm`7m`#`!FLT^e?ZczX3
z;^CnL*~vqRUNfwYI_kW0*DN+RPM+GOog4^p-zUF{8DOj#+FI}A>1y>f^+$NtiOw67
zp_^{$d`NeQfkBTNR=;Sr?{_4srsnDg{lB%_zIb`5-i1z+yy^`dnwZe~ezr%f|AuaZ
ze<|oZdw4;ku{Saf6sEavf7EEH<HAz&n6Z7XWlY(;yU(R8pL7kKXH_+W_bbXAztY)W
zlRI3lGD|$_cI%Ir3fJqli#FEEF=*kbyiT(nP!zoFW^ne<9W4qbPg|(m=@F`>D0Tj<
Z-QcORVBF}bX$t@J={e9j#mOi1zX0p?q3Zwu

literal 35183
zcmc$`c{G-7*f)A9MN~*Mk)fzerARV{CJlyUh|CHR88cI6LZMWKkV0gr6q(6bDV2zj
zLYZfo_wVd|_qX0}@9$gt-E04`TkBap8SeYOuIoIH<2M~=km~89YZx{&P!zT1_%S7Q
zidv>kQ8W?sEAbUO@vSlVOVZ)6w!;~l3l7dkc4pKmBL`b68wV>3V{RuiJ9`V8%lkwm
zMfM7Dn>#qz+8^A#+xma}fQXIV#oauom$%?WR@olYv8N~|Bk~_js@!7>iVAEyu5?J_
zYV5#w7rj$6OLQY&tve*5gEemP-HP+ws3scf!KmYJG*G<yLY1u3%E-7)t)?+K`<imH
zbZ!Z+-nKU?^Hj>Dr>ECMe`s>o?fc4Ey+5yT#Wu{u+PC+%br(t{G|X`LF)Mfn;?L(J
z$=S=fd3kwfKkq5SU%cx3__dYr$Fhnx1m8dQF2;}rf6_Lw3XyM%n_N4L?>@Y6GW*}J
zhpuABcW>Sk{r~Zo1-PrjxdIdtOGkfJr{v0d%$9!qnDfDScB9=l8v#A0t<v83UV&pj
zgH+VI+K(SuJZ2|uJ_@ODHvL(3BULYd@ADTgj4oWzZ2pn@=JA9~&FpIH?*)^|m$edA
z4eO$IaXH?9)3PJlFjM#CS_Z#mcSOz$45$XumkzeR9DOIz@!-gf&3pFm_s`4}KKJtS
zyJ2${r@1NXi9es{-oJmZUF0gRnR)JPGf&aicp10O?(P+rE?wHVapME`nX%uEDU545
z4yZOKb|2U5ikfU}YC1AA*8TCdvrSuxS4nn-p!(EctJbebnauLF54P*zwW5^Gi~<hv
zg<ikDT))I~jkWb)c=4e4rKZl_1g|62VVt9rUk$d2h^!UVda87N<r>@0Qktu7Ze9~H
z47!p0r$%NcFa7@gd%e?6$%CHr2cneu*mvuPGO!7(cRDaE?zQM1$|=RJudg4o$7tE=
z)vIlX+hykQg3X04``kS|7^Nzux5&C5=xfRhdH!6?*VotZOZwTr;|+3G7G@orTUyx8
z>17#|_}|w2cx($kctFaDJM4e9KQZS>TbH!wv~2=!ih9uJ&l<n~{PBny<m2NjD=qCz
zwtB+7bA52QQ$~AJk(=|$yL(q0IdVi@r^ItXHAR^X|K>ATrD<%;yL!!<FPnPkYA;D|
z-n`jw$}_dA<=I7Qr2Ww$9@<-xk%?JZODsusI<Bq<AE_jSu?wH;{E(>F(sOa}#FbC4
zu9!IVeO^U<cxhvxk)h2}5x`VEJJ~O4RPL(~@?@vi<&Y$m^dQx<T2J+S5)!yho;+!2
zYU<nb?*7mDnep6%A3uKFxbMR1wzf8WnU<B6_3zBgkG?NYTAHSZOO}$(zjoRqCg%I%
zg*aA%UsP0-)nxn7_2@4<3>W8Tv|m`V#m2=YK6w&?1=!W~CZy%|($8?Y&b~ed85tRk
zCz@-doCZ|$4Zc1-|N29L<0ah3Lt0uJuy$f(Jr3^OyVrE`-hS&~%P;9XLPD$G-4nm=
z<3od0c|G60x5ur-ey>^G`km_;+KN54oG)<j2?|=J94+9-vh4`Bq@<1}S;D_RB+@f5
zDBxM)QwW})^_u@HimMN3OgW*5cRKq-^Udy(d0t)F{@l6S!nz}aFFVSss#f~@`<u7s
z32&8gjrzH0Q0%_x)IBjDym#@!lrD8wu4!Rz`skm=l*Gr6>71RNGYm>(TZ_#WCWm`^
zR^r06b#%(UewEOD)|^$c82s(UB}D@RE_QbI-%Xjic~^(pi$cOUrO4a3y1MSv%@e}S
z@qhK|K-&8s6#*Yp)wadly<1jOLmw@0_LlKVyCJv6$0}SKH*NZX9d7>hDQ9SCsG*se
zpQuTd>D<Xe_nCD?u9Mer?Qh?{WoBmfexj9?{y8DVY4BU_F9wR-kg6M7e&Vf%_1OOo
z+plA1_s4aWwzYBG*eqW6NtD*Rv(xao<rjvYo*q0)rOCc8Iaf!Gb>fnbh9_P5Sw)`j
z-MgEL|8|8~i53fP<)QWb`-3h@SeJd}%9Z9#8JjM*7v2@V9Xo5--R(9#@<Z{tb*tu7
zk<`@@!#v0Iu@;y6$;sRJRpM7u*}1v5CiAa2I8<WChFzy)N;(~P@Wa=y)pgN=G}QEP
z$I;&RaYjZ)G|QJS7c>7rc`eRd44Ye+8!j>F`<%A(%%jzzH*S1PJF}zm%^My*z7^Y!
zhLM$r`+>#XF})aHcy)By=;-Lk#KhYx#V=k=O5LH`dtXV)v5%IKkr7)j5%1TGotEdC
zlasSi(r){};2>F@r~-!XV<mGngCx8@Z4l9;r=z3$-QQnPU(YCUx$UZrQ2xxovj&R#
z@#9CX9X9f&eHR{Bwd8*I^ht5N=iL>Q3X8>GwULRLnKybH5-#fYmijD5QRQD~*Dr8b
zB`YhN{rtIaaj|S{Z0v_D1G$#Hl9OfX-R}3kc=W!#yKke6t5`-xhM~E6ASy@i#@5A!
zxs>6goE%ZqRN*<1NtDwQcSNF%>s;By`Gy#p-rbk@h;1Dc6VrL$rr0MhZ@=bKy`V>@
z?sruNv8G}%dcWlgjgxXtvhRIwYiC#f>9I<VUAOX87Z+@!lLaT|PzuFt+Bwj>Hln5t
z3=Cvn`FVsx##N&`X210}U#%?tA5XH1uc2|Y<=cNuRHQ>mHYn(u#A8dk^!2H&y?sT7
z&NF6K*6aAF$*5BT)+XNz9QW+qTmJiFvJvVB){b%G!{dSB;njsM<ED-##>Sof{UK{P
z4?e)9G#5AuVo}mbNJyZZq*<5HkgwWeVc=zL7w28(CqAhJ1_hP*ui0Wc8Maj>xWj9S
zQ!!wzUrGue2Pfy~#Gf-*Ao9wkxNq5BOP&+M9b9<uc%%=lIQLz6OM2d`D?djDTJ{N@
zdrsfp-cG+}P4oiW;#l_yykny7%geu8p6yV+BXZ+wmO-+`r$?`xhqwB#<z(2gW5@hx
zHP`P?kC}{3Ohk<<=`Ch(k>v75#>Xq}7<dLvOgO|IbY#GjJ{ot>@u4>V>DWM#^97yt
zyGts^dmC6bZVco<b*~ePde6Rnik6lF?(Xgpw{BfCs_-wvrVr<mt7<QDW7)EW@ywYs
zZG|qZ30{km=~`J~_!y-8O%HvqxV!ISyW7CNy?Z-<{=ANYWrA}0w?C^S+puie0Vyey
zk<Kz|uUBd7bBpVY8$=B8Ptwb==l#6By`_s9Y(j#Aucf4<)J;k`53Sy?VZ+;4Nmd1V
zDxFi2dmqih{CI=WrAr~Gl%@DYFE4*D$0tge9z?ymh9*#VXLtCnGmkna`@hn!UhVt%
z@eTzAh1>;}$TQODq~%O<^WJFeiKw3Rt5zMVzb$<8-o5lj+4QlZ6DLnrUQF=tuc<j^
zVL;ZBNp)ClQ%c>%9XmqUh0F0gvrVek3K<l0pwp%57Zr#ty^oXn-CiVBJliL@dgC4n
zRgWy#kJ(0w+xhs6{*L_Ec{Y80Q<gz^o^`8ne^aJ;M{$wWmS-2<UBiy53g-%Un;zoX
zvxoWHw{IUle2_nRa`mH=cdy|=kY`4g|HI>vb}|>5nwm(d0T9_^)x1YrTRYVu;~Ba8
z@$vDbwBVJP6crWc7w3jak;R+wzlo2EqTRiFx3uT{MgxyYHayXQXBQic%Y9b`hK5!q
z9S$+=|DJ8MT))WGk4MoTO=nZchTT=<`uo3TB|H3SbO~mm7H4|7sJmXVg%(o-E%=0`
zF`_2S8#V->hn079aFvynQQmk3qi@eGnsdz<u?Pi(@7%i=49Jy)yN4oEfj9k-Yjy&C
z#c2NTC{|Skif6XR+|=||xwG#d>)^Jow70iE885vFfUguEY>&flRaB_M>CdpUX=!Oo
ztE=hkd)^*WS6_E~w?P=1^$%PP*>PG19)3Gi;yXuvR5YWg#E17D-6qR}UCu^Tz6sf2
zpZV$Od8tH{aB>}K1GSMm%A1?D#Vi_?1Wuej&Aw^Vrd+d%iVDA{PoJWA+|$T2|Hw-t
zPi~{Sj<Io4s%qjjiW~ioKbnq~mK4^OSt?LHMLFpAZ}T*FbpB=D&Cf1|YoPn^*WDHt
z#I4|q=9Kf)qarf*NgO|ZyrqsT4I@KCZa|%sy?7op@>b2+hXhU>KhCm$|9*0lX1)!_
z;_7uMX6x3x=xDEn$*;@2U%5`EYpj$vM_s)yVN=&PHQZs){Ow!thTZx#b*~-!`A?oY
zmEs}mG!R2^15|A5`uQ`(wPb1WHN_2R7;C+xm7&d}d$DP8akf88UB}WgePm>W8SA#u
zHGHd#02PRKeX;doiux{J=B~2qbPCwcZ(~Fi_b*|?Dx5fRLZHO1JDB2L{QEOJc5NcF
zLZBbx1_r8YX1q7QsdhFt^ZaW~0Y-XyX38|djK?=s=h>sw^RM&7imY4r)5xQ49TTXp
zsbNm=n9@Nb?L&i6NK_3BV%<^v@^Vw}LoEATyR+d&uC4`G<?Gh2UCYbQe?(KFe*y2b
zS=^EyV0#qxE^PpCO#w@LV(9x^(WtcB)JfprKmdaJra9mp28x%PTV9}kR=RkGQ*F}i
zB}xp9{6Jg&83DJ2*%zoQxmI!M?oM`*FT!oS9&vDR&{9``t#xK<Zf;vaUFrM0D{bJ*
z6Rq;v+T#Zf9#k$#)|oq>c}^TPLEy_^d(msvo$JdR8dUQ1nV6WOJzG&5w^Q`^JU@DS
zcU*WI!y{r)9Gj_sy5l-PCnH)yi_HV|wDoJY>|ZY;BBI^`HsP0;nD`ekz^tD`&a?2t
z=g;fWx^k`2qC>ov7PQhgaBv7wfojP|itG(?!#)y37cb`}5-;t-yEs3t^5ge!phQ21
z%k}A6z|}Wz-QpE40mPw^*DLWnFEEa$ib{9K`r_QwU~WS_7HhlP(0bnSmsiJr)iyp)
z@BNfv|Lo<<mjiR6mY;VfrlsvdYw%;fo3LfyzI~#GrBsVka#E6ST3T9$drbsSQtIP9
zeCa`ZwryJ;u$EKdwbP(#vAauJTT>IejO#?{pHGijxVV_84`06c0cSpMtG}~5rRPpW
z1hYj8wscujlcwcvItmzQHTY5Ys{*G%25fGN0$?$U`@1+k6DvM9XOY|VZSj|A>SgcV
zol3DTbn)xKQ@A?XwPLfx<<N%@w*waIYJLTflyRGidgSQfpqiyG({f&@ui1v$xYsn$
z%C$M$sByOA7l@gbmX^gidLQhb#8db8Gb?mr>o?Y;Xk58+C3kui<vKmI#>B+LqTtNq
z)7dXxyvq|lfByUg2%2V|O^0lAbMpf%NA<gaBK}NVVZOe!u?Ma!qq4D*ap%+ScAwI@
zlMRfv7T^i3vZgC9C&wowB*a0Sw_l(Fd*>#o!_U$B0_A6@JnrA+Ma@5Ow>W^JnhlTp
zET?+_WJR-l<uNnxpO$usv$&$wxR>6Mk*vitJ@?(K)A~dU?YbGtD=I|oe$`lc1n0Jg
zqX+r=`zNU+$mR-i<JKHS2g>!3wF~Y=n^QnvM%m=Qlzw$ipzn3+Sdo-%Cq=jgD!;NB
zka_Mjo$BDTNUqbTPmhd_-i!w2Wdb&i6#u??(<Y<NQlG0Moiyd;<))Lkbm9K+b0wZ0
z^gOxZN55nlaG^jbxVp|tncO?*C_wt)J@HFjon_bm4!s^$eeGoZIsI&Z+`A88R|i}t
zb{07N;a%V_2729XQ0yBX&O|r@X#Mh<f%tz&@BaOISsS33nwpwYRA96I%U_?yWjH3H
zSOV{Ph9#uLPV|3e($v(<e)dceP4Z?;Od!_u39Zs+<S98lt8DFE%RPP-_4kBU8O6PG
zC;ima)X3P_vXPGA8Z`f#w{JgE4|S1DxUlJf?Sp|i^0ua?rk$v9)ZVQ9)m2qVq~QF_
zNJ|SsdAs;pUH5ZzDs4ZC*)e5hg%suJ+;>mZQy8L@Q$BksrfC@eDEG6ya>eKAQxPFy
zVI%MrJlNXVJ<{%fnb`z1YMK`Bf7)+%=Bb`!i-Tq^8!PKJ>*exc&J(GwcNz%3E%tDW
zxp%L;vXT}T)fhh0>aiEy;l8!k+js9$uI3ugeppyZ0oSxVfA(yjn3xz4&~lyp$jC^m
zS$w3x8#mshpM3(F#OG$lchtt&*27H~`UQFCyiCwW)7KUKxHNpio41C9&ZcYJ>{)*I
z&e-6<KzobEmFc1L^gNwiUAKg%fE15kk&=`&n)v-u``LvxxR@V+WT5wT?OC9$<)1#W
z8hFm|5h!{2d%=(C4lk`;Ep>fdQ;%ZXFY4;HTE)$e+dHEb^2#pF+ZVb{GN2&THA(cJ
zZ}(g}E90-TBO3g+yI?3|TI6MiADR=lsOV_isA=ZU!G@UV=;(p)$Id9ry#oWWneDB^
z0Rjne^H<$Uo*CB-Hk-Zk`qWzDtW*1-sK_G^)Fe&)?f2Kt)oEuQ6Lb#5oOm>R>nrRG
zpo_>%m5aCW5D(G&pov_VTWz-B6E!JW;5ID+B_<+Mzv<NG;kis2?_f5;3v-#Z?*N=^
z|Be`e7_3L1u87>B@&V)$4BvSO;B%XUqa(}u^|ajM)1JfaMI+PGcVv%3K>6LAv+dF8
zI0iI8_t7^Sv~jsobEVzg?&+3=&cp31B3gO}22DJ`%#EEtDFpRjPe}*bH3oP2{WXgV
z0>)a9H8gF*Uo|%^xhxNzIkT_YZgj~*N>;<lN~o}~(9qcU8lZAnOUou~Qy|bXK>gf7
zl|$9zBKeLQ?sKP8GGg4O2JT++dLS_u_UrJW4z?5xfkf4vpbCo|;gk1+s;{kJ`~X%x
z@a+X7YIHfkPs*aDS^aH4V9L|+(m}u!KN{qgDp7l~&Fb0Rr&=x^0Hk_4%oi~?r^l>*
z<_w`ldas?<&@pXwzgQj_8QboKW_)O8U_)R*iSzK>z^{OVQ&KM%G^!Wx$HY819Kvq?
zF=++Vwj9p|S6Z?SE!(3ex9mj+w9@L%HRXG%oU%^%-1C~r^h<Ao+0KTkv0c7=S>U_T
zlRD9T5)##fGCz30ee#~zDy+%F%F4k5mKIG9Qb0opsI?vGJVZ(WBfC&3Ho%uD4_AXi
zo#9&0EF%+>$V`2;O}q+c-w1wVGBq<>f#w2cx1+VN^`#9uvEr<tB|+98^Pb?`Iz>Qu
zI=y-*7HzMtELWh{v5WY$f2_W&jD|9G4lu1v8?Z)osz&3=@tAY^hXuXn!lDYR9)>Lx
zyG=hG$m$~NEKQ?$`u#CMLBWk%wrtzBO|e^d;o0KBI$qyW^ezqMN<azQ!EfR_qm^6E
zW@Pky$(XLeGsO*6a&T~Xs+9xnh{qQ-K2llkE$#)Oo!DOCK*MC$32J7Pf{9Sv&uX8#
zjQ5zg7fO20j~*pNr^92K6J30&?B_|z0|z>rb4*(N(^b3e?;K9kNWvOCVE2pOb7^6k
zL&eD@rBBqs$!R5pE8X_h<mP01_ta}c3yYa{qm8*uq!Q@Z*Mdx#X|c*iL3u>M&-EC#
zbCYYIZc)=Zna}w;W5$o@3fd)}GQ8Wi*~cbK%355yR5I<>H82ngq0oJ)i7EwuJ#Vfu
z_WS#52?!~SdWBb64jnoK$j6_qnRzc$AA0472ZxpeJ}$q%-}+ifiQImh_D}$sy}I8E
zV^z*ZPkOw_%kv!05ear)Q=F+J&SGh4nS=$~{NmD`0rf#b@hv{_i&=iA=jZ2F|Ne5x
zZWc=0!~HWtnde@VW9yoR3!zY}_y4YTa&k)5%-p=+s@WTjI&B`J!7I;&S+_e4vrm4!
zTR48|)SFzh`Z3PPf+?wf%~l}@Uj%nVZ#i}9l*2$XOKYBW{peJ0?B#`b1<!WW14y!L
z+BDN{O>=i{3mY5X>sCG)8BY8X<bYeZ{P7$V=zUO-F6bU@8Xf+SxLizJT-34evsHp9
z53PQ&`zi`5K||A0<-2!l(B2zU<^WHvTGP~$S5m3crd6;1{{71>EW8G#=XM=5;JoR<
z^XT0E!n%2eExBf>BNcSjw5gt}FMUa00s2k|KjfX3KAO88M=U?5`k)Wi_mPE6(AX2r
z%=RteFJDSvCxWT(4Cx(wT`wDjp1W1fQ)tUS<#1||O80R3oC1FP%J#=H5Y!#feEj^z
zP!YkHq9)@sUIJdVICVUS^g!i1>t^TW9r^U=6hxLfj>v2YFGV!;YY<<4pyRjny{W3Y
zAk_pO9u+4jqW8)ha$B_LB?dyY(M?1zzUKf~QgE7NsIf|Nn{%5e?zl-FdH2ts%b~Yo
zJ@2b7Hnb_;q2o1CxKJdbEL$t6T{1s*A}svaMp5H`YMe#e17MoX=gyte&bQ-JS64SR
zdG8Lw21d4dc4{yL_p1wC8&c@41xE&I`O4L$xA;zcfY`1FaWgM357aOD8{MN=Nqc^>
zKCimECfRfp6A1=CrwTN$(-<9zS1E^VNJB$IWTW*AEB0S*`+Mk=XWzHskr7+Se(c4?
z#Rr^+I6N07wa_n@4-E|spLYW7J>WF3vF~eEI51r4moIF9J)~?Kcr8Q=&tzw3%O@YX
zLG)>9kJ<GAX$pP}Y`Koi?`t8W5#fsX33qlI_=AMzUH%@t@8WyIk4cBsduJ}ZyO#*D
z>hGV&3AWg&e`jYE(lok0r=1~{jHo#mFJ7D<sbC_S{#NO$-q1(NnwvL5#zRS<Te+4a
z5F%<PB&&@F9d;gc9tuV0<Hh3LB5^tD)(MK-J<<%Y!Yfew8scRturXBgtaNl9|D3mk
zN&sdRu(UAjMbsk!t*4>ry(g-tJiHEzU=czWxgHQe2Qy&=%1vDl@UN`Fb^mnN)#74e
z+3quT&n-T!6u0~=-%;#A)ELy_pP)dEtL)ngT_84*U!I*F-o56NA-HGbv5z_?fzZGi
ziClE<g{2>S4#TCz1((fXT^@uY3+d$2lI9=Cvds`Lhh||x)nrU7MmK~NgmTGkEm@e_
zGCx1R$NjG@<PXDz*-3gPrfR_5+(})H$5_!~R?W<7Hj8;@W$lJA3V|vFBI3W>iA%L?
z%DCG<2AS?K9#&^hk3XIzF><cXPVB-C2_Qsl^R(?ia}E?%34(RVV|#Jw>k&Yorv@cq
z&@%{2&YjN3^ELmR%CeGaYiLx|da_>uAL~Bd;Ou({oDURbRC|jLEHCPN#&QZuN;U5K
z2LM6{Uq6B4iLV5kqJ4(WKfU+N*}E|@hH#F4e|fS2K*|rlURGDf0D?%|nIC`t1o54?
zP1SIiFx7BOwu8~!yLXQW@$oNp9>`W@26LTg%6yPt1WA0mFEj7<?Mf&&^ypSZZ~$oM
ze;+R+sH<gXm;1M4X>o^@wKX6@F%;(Y(5hJhcgpMQPiRg9OD2Ilm6w*vYo9w83}G#B
zIo;Y+>5~<ZKXV5e+Y2}~>3LAog|JM7fSeA$u>4Xv^!@c=7*~h8>!Lf{te`+|+bm|z
zJux}y7Z(@zx97f1C2p8~;rT*bSj%lMsj0#N=hL~DS1>U$vO;=XS5;Mo4XL-9^Pond
z=fc6(9MHOBVf`+%6KRCtWxss60je0Bh9i)B^)k-AP)?6@JTY!lvcS)OGKM=NGm~75
z`S*esSO1PAT6yFTdNt*tUI?Nt`Gtjrq2tzHiMa;BQ`DwiS}otsj0i!{TzwM~4DxiV
zUqU2<(y$%=6rt!uDj@Is%Dy)Y8pPc6a0vR!Dr`a+B|C(Kgp{D#RbtokW&VVA&=s<~
zm>JDT;pow$aDIYtH|j6%Xt0i1si;_Cm2<IZw~g!Kd_J~k06a$aM~@y6F4qOc9FkF?
zi+xyi-@C!WeyL4cw=TZ#w%@W>{)<UWH&z|=FLokQZQQ&$7&|ls4@D=gWO4Qc${K@*
zhldeXB=GPy^m2``9RMaL;|`vkeP{mdc^Z(UzpbsUszuDovn9^3BsO5#vd_-Wme<uO
z&kuVoMf!g_;I&w&(d&^A*H(Bb#ve<m_tjgurTJ|K9s9P!gYku+n5vZ(-~8G+E8}#N
zXNio1(&dW&!r`I~3W4wrb6h7aKSERc(b>t3h2V!yNu-|`37dE;`s=a9bUHaufOWyC
z>8-7;)gGPPG&<9p5Q5K9*9WIZ`DDzVLmH{7htMVIfw75DDhm73qWPbBA*9WXy-U<M
z^R`zxR=@AI{c;M`$h^}k%fM3!{fU<Ph}~p04nbE5Z*w@`uG<$sj1I<*x|09O;m@rM
z{nNdCkQMWbswF)(<koq(yAy2#LL@7kxqp26YU8I*Z?cUle8Ep3?;N(P@lV>o(jD~r
z_3M$TDUpFaV<)4zR2<bNkA`U65x@K%ng^rQ`gKb;0;YPJPfUy!^@sPAvv1yf&pJa~
zK$|a}N%P8W{K<@4`aAj)x}5-QzjFr;sRa?&w#DJdk(JAqFUMoMhPub5uEF=Ub@-^A
z-Co!ptH1%H69(k@8t|myJUq<vjF|9DFy+cn`S`Os{Kw$n4WQ%l_wU!D{8pj98v+em
ze^BIg1OVDdd}OFn4<9}>g!Xg5ZA$3E`&gY+rdi>%gATvF(a#ehl?H}{R1hZ*1^UEK
z4wfPdbOL%t#tJY@=&T=jCm&3xaI$6?ljewmSB0`MGCyOF<(K5x-xMR`=9Jfah9&J2
z5r$VVvKxXe9Xoyc2)Z0I5QtmeCJ$+NM1);lyLK(&=1m%?F;?w`n_#XA4}3_aC!aK4
z)*~32d-ql6eQd}ta2ZV;Lm(k(ov+9L97V`sx*ZH}8`9S@6O*6DqDpcsENW^zzNLUq
zh8HhtJ-FV$&UZ3fV*+xbw47EDatw>(*kbN-R)w#OuB9Yp98HvlB+<~Ih1VCTg(zxd
zW3xN%#EE76+5&Z!>|&y#MkECh#l)8ua;nyxo)14a8~A?>N^l`C!L}<}`Qf8S>`oh%
z4u?S+0`Oy$3gz`fYT_mXC=|=qtq_ECniHAXj$gQNAv-5$ml|hF2l@U-H+mlCO`BE$
zayGZN-ih&97o@@CD-Zb^Pje*&2}<}^VDL(QZ9i^V$u&W{{$z`PY1qGe?~wRv#}|f4
zkI&QJWKlbfRSIE=R!T|=sRQ`@_!z~WJu?Gv&#~Yy*z+{kE+mJjoK`H|z2Spnw~KU;
zhw%OB?Nj0fPo=}X4MgzTnGw9(lU|ycno<-<34`Riq$I)q@bKqi@g)?$HrIJ$<%9bC
z4|#bHuKKRIaK}_8$m7Q4C-1l6-@94WZ^qoxuerJIV{7wE-<{6$o;9Lnvo%(yCUaa2
zmq$I@6LBk}o+&xyS9+`;&3-1U2$OLhv@JHKli3VDad)L_`(Dk*3gzeSGqF3Y6t&?$
zVjl8VR#rv<Nw>g~<P%l7#l$qa&4@>SbK6mN?UN7n@w-8BcV*d~9PdO65A?nN6&$FX
z0WSwXZ0ZJC+`y0X-nW+4)@^(Dt^=MG98k3rH>p}pT0iVuSPOy!w!xgZufL8DTnhbW
zcUE)1W&IZ`&W@nppKd0uKQP^JVt~OT)PAW@$zOfF)3L*+@hZUoyWGSr8Xsm?s7sMY
z*4!+A;>qv!w+Zku01k*<<;SU<Q%U=Txv(X%2-lmpW-4N`*7(-pi9eFI+t%Ia;W#|~
zrB~G0erG|JZ1@rTu&&Y@HOpFiP+ot)RY%p15;)5M3GCR(le84!PvFYlumd6D|LE@a
z`zN2Gi9dkMlsgIMtE{nc-Io1URD@*i0$jz;U%zPaBClS*HUZP+TL0|!ZFbyB)7_k$
zoK|hGSU^a8;JD&TACiwUS+u3Z5~a%e+jF1%d`a{-wHKCW2U=gM-1GWbwFVX<G3X%z
z9m&!!8bPo@`b|3Ig$wUCKey@FiW>=GsSN$>?797q`O8^%oPGeMjtIU8$`H$H!eM5O
z%AY@f2=2rM7+F{ZL6T7jTv|5?PFMEk%?c6?IA0)!o)Y!g!}Sv|EzzD|<>z<1aq?|q
z%?KCTJLH(RcJKwKP_CnUc&G{PWZD7T$?INg4w>rZW=IQ&Y{LKVir6lQM-5zf6tNQ9
z{w85a=p38}9U@Lw;j=5q%TuQlWN(1sR^VL;S45$psKv!axH3%Z)~$Q!2;|HR9|pdg
z3}x7qp##-;xn_p84@?!~&#7v}NIe~UfJYd5;l%r|4-Q?|_?Cb^cQQei6X5&}p8qJs
zIrQZnUuPBlS07SVW+12<z|I7a2P|<JRasTl^{hcw5%BiPpGH281GW@e{b9t7#vDR@
z-fn*g-1*9Ba5KvP3NJ4&rK3lCU1VUS9s!+GeR=u3UXd#s)QD<GHlbXee-CNe0Ns9Q
zY%E8|%ZAcF4-1CWSE>`i4?<pGmivQ|LB(C3`@{>3!hLuSd+%m%^RA1Br@#H$QKzcK
zm=e0Ty3ysCqMK&*G&Xf|)XlZ49cP-DJs9>zEju&q%k#KOo<^R=urGekbK4g_kNjsZ
z+lPmSDj|o1?m<C5p(4%){Y7-ZbW$tx+zPk_L>4Fb9hNZh`#GhY9^f8P-Vogrfggc$
zj^Os72?YVKFmBztmGU0zuK$UfM~EH7FRHUB?$xQ2Crv-WxW2QFhq85ae1oebxdPY^
zGh>7dkz2BT`}Uf?i>UANK$s~WFj)%4Y=EnY=787V6}>Q4zZ(d#8q&lK^u^+RJrX2o
zfR#cQakrE>@Pzy#`*c>HF2bd|w!MApiQ7Ux3W@T7tD`U>Lbph)g&lk=eygF4O*lRS
z?5PKE_8=x4WEas31VP~D<y{7k<1g`>t*ln#j(pD0IrFUwi=_R&(zlkD?p>GbI2*dS
z?gqv0Z<>B`=jX8@rwg;qV`rC#{W?9dDxZ04++f|8`?TIQuT1sm!~Fy7cfGLw`u#g6
zG~$5!_qX6a5@(booM0eQ-j7uhx?mJlBPufr^B)Q}_pV*X3$7)mr1-&jAi6g&lmY-C
z@yhWc%PDNr0Fa;O<{uUEz9XX5a=Zux#U=PPE+zNEe)t?zX?Oh{QDlwCG7}XQZQRGR
zjh7cGrhC>hBu)jEf93ZF9)!)3p&P>0K1g)}jezuOhXu6&8b&^*6}%Kj;fd3;vPL@Z
zKi@;@8r;N)8+_ehD3D?1@u_!eJ>{TqYgXnS#FN*~Hl#rW>O<0D#sdcq5UMo-Vvv=U
z^%;^0(nR3RHTG6fa#p<Cc?IMf^t<Erx*x}<qsd-@XgknR!UbFh`(6p;iW!}jqNk^a
z8M>3i-XNjziixeqci@AhKVOSI#UW`&OBgP;EAnK!&)==JJc!38$Fg~|KoPMy7P7~_
zDWxVSUq@Qz*lssBx9$A=<=|7$o1iO{!!XK$wNFL7nR^7?Y8{F5pupH79*5#Z2b8Nm
zfO2~C4JT0fYv<vfe8r-?y!mh=KLs^&CRz!s{A0)HJ?91`;L(!oh^@2p9sj3>tUs#X
z2x@cbG$q@i(O%dxF7RaBZPzx=jA5;Ct(-tvnx-mO%gj3)pzZ^BgP2u9w(jig^v2#Y
zga~oKzGpR(UH$-1G!zMRWkxzz_^$z|2`35?2=wo^{AW?BuL=qj5WYYWP`5WcjZ2M*
zB!nDK9sq7XFg1<ol!Pl6u6y-nF?#5ANCB{B1Iw@8vVS$mTseqz=kMRzrbAuC2f@Eq
z^7uOV^?|OCT@9rw#T8zEZg=i%gPF{n%83(<=w?96RX}103;C0{6$E=L-uar~svS>g
zUFOszb&faPcV@rv1-Vm=`7idl-kE7zle%u%4+Nx8h9>C&uBZE~3s$XNTZQ)jFCn0-
zyY0Y%jSUHMN0FnTC>W@XaV{hoBjuDaQQ9ss2~~y&r)1M(tsd_Ng(UetpxhPk=I|E}
z5|kI;$C5DJvSrJtUqwNCc3{I_4+~oh3{HGGBBeoZ^y=M90$5P71T-@OV`4UPNI9MS
zHjN;JA#AdLk&c<3El?UdVK0#wC0fUsolFA6P0v9{fZR7+?;B_gdtAm$L$}JD>+@P+
zx<3ecpUot00g3{A90<frQBy<TL%=7Kk4N(Fff!!wG50`2KrKz3k8-i$4MmZ2a1a9y
z1$gG+t0yi`j!X2fW~IM3N7W>i_(C4}FN<t7onmo)&FI!N@oWE6%fZgIruv%>x{Pfn
zQVQzdzp?>aptHA^j`|D6#R3Bb-y;GO=@=l(&oZkK*g!yy<VB=qWX#4%+!Br37?+lc
zhmK-73Z0%f;hA&B@Vo&3e}u~|dLw&yp&|YTg!vNtyP=`0S8v*@6#T^aO|W*J)h6$^
zPsDJ?4}s;J%d=Vq2RxKRavcD%`rc<yGs0)Bir`ooLM0*vx$XOR@(@Vk2@kO-LmzBn
z6fEiU6D=lm*D|O-du%)9DQ{%<;LV0L$j+^Xzg31y9BH*FNraRz6AY+!oHPQ&@*q*u
zlA>HNeyd%Dr=3Iox*Z$rX=E9YvP*L~KIhS1Y`nrdypBg82>}d(*&(w2{?nbcYq<2r
zv6J6f`TIvMUrG<CwbuKg`%d$G;;nlmhyqMNBFT)V3(iArhp>W(mi|JoTaclBQbuiB
z^7#QnRwJHTSB=xv-MtU@$_fPh{?x7ej$K&K+LlLpbAvu##kT{`bX31<Jv}Ca=tekX
zob@#Y$;rt%j{Ta*z8&+Z`~B(6?^C`=uP8w@2fLy3Q}DrZs_U5s*l4v+Yu{?H{oujP
z05f|;MSXBXh@7^CgNcH1=MQH@QALFbHfW5L^W{Us-=zMnm2j+;t?yGt4&T^2Vk`3I
zS33P`+;x=mJHy>{Yc@yq$GM`iR3bf-0}0P!Bg5>(`dPM&%1R|*%Ve0b5Tq5u9I+H~
zoCeQX%nmX=gqja$fK=s&DJhB2RW}~6<%TH?>#WffDj^}MY=WAdP-uw-1`Xk1UVr$X
z!K2+m1ASp?x=%0k|2?gw^yU);!#(heIC`OZ{c7&GAuH?`Z#XkEb39JOKKaQL#w}a!
zbMzwh#7MW6qZ9>M?eS?&N*+QMS>srI6`;Ye9gacaM~Pkr=&O-=j*WyX5P6exy%zl`
z*{+@Ajf`OJw=p)U0#+6_EySiyCMmyCu;JBsgU4xPZG8igQX>HRt21LMV#BbJKpG-%
z2~sF!X!ZVL`ZY*4eRz1B6#~UEM>J^L-uIl9m6h&=oMm3&buO=gr*55nUrv@37-moK
zyiVKKuNweKiJebUM(&8Ekgy$I=K<{I)YMcfFFtb%i?Z_aWol|_lsEax%QZlU=kDE^
z{2eHf^6()yAK&47Vd3Fg^@}6e@=8hx#k>iI*ng*HOMnv)uUiWpieO(f{oUDv?;)fj
z%OD)#c>lLW?>+e(oru7|)W3r4r+jS$42q?pfRS7$<$dGEsXV$%j~+kXcJSc2zL#bu
zCf5Nn>iSGi^)|h{M516JA(8s<`_-qPGPAIJ+>zeQr@gc|x0_fSx~*@0W~8O1nW3cu
zpPq0;ZDT;4#gjhaNI)=f^1s+GN?8iWeLA1FVUy^mxugx<6kw1kQ$BVqBHnZ@NuDCX
z2--~xNWKTaB3908E6IAH@Q=LNVDJEt1t|p@>W?TrQTKtyY<u2rf-<-s>mhRMxfZY*
zJdg)oON*~u#`*KCTCQP%n4m%Wy=cWq!;$|Ly)2wIYPPZb_I%foFb*9<(VMPpuGbua
z&;QIEq4u~=n4@m60s&ro^oXDADD=D})U@9nC2|nQZ{YUUR+Td#evRG#5rQ2F86$IC
z4&CJ84CFjGs?11is38wQq_qk(ZU(c}5Dw~EqIR9hT_cpKx^v{Kfft*Tx#dOlYXmxw
z8PCjCto?}m+lLY_uLF{jhmfr%fpKY<y^s_brJfrne~`+Tu>Q7w*p-6_&K<9bp=_c0
zu}vdOpY!qQxH@}xB_%EaSxMn)sQ{n1Iipv5N4$s)C!Cm@oxSs+IYZc^M;D%Yc!yjg
z_9(Ip`25JRExX+I%7=hj`13_f-yWUx^IQ=U`1=fdLaaZ;f(QL|<1JhLCjTe-K=_XM
zua5uE9F~Gb`u3jqiGsQxLqkMJ_f&lguLpw3%_680B)v;87J50pbO>uP_j~8WqW~tZ
zB=8FK%Yej09$a8B;zh^DZQ5SZ$jQkeP@af{B9YDY3$NaMtj)%-0&VO%BFGh`r35)Z
z$A76@-}71NYFFhd(q0M*3Lw0^fkbyRK3+su1WpMWxF7OR#K*eQrPOjb_<u!T>uycb
zMgxN-0mG75eO2hD>qyh|Uh?2$!C+0&vZ$C_VRu%gHJ;g=dn-eN>+a-U9yVw?!#Zc$
zm5v-C!4py!(F^?`=_TVm8*Bf<2mqiZX{sv-48MBy>H+M!tCM|f-fxda47NNwI;Hm&
ztAuygu2pz1x(LbGckr*Wjo&bk&?h_$1)$w4xH5~oZSmE2CZW7XD9=USzU_~f{E2$s
z41=7QMi{C2b<PX9u4BiKmmz#Z20j4l=nw>?yrD9aYyjz{pclT-{5$dM7;ZTcA0|pc
zS7yUtLK#HC571iv&ds5S9Bk-!!4v{1$z&=5@1$MqE=hcMVpZk3f)@usoFGmicIeM)
zF0V=mij=8S{-*z#xSBUU40=9*kJ2&ciGufQvx%Nw+YT4;oKkxA<9d3r6n9rw7lYJ#
z-q{-HoWj8Hm3Zy(7xO=3wtu|(UhT)8%UR~qy{WGzI#aA>ubjMfZyS3T*yb{CB%6Gc
zCy_q(g^^0qnNaglsUTDAf@{qE<quMQzrVeBf-nF2WlEfqe=dm%!1Q5=$|-+<?~BJL
zk<v~Z0=gwJw>@HFQTiyy??l^?kwpp;&rgA#hXg|@0v>sMnPKr8BY-6-BIPmb0G0ZL
z4vJPd!iMM{XV>0gMtqrov^$Sj*R7+aa!|>pMYe3+DnbRq38Uxn{X5laa~PDyS3NDN
zPw0Gs29|gbz!qK_K1~wZR_;M0%2<JhSQO}UkWC{-00d6^wjLB`+(oqK?pFg~z<xnN
zL6}}S`*d#N>G1L6(gEzQ5HyoizPC1P8GJR*L7BRl-aeR*hL7X{T$1bXkAdBSkOMfb
z_=(t<z-BUGTykL-8{&Bo1cZLl$hKNoSQuMw1zIrKcI#MKb1r=qAxbYr#*GknPK0xj
zJBZS#EFnxI4}o}Wy)&-J^qrNCgxGmlwPzlkEW@1xHeH^g4(B{D5ZLlk-sEa7Sq`lB
zszk+rPM`_g)+E=-K8g&3biwOvWXqIT0GUhG&Pl2py^zUDLDIt2kG+3X-_{1e0KN$w
zU;Qq88Z?*@GTNh;Z%28rT(h~R@9Nd7hGo}QAbchdcb0G~tda`!Y?w#t<9rb<cZB7%
z9>70eZD3&FFx0jQ9jIn}jF0U;eNdq6GO2wYz%e3%y3JpT<ZlUbKVzMQU54l93C_if
z<Tj{^!quw>C~j_U3SdOL@Tw@*Q^<!8s?hwDo$kZ{K!tHgUc<dKg6oDDcK{eFb?j7t
z*W%1$vCpT$YX4s_)SAhsdH)@TT6gcWMq;LLiR7U~)nm0C)fcR+LLoEGW0{dMNNDEJ
zkjR?zHxu~Ffk7YWJiB1toSir@<nAh`kBPup`uNJ?s#IYuGqdD8J>hIYZTX(scDN|u
zsWD;}>kxk-VR#Uq&4B-9#N<Sgph~gma~;PnH)r#Jb><*_M7TU)?d^38Fb012^?~Rt
z!-~$Y8Y#XKud%6e1~nUKj1LrJ4frW_ci~2RHRKvXQXwboF)F9c&@b8y)~g7CkAyOj
z(^WX}#5{K86OFWM(47v^^PEpS2&Rky8#VabY5KOd*;e@(i}r9!k^hr+b#tp|ZQX(#
zi9cX8naIE>han;>!-E%Zi+gT|K$MQ_M}B#K)6?^eYu4yT)`ldF*5WSs7X63f3rV^f
zHzOr%c*RZA6?AmO0yJ;Q<pZ%|;ot~Gjwu;ilp>+NKkp0w{=G^D@@8jSOyEw?5xucw
zX>kj*tjM|>H*Sbtc)Kxlvp54XQ$Q37dU_m?5=mSFS$C?&jn(Kh06HB2F73*d#`u`<
z^;UwcExtDclv#!LM@Hcw<v^o}c|J^d6YB6sj0U-nzmtHnLJ~^ZF5?%V93N5Elzl|f
z6=Z+`o)?MM1NGA3UR2?unFXB!DmxOs^+s0lECUY@4<wgL@JNb6+j@gRv5$blG57DA
zfWN5<M5k(`t@ADvXOYEB0h+TPB1Jt73E{Z<6XU^SBkK+;8#yl%6j3&&li{tK;E8KX
zsO0Z%PFxra8&)y?()v*b6FkJBMyiTTw1Il>1T9aQ!5folDg_l474*VDxy8SVP>o39
z{DLkMMZCs-Jz-yF<rH-iEZ0caIBtIF5+hy(X~u1kZ*OMBU=0g_UE0UKM3RVPrinWl
z5D-9cKt|->*0?qVXao?-BJLt)xyanvy50JP5lz#GWrbi7GD6`b;t}z<ai4b${>1Rx
zo4M0BsY+BNQ!^Ac<H2t)hQEJ(DV5L2Qwc(G81R%>%>XVeD9(|N2dBrz*1;owu@Ma!
zw2cM2UKfaKw6QF-a3ogO;R^~VG(dCbG2+l&l=Ex*r6qgUZvVKp?)3_VCQ&N4Dyyq2
zkP=6D*<FN3ZB=A!Y$y^c1TCtl>{hA2aN{~4hIngqdWN8GN~lA2v4PCm{pWoDA9?Gp
zpkCGeEbCa<xLIYap+N1fzS%bTb|R<y$x4peBKmJ7UUIjEbkw=~aYa>teWbxm?n+i+
z`Ui6^Bt4G1v@H75Py5u7^WgH=Z*z&6Gb1eXm817drtXHN`Ee#pXNb5x74bOt&rnNi
z`LC3(^xL=DZAX>3w)~q$7Jmi{Yu(xME2@kr2>-p=<Q3*<u&HXv{&kaF(pM=zh0%68
zvojz6O*=Eh!P{TYaQJB!5YKw2z?uEnV^9TQ>eQSyHQnwy@!JO?0wxKTL-!FHh>%^y
zK?nS6qIQ8|YFM^Pg(kVtTTxM7@mY4Vz&a8ALd?jlrb^+peataAiXC&*^>SQsv3unl
zpoICQ4dK;{n>KBNkCIB>0ID}~1tSa79VSQ)`*FVCaa{|}rmTPV_tGTG(%A+d>xF$w
z=QV_%6?$8JFCf`S^ns(GO{Cv}eN%T=ox%=9bZ-^33o`45EXTP##9s+gvGTC6u)q{v
zB`_dGp=yx%A<#`^E&dZy_XuiYH^8|f6H$;?sl9al&w-|4GlP(m5GY;~%ZCZwTXKI9
z+$VZG<lI~gAU{CeBC~*?2{~Ai(r=JbI*1`o68|Ey5C#;<@Ehn$G(sGw!T%6nO(X+^
zU%nhh`NE{Kk5&D5OtE6<0r7#YAV~f&jgE~QV{C4Cm<b<@j3dIJfxGqYlcyP(p@i#1
zrlpaR?zzMn#YtA!HTJwMe~ToTmz4Cka^2O@r;cml!4)_UhardY1MBesCZCBl!9z=R
z{%-*^(uy5i$j=^9P`LK|{eQvG6gUVYJhf6R1KaVQQ=|Zs*#f?0I$Ab%Zio&Y>-N|z
z=P7+8bfXVKs%6#HM^nt;Y45RU+)kp6WY7$Fl~4uD%<6X!E+dXEsed=NNOS=y0?*V;
zsvQ`92G2%FJDY+nRSob=hTuRhyCBu)x<a;m1L!9Qe6j+t#r)HwHUCnCF$b>j0tJw9
zK!Rw1=mKB^KDUBD+2PW*Fh37TBQ5NduaeS=<9BH|Hqy!e+H;0drRb`bN9#U$kq;wk
z9V|J>H_OqPDGDpBaUSZ~Nlh=j1R1)5(l-KOumYkt5G{$20b{M8nx9*+e#^6F#C!w^
z67;;iOD6R?fBc}Kc0x%Y_FA-{7IH$2RC}wM)RR@JY}i0bD5e@unJCgm&@LW!$HvAo
zV>TB*O6GC8Cjmx{5Cpa*;Z(xo5iqPjBcwy_7A8T+2qWb!Y2QQAt=iAcS#D!A|H~GV
zV{;myrwFA$sM{M})20sh@iizAs?RQ*A}o>0J^uo{maDO`(eB2NL4GZDIdbU1ia$SE
z2DF}<(lRd{cou)g<b`$9|4W-?6+{b)`tM`hB*ga`9RPAa=c(w_`lbU9kHWws62-<n
zhTa;0N%6gp_8_agD}NcKtE-FAB_Wl5${W}~+GUIu-_Er|zk@4tR`YiBt7UhG$v`IY
zIH^)>JyLd%zkL8oN+$Y{qS*PRK{-8bgq-ytaBP*z7hRRZz&8in|L!4p6TFhl5t8um
zwd>b^{QBkV?M;#SY7iEG^l7w1$S^*zh%7iEDWVmX!$%<rd9pb%@V&2X$>yJDLP9$&
zd5(^bDN7|;_Rb)hIpCeqQ?-D!`!hkt#a%AAjHjQ{3<W+v0;|$&QcQf@>BY$4+DQgK
z-qt)hen1prKqHk>0kBNe6KKY?*bj6OElL=QtkAmyA}<PIbSbA?_$KKVY}=C?`!es)
z{db)ZUor@H+vb0PGuQkNoT*^B_HEF?`}7?bpk}A0?xg2=pt>{HItw%glO`2_H$R4l
z6NU#<BjFcdkeG;0Emx#~B!Q=PJaGdxM?9QXzUS;qY)BJqu10rMGoUmA_Oa`$uzXW!
zLr(eng(LQ%cF4}0KBn2s$-E(l>o%`_v0?>BPq%@s?H+>vAt981`?eV_%GJer$#jjh
zWfbw*A><OF6FuJq=|jnQ2RC#oqNjqzRKb&aXosB{x@q4^kp64xX-fEu%wNLvEk)nx
z>v;H{zx<^*1S8lc)#y`X!kjqJ@Eh*%SwqEogWGLnX~_W4felV9WD<-8_G1*vbKWH7
zBt)j$p)SG<UycHO7<2?h&vX)7k^yK|BTan;hIExMnF`&Hjw0Bf=wqnzyqIDKOpI>V
z<sLres}p3Qps);+YhhR?5bF??ovd)m+s^v%7LEs?k%u79=Co63;%1TO!Z}|*zaUt^
zy*4W(oL7mqOe`7j+Y~OA4D^Uhu9#awA;cU}I6-MpZHOudqNRF|Yu!3tjM8tLn3(Xz
z_!V4nIp6EouWP@uHOiZ$m@z|$0Bv0lay!JKA^r+x+J#Br4=;8AY6;yN&w*x9e3Z&c
zFmB{WH&B(RSh-(7PV-6L5QUK>?2V!El$Vtq(%i9g=P}$DMO+R&rq~D=CNl#T#dq%9
zfqqjX9*_FYfR3%x0*L6F{`dnV7DgPZU~!NH^X~3F3@Pvk!K(Ng;fxlZO^cVmJwFaX
zN`<^Amg<#>-)d>^;gKH(lf;~TF#tTXf%~Z6E3c(u<<VcXcUwvZCa12rCpdekD0fL}
z@F?-@=iRUkzStgd@xxF}=*~CtCw1+Rl-z_Jj%mtk@$veLn(OkU#xIvkNEP0XqH({t
z{HgU9)}7rUs00{qIcJ#sMkQts4fMovC_b<`4!?O_yn}C)qmEyJHz~aAg>{eWYJkFH
z`H)+Y@gTkWMV2nT50(|7KDknYX{LrqQcdKTo2NVOTsdn?PNTrxkTvHVE;uuW*g72I
z(w7~cbB9_VbOm60uzaMu`ZeyBSzXi*PB*^w1O_HCsYW;}tB=092w3{RKdC0;18W94
z4bcO!Z?7vPmcr+?&y<3bgaJK52{earGyN2J+}_2@=xX)?xFbL)iiJYVeJJtlrR|Wn
zS=fAN1p&&D?AAueU8;YuIcGV@OF&%Q`LOZFNL2vk{1L~5wS~UByEO5$VEU7gISxvw
zz@yBz{37sTh!L04O2)L29!=F-f=UbZVc0`;Kb!S`I2u0!xIE=i{OmKw|Bjjvs}QiO
zF|w@#Bz*OjEnEJWVUxXMgtm-1KF^u%4aCR*m8ig09mT3n_wWh~+&OG#8FY30tZI19
z%tj(QqV2AC+L-^X*hA{vb8{LLBKSz96&1^orV<*+4lYtq$!<T284=?7VP6wb_)-xN
zY%=yR(fAP04nP{#qW!;E9A?PwA@RBvSj|q)05}$klG$$FB=_TC%e%JrO79-J(lftq
z2yjiEu@WeTqF{*Ktb+|N^d#Z-ZOx5FJs~%5vH(M#Z8rKv#(c@35ZF`zDrPbf6@YM_
z>gB69C$e2SEL(PO-^I1hpFc;8dql6F=sw8dkTN&&Ma#g5fDhz`AI`uhL4N4D)!mFg
za7#G8N?vLb0#sBc#=ZE!8kXn-wO2~BIDH&5y<d5Ck9RG;6Iyy<;<H@`xWW&H34pO$
zy2dVK8n)qa%U@7Hs+JMa=5o*~Xb*_*-@H8tVvgxl0bPT0=QcwE&M~T3iAi^=0Wc9$
zlSHR^{aOlO_+FNFW=6(Cc7!GwDQ_IvftXc9Z0u^#MWEmncs&B2RaI5PPT2s%UxUe)
zVTCLZ0nb>0st6tn;hYqe97x}5VT>NQI>JrLKVsU*{PXVJtDe%`5q1VjJz~A&L>07Z
zOare$73XfXL-6wmv=3yE17Lpsz_?3eArwcbu@wl4Bil=w2-f@fa|0cmo#Sg$JhKu?
zrC&%0BZ4v{U^;+^lR<y-$-@WB3fyP*k^}{Q0J6}pb2e~L5FFk`&Tl|+!w5PV1OO#v
zW#!_RG7w%+vyW$igmk-|SJJqavYiTQ@QI--EofTe)48&A;dHfhO>Dxg2TkuFC;u;m
zZe|6FLUatLI#98)9-GNd!^a}pF_tI|HNUWsbFpFT_U-c<zG4$0?6}?WPmK5_b~4;U
zS|AqeMsdsau2TcMPSApfw9gQoyKYX*bN*`RM$u(J<kwKzmFsC&tT2KpjI#+=5}o}&
zC-N}VR8-fx!W;RRw+V7wn2V@Hc}5xV!QjL%3r-z!D@ddj$5W7e7K!8JS?jhHxoK(I
zpc#|Qd;rv0vd0kqD8q`Tp}=gEw6!-9PZx{L2-$rQv#8sUruwA9Un5!mbQBE;lak8H
z4!aVRSeD7-l@#ykzp}*$-+D4-?@GgrNg?zXp0ATgBPdeLc*g7s^dFyS?Z(KVK}{by
z%!FdboQc32_6-|$P=OFd3WwNP*z9pi6FV&YE|k|9-9rQ0c-YTwFwQ;RQ^M3x|JZ~p
zO~R0;5}}V36bY?G_gyqKr3ZW<cNsb|NMw0qqdGZ$ApH~6qK_{wY2nMYwY4PqA1mXg
znHP`KLP9`PPJBWe^yuwJb7(P^{CCIzDugeyf^R?oBV~*MmRwg<WOh{2++4^sb?=#A
zV;KYG=N?45Vgsm+0OtlCU(8QtQrvjK9nr$jw4-2plEwb%{rl78umR1-cwAlJ8|(`6
zFH3+&Z}&V-NeP0O7z}cN9*yd8<2UgB(^hwwwo>79kkRh<=i)F3qO3?3OAL?wr^Nl|
zBFj|Y7m`ZJ-OI(rHG%(!Vf4;1A7}*gm{1=!Q(!ed!^LxJaU;}s%pm-fjFc1{rrobN
zxp|jSpK|3B<d$9=PoAiMYiD2m*6vfTWyeDlfqN1*YY}XKaz)_y@6TzG6Zfa#54d9r
zkC0NNdi^06Kmvy+yo`GA-;ZmN?7}_GUi(?#n#jkq5bpmXf<eqdoF*bK0DcgVmSz#(
zWM*hc0i#)b!x%mQdHtt@-fv%jOF&K<KcbTl;rpq6k$@l$1Bh76!rLQx*$Ku>d1GIZ
zSQjcDIq8HX_Ysy=O&{*;jOcBq4DrBXFyoCl8DE^@F0cRaY>9mM@DC&>44?ywErT*p
z-z2K4tGfjUR{WCy->w}1jwN$SkX)|}wMqWj>)6C}9Nyg?$36{`?tmIr0f0>6i$Z#@
zMt%<NWQn$VWacyVWbwpP@3()J9eYa2pE<({o39EjiX_k=c6PlUE>;9yCTtRiL1Apl
zc(m&cMjE^^i47+@0;e)$R)FB6=w6)~*tC{Qb~SRbD5J}~KRb|Hmjuw2Yu(@1r@SPw
zcdzS3tm>&sFn*11k0plJ(ot*HtVyfgSARdQ<C!t2mpJCSc0YNH0fEN-&k8;0UMnQl
z<PC<`HZ(9XamiL9sY4hNIc|uktT<DQ#&kc6EGXC4Zj_TyFo^oP|D1JP=Y{#rypSzX
z&NHX8!B|Idm=sn78Rr2siuOp;Am+2!rKXej5abf02!%kH*KK$V7?&iB2%^A55p+Hy
zV9rKYsubOd%=bp{D3Ymr^e>VuL;S)p{wE)A-JMrnKAbiSJp&uH4Yjhp-)=AcZ>jSL
z{4%zT5v``ENQOA+xQJwo`>7}Wz{zF^48n~ot*;mSy0Km2Hi*&j;^_ul16ne(!m$O1
zjy8Rq9cFa#VgR5Z9)(;-tJ)4o*O-C%0d*wzrxQpNfw!8|xLt7hRv{sD8Bekb$&!>A
z%)^r;AA-B&oCh?1<yB3%%k3_YQviLfW&s!#5%neN_4CW$XRl93j>Q<tTpgiMe5=t9
zMnQ|}a-E@#i(PKp2**+hqB?Asb4xQw#rFKk@&+2Jd4y?7KhVt*=X@}^pAZfNYytw0
zS+@^-xI7f&(rsB?x^%F3gZwQvX!pQXWLuLlNGv@<U<A&lQ<R>b-v4P$|3?JPDlbwb
zqGcH|VdtUr5%FE)GF%lj6GJ>O$m3)#46Y@ik$`680eicGeKtL}I3w+~$bp-D7>Ju3
z?FUoD;P&%Va9B}=u*G*Faf6dRt|2MRgL6=(0{&KuAtym3UDQ=*o-1KY5Kjr6uC@=Q
zl$<U?00xPw0uGSjX^IF{pP!!Jg5`z@YX+pw1dCqEx8I{jo`9$ULi&Xp(Kzl5J^lLi
zYlHn6fuciS-k$@wU`1+!9JghR|L+2J<CT@whkz4=s7NsGP9PHafp8>3!1;o~1=p*-
z%qdq}C-s{}?GaPoudQ=7?>WD94E^1D-wl(6fJv+Xm1N`yZci}wUNE|gh3BzjfvIO6
zlM{hh@!7i&EF+AKoV3u=v|Ju?KRwQ(x&K&0;0-3ANbJ)WlbwVD;>F0(U|j3nF2}WH
z>E++b9D;-AS5#C4TXsEa6+6z%s&Qh~P*sf}>M+iwAk85OX**+p@J4qWy2HZE9C1k+
z^p*`Oer_%@Q1oY25^bFA8gNDpY)KZd5*9LT_Wk>L@@(!UyeL5`YaOzHtT4UHzkE4M
znsWL+n7e8?g@yP87zwM~VBpR()KQY9E^RXoai7X9YIi(oSAKfPj)6zxwYwNF6uA2l
z<oSu71t5Zn8y<t>25Rg7M@r4(1D`dofaiZrr~T=^@?(jMPH@y^O7N_XR^IAN@Ay_q
zMqha6YTPmuY)hXT>~eT*a*`Jwl1Rkl2DahZ_^3+z)Vfo?P>0oBQgq_Dg94SMWj?+A
zwTq8tPqg#OhQimjTn{c){z{J^DFWOHOmx5e_Ep%o6gA+=uNsz?xM+>Nsof&L$r_k_
zDW1N}f+?Nj4Pw)@eS;4}WYe(%x&Su0o`*Td&Hd;65eYnTJzpc>ITmY(Q-RoF=9qtY
zKm&A#V;X5mc>S1)N;MfDLU?JzpNk@d>3w=V6eWZkA11-{;qh*jRZX}}doap@Avb~|
z4tUIpISsWDsre8jd%1-P*5ai_HypiH_@E0jI|AwqW2cV`6puyyJKPf~<$Xjb#`Z~s
zSo{~;ljvuZJff{*6MDN)j+0c>;<rxW)Hol+L}_Z=O??nkz~%72L(aFLPG!RmUV+OR
zg@5j)Dya)Z`*AAVy!BX68%QDd<2Rf>V;atcM83k2BmT2V+js?*VE`L=jtolST&v^B
z{;X;}TwBpbh_-_RJsu<{pK0b{TjetJYb!fD|BW#LUvlbbO0P`OLd*($7$2mLa3lyh
z0Z5|t)Aqofk>qg5Xu-#0k$SR@0!(5Irn1`mUef7Zh!$KQtTHB`d7NYWjlf^XRJYH#
zOC;S=M)O39CSU)%a8U0D>GNd_Oia5|4+I7VOJjz`+|rT^E@`a(wX3YIzG54hlu{Om
zX3fABNCW`KNnTfnQ(r<wU+OHy_X2|j@lEhqZUF%Xq~@@Xs-)(OJ%ayZKuaUV?iw4i
zli-|xme3!RqW0m(CFTrrc9Sz?)rQ7C*Diqj34FPP4pn>&Fo<_{J>DDft2D8y!<Q>A
z<}i_;jCOEQ&c-1q$kT_ys3GG6fX_myul{|8Oz9gJxe$9G!Z4&PL=zMd%D6H$phK80
z)}$+5f+gA%uYusu2f$YjOm`55gncRsXA{#_KM91u{K=s=$MHEetbYB`@s(V~#B`Lr
z5&|=%5W^tp3(h>YE2u#YA5=Zy*44G|zHZApqpqF}^N=Lraf^uG0s(ramS2lpvCGZJ
zr-yL5Vkwq?4!RReXfk9@mfBry^0A6|R8IK<*pnPQvd8GygL?fhaGIoW85<wp=omjj
zaR;$O&Er`!rk{?ma?(B7?uq9W_&ITVyyEz0rBn?8MuD~emg<q>gZZp@O|>D7)7kG6
z<g&(;BX8Y;Yw^x~1^F-<ZE3M2r_6}jNMx`G+#i#;?Cd>cFG6##0tfiQzMZ_nl_Wc^
z419;2T1R3X|7nDgnL^wpA_Zby-i(OwM&1937LA)OSo4akm*5Qd8^1h(SqOI{XbAZm
zGV6mpPZEfI!a$5R-{@L;d|=0&WC?yh9FqbQmlXK|lYc8<`-q4FzWsl5_x>At&Q?y&
zHOTdo=l=HXYLus=@N+WWLty%Vvwd(HW*H&^Xj#JEMdYp26|Y6d#?BwA-+@>^lz$Wg
zkBdbp^PK=8(2VN$HvlzC*tA!Y@P_lSeyp_1I-rNBp6crAWORRE%ztwdm=p$rT!En8
z?1N@<7wm3j(VhS|pPl&g?+nk-P}`+N52_R$X%v~1UW@ado;Xr8fD1F;b9(*cv^^44
zP*r6{i7*={bQJGnNb~@lZHXP`i*86#Gb-`YG!)u7kGMD+4n$xi5jXraIWv$1TE}1Y
zk|#ZUCyTZpauPWNd5`mu9z?@q-Eed&@Dx6?b41*IOO^o;{$YIa**iI$UjW0;wBiU>
zF^)!A4w$YUheOM1j3-A&%aFss$vVkRSIL!)MH^Z-XVc(P$%!49yhyQwN=eS$vM!@3
z#bFAB$KZDL9+3NwqL8~6_6Q>Js1eHPX9^rFbmB7pWE`}?QFe#i-3td0@Kkyj?9Qi6
zW}D!Q<VFi(gfb<?!&X%X6Fi|LvI&(7G}ux%O91}K3b5fnW;QlUYA;pryKl6L*9k!p
z{Xbee6R@81wf}!B(KacBF%=O}j4j(BNm5y(T}X?un=C0pvXr8fHCvLsDA{)*jWS~!
zOBhQVLZe8s^}Oz%Gv}G>%z2*cT+jc1uFG{As^53{d_MPmzwh_^eG}CzM^;n5xDd(e
z>RaaFzaeIrtF1irIr2mqMb=b)w&rtPnwW|Lq9(p@M|_YjZA(ePF{Z^WQIVrxp6R~%
z=wN_Odg(V_Tu&J=@qT+&%ZEe7FI;-S{S*P2Fn?%jvI`196-6FK;*@&iv2@3#O`GPG
z2s?_em+*Sk6>5-wuwhfEnUrwYE?~~vh&jVI|GUcaYS4YMdpf0V_s;-8x?GOub)p<U
zN6FY>$~|jTwvyBDc1vxD(ZnJEoT3S%w6(RdWY}VDVrnW_I!}Bn?Lv$sSErpphzk5P
zOtb^GU~bZxh1BUwtIcuXzzgi(>-$D_o8TBpiQ!94DQs3c43QKozEn~ImCp}O;^jZv
z%<EUPrA&j_{iLqG^aZHr60JEP#w(Ja^Za++_(A%g9IR3Sakhy&()<t4Ehd~HWraht
z7`?<+9)z5gFp2{F1LY*#69YF+r)N|_GaDOIvJ5!Ji>M>UM)s2fS&qOn`+XBPZhRWz
zkz|(~PRrQRb+<4T9Y1g9(xRLb!e&oT0?WbgL0sPy6(N|cS(->d+>LvMbU+*{-gSp-
z4`SiC{#I<2^#dt`c>5x7adba}@rLmaGqrGg>Bj~szd5vz%I17qJ&Q4gz9#&F`>%18
zrZFWEL=o!J^KX~%tL$4ku?Ru>1T`C3&1>?-(pN#Z37fDyvi|`2IKAT3Wj~RV%7q9A
zurljJNO^MsJwdH-YxwylwhHs&1=2REUv0Wm3M0?V0PV5|$2Alwpy}f;<<H(O=eBJ#
zf9U7TzR?%(Jt)J~wO$`%KBIJ4y{pO9rk8sUq=gSP7%#Bm$MSHC&BtthKroQE;yH5U
zg=^OgNOo16YZs@r>9r;SH;F47R1AHJIVeE2X#!!%U;?VPwXCt~WM323#jq^@U>(}w
zwq#q^aW9c_3h7BW4FcXdef#vX?yB!y5jH9-IyP4P%@GkD<;&WNIQ2ldaUC;L9$EIV
zGxgF)$y@a5WvmF?DgK%8t|liYChlq1oej6Gpfz6LaEO8`OWl-naBvUId_J60Tq<2r
z_jqfV^KF(>f9s@wo4p-WT@i>&fExLU#{i%HL!68+EW*&<g!aeVMLAjOqD}-4&J2b2
z9;H=1x%nnwWop^xgJ;7~q;{}N>=d|tXFvJq1j{knx2Zzt1k`QzCiz!E96-77Z_Kd~
zyL{II-ew1mH0KP_=|F^)Y7na&ds>^fnl$5?y9BLDxANpMhrE4esEF(mxj=12%M8U%
z@|kC{W}}mNOr><+iLYvauF`oWFeu^RheB_k_>ElZ?qiodA`bub#E$Htfa3`5#`oZw
ziV`0m{~l%0pC6a9HYme6BBA@zI)5e&>=+K~C!62UaNC^jD<5g2S$!fRaO%|WHx3y%
zupd+eaw1>Yti3-~j~HI>;52St6_~?*@81}Qy16aQ%^!2ZNs%f-wOKiia`$OPR#~~r
z1T9A5gY(DkNo!Q^G~r&owu&6Jz<j?Qca|sVXTj0~7i_n&p<Ofh1|q23wQHBRI(ow9
zmiswS2+u>h!h08oZ;|fc=QV7AkLvfiv#oG=E0c^T%I4dNuNFzTu>Z#_f>`Mf{e2bz
z>p72VjwQ;`vG_!xgnG+&e9#IsM!<pt#B?8MU*c(-Hf^eP9!mp)jswkHTD=)Fo({?X
zMD@BAF9eFk#i*fAojwg=uWf4K|K2bvu^KJ6Ty=SNgb|WIs$SvAG{(yS6BS7{>CJOg
z1K6ST%i-{xv1!Z!zy9K4Ltiro+!PL46g^)tOwF7lcYwXaTiW>Rt=n@fqTZu-sUcwz
z67E=tO~TlHIC~3E=UMLtc3S1hR!*GgK%pI`KIl#q#VGR|w#EQ<5tWB)U5DgzoIRN<
z8r1BBQowE~faYgMil`PaI;#ox;BeRy3p)vJGW*fINZQ}z4vHcIZqfiL^DVR29{!!)
zEJ@bxQxbq%j)E*af0#uT94D2PFm(4XRcC8d4q*t8A!kHkztRx?KxuS+1vD-itRV}S
zN^sy%@LLBcO+wYUvawrT=qNW%k)kD2h!3Bxsr;qW^uYa}ohF{LTM^Nisu8fbovcjY
z+N~@zf|Z$Y@or5(yUpl=)V0l^XUC8unL&#O91!XQjhh{U<PHFU=cHc9HT>yt48owL
zMByYYzKWZXyRR)F==^xUgfmfK%EK2`_dJlpi{wgdSA=&$dS8d(43lSpL0+R{Q&-<W
zA=g?;AQppmp*$enF)%jP!=Y9=M<0F1367~q6oz7BBqSpue)YW)1eO6WR>Z|co<99K
z@|6~+h|A6^is=^3dRx>TcBn-z4PQEL>;Sj6#XYieF~)?`8$o}qB&66P295=A&&R%5
zr;qPPuPWz<RMa3+uSq%mk?r)rQu?e7K~Qjh*S)UVAhUQGNy>8w%}?wLQjT9{Pj_I0
zzg+yPw*GRBf}~F#<NWHp|5eTBe#6l|*{)kY`c9ZQu>h-dJ2DEj#VJj846pumtQizJ
z@HDegPb%o&(l5bVv(>F0JZey}x4)XlbBft(-T&s(!;xEj)NI27#)aN3JHIToah``o
zm2{{$TPJEaGc!};x1jpbRA?Er0H|Sq6Gblq@Wp`46_QvUqZ<XMAQJJ80FX+jo*C^S
zrco0L^AvZ+#k9ea;Y|;(`0d{cfbupdgeYh8K!=hwRz=pk&(*9mX`JL0=ejoC#<S0-
z*Ba6`Wh+Xq#`a(R%hkMg>v?;2<dxf>r){?Yp%XnRxu5tN%KMerL5?cEz|xep9XH}3
zsH4cIAy1sUd|4a*MMBG=WHqAyS*rJK1PkT@ZVh5BPGER*@FN>3DK_%QgJX^-7}|a+
zyfSCViay?+*`v-}%DQpw{U7J=Y%KKA7ADHd`10q0$6E&J)#X%E+dob7NacbBr(^qQ
zOx;{@c$umwHA*A3-_uj7LQ6e|9k)itDMg*LDk>_5&z3B~wXt!NaSz)yZn|vK$FXfX
zJ?&}z>2AEyq-y63r5UC}0*kO+G?m@nhb@J@LB4%hQ&JesLH#<<Xub5&T#aG2TLL~W
z=+^8}zHwcvxQbbgp0HCMWBx~1r#bRNx=>P%Ji);8X=HDTQWvusQ*>wME9>v(<_&(?
zDX)jV`<CL=RdY!tU6SoIg{$rDo!BT#7H9FgF$JuL?x7Xi?`gD~-15L8Q|k8)n$`((
zIcZ9)vTk5%4g(|Ls%fooid12EAvTz(o3Xp~vZiv^Un5u-!wul6{O8DOGH&0=lRstk
zWjz@h{m8A-#Es@d{ONB<d?xc<4A4}Fp}lwn-7;yxH@X~1NI$7X1G4TCyM-uvTcG|?
z#Fv-;h(DS4e~0I$X>GXzX(cEM&}#>XCnJ6P4|bZ|r`4ZOK~;B8g+Qy&5}K85$J2c4
z^s|T5pUWxj&=Kp=p;?5C<CmwNsstl}?6j0bToPsqWbwVttYahf{hFCvzhoU^oqY4=
zh~LXqEQPt%O?D<zh8q77O*m-Xh;M4x)-xR9+!MA<X>25ayZdgQNByxd#%M(^7excI
zCjiXMYF^kx?N}Yp>BcJ)l=W*b+q5t1xOGykXNmJa3Ca?EoB~aZ)(|6goKZ4}mfVKT
z4`Nb^x<9@XYg;g5>(!+23Hdc8*`IaOCVkV`Tdnueju7FS=ce#;?8R)z11JafmxVm@
zcXIl9(0)JDfL0^CoZQ`~8@+jac8)5bSD25Pmm!vN#KKf~@aqTV1+;Q2iKT69m{rr#
zgRhci7GDdK4CIg1B(1yxRkxLk64828T->_TyVrMUXEii){)B4x>2B|S&y%$mTT$88
z?wb`?PQ83}1_ci64@?qvTbyWKv}%6raQmOeO<%L)k=a(C&*x)!NH%Sf-uAF=R9(7g
z7QCNXIenM3EF0sSV;h<uyYQ6Q0KHWsmk13FWrtbnO$#31ZFa4D>A8dUKP(f;s(okz
z=ZNwXXTjT-`Sod;T;%%H6lo-Ls@!U5Y_#=QPJYir>r#_W7tVc9czy*O(A|x5$?=dW
z&@Qw^-bY|Vd!?q(OBaFzD@`YAze`DXk7={VFF06uGTCihZ+X6}!e&iRhou2Lxr7yZ
z0jobw!v179LB+X7n6{W%TJCM;*UmL5piXc6B~SroS%m7(iwmRtfWfiBdP2g!2gG7j
zPfeTDpVxNI&f^xtjB8jztshm~vLBE3ljJebst<({GZJe4vW05vH4Z2DYliwB{vF6f
zU+@b#JlP(pJsr5bZGJ7s3|`FbN5VlP$)H)k7+Ap;(*gfW%d=1x{Pxd{Hl)mpibVvd
z*m#IzqJu+HnaPh|cmG!mjC3}Tg}N{`HT8twSF8xMkY-$xb0vhBbzzz$eD-hK{5&G!
zFmz<GkN_`uAHKG~T+2}JE%nm4v_k0?p}i54NGdgYmD{%ZsglvP71o0;kd@)>vrHHf
z5P}!d?h<E9D8Uucl5JkE`MC9@R#Tg>DCiJl0c`}P=H%#;-&1>Ffr$YZ@U;qSGTznO
zv!4b}#!idnRy4`v--xz{f*Ns>EhTh<Z;B`yr%bQS%n1;x22Rj0KcpH*pcF9c?+WfS
zf@(LPlhn(?lSKAC&h}!RAvzC9C$X{QV2Dpo_4v;c&fz9tXM*udvBP2tswi?2KlTlD
z#^Z#Dh#{o3<goYaKxo5T&+=-yl&hzQZrPxPdCMfps1cWoauFaO*l*7n-v&C=mKsPP
z@(vHV9e7DRUU*zNBuTi5M8h)`4TlmA+$Czp_sA-wO~`guVY05S4Jc5QfLMpKq~!uL
z?YQe)P&}C1{u4huMr%z#9)2VTy0Vnm#xJHkIy0(W*6DV@WCB$IJRtK>Q;<?EqP|@1
zqZW=IDv&!V*>b@!0ggpmDE|O*!;V`-e+&uBkM||%#9egzb9SbBz6Brr;jOGXY;92v
z^vzC4rJ1x1RtHwI5ikeoF1H=kLuQd2K72Us4E+LHJ_eY?-U^yNJ>gax7)sXdch#DN
z@Kky-eP8PH1m_i0^tv{Ftn|joq`+KsB_g7u><h$r<f8LtybHrA{RZBos|e>1HMgwA
zU4@Ivnt$>XuO@=1%ny>_4O2=oJ`IHoO%O1z&+xbK54wOU;@&qf5dML{-Nc-UmGKV*
z&M)5g^x!?N&Yx5M8?GAohUWbLCf=4>-^M=K!V~mK#M&^_lx7t4WO4k9Em9B}AEgp*
z0|oPjuH)GwXeY%)ZADn3^lxE4D<b_AlT+BTI8}Z}C8j8VO5r5P7#PHf?-G$3ncRUi
zZK;VJM^*e*C$*UmvxWdkSM5BQu!UY_n&$y^@w_8zk!OgMPKRBZ4H7tvI%z^8{-8oD
zXZ=MkU0PcTlcf0{oHk6GI58R~^jHM1qUNGH=txsE-_wiDY+qW@H!io0lXF31(?9q2
zl85#ZgWm2@xx)Q_pN(fZB%v_;SWb_tF>^Qd5ZFxzr@eyaJ@nrnZjrIy$e=1cZ1jV(
ziN$Aw0}=>FuC+R3S$;pfUiihQwpTQKN4=;?NISNm^DckWfM16?wZ77tm!vf)Bf9R*
zPB2x}X5{eiQIBg9tRSmY?+n!GHiR|p7vYw+e(f3yud|23td3ibJXX&7GQ{pJJ8pv4
z*3XuqULV~C?dMve4fwmk56+&8U09K6qH%C`7+YeS-Gy4I-LZ{2dA!B7KUSU^+HjTd
zG@CEfb`LVF>OME}-SkSn^XimM{B`pW<JbEdH9FxCp6vEc|JAhMux^KP(<HxK;+)EC
zLZj!2>b;K!#?GjGH%t%mht0=MtE_t8JijcCk2mK=>i53+pnmJv1#<5J8Ov15;s0%F
zVfTc&W|xQQ;I?$>pvUEmuDAR3w$L3vv9(T5x!&O#c*8yZYW%SjQ>HyvZoAf9b^qA;
zqZ{^p=(_!1%CnsxZcByO!!M#T-sG6!vaGX9ZBMzG8m(K-SH7WFy-S@k&j)MNxujM;
z^ov#J0~%pZmHkutgnj0RR$INx`VjTiX)AExe#J3REVue4j#$y_UyG-@BXK!2JUxQF
z_qVv>{05<e004NWWdZeJI4UmOTYAM?=!1O&rDxs&sSNykL@CR;+dEPB$@R=}Sx2>%
z_@K+jaHFbO(YkY|bf42!D|&XYIY=&UXcPr&6zziOh)Dd$ZCpoSM<+UHQ+Go$m%ETn
zK`qg*9PAbZ{q`GxsvDDJ@`h*}4^7UO$t_aHQ6xnIw8&gR%@fn6&3$KCRb<(xa{AlX
zliyi+bW)F6u*pl_x{iHvRaOP|z%b=v-@q&uV-c@>@o5I><-rNmJ^c7rGrQ?NL&-zP
zCCW+WZ3hgfBg_U4rui^!B%ICb`Ns6Cfl|uiU8VbE;f1<C^T?>M#0H3PO~}ox_|FNj
zHtx@MKMhbDIihz_*T##~6KB`IJtOny8i(c1sYm5m6?-L*$;ypEG%n_0<j|3vxvsE*
zeqtboE=@(T;FRMX7O}Lw#p<Iqbe_w%-Ds9f*mC@M=#eRZar>xw{Ju+<2J0VOGQ#R^
zp?byW;a*O6u=i=&)pTvY3s+8R7Pg3=(Wh<ylCa37)sJec7RiC*5o=KSgHqaRE#wr=
zD_Ma8mp9X2TA&c3MR<f=Rc5U=>3{98B%f52*ZaoB6!)H#b;<Ri-gy7LySA7$v9|6U
z>8FHGzLWc9!M)jCb1tw+EN!z3bV%nbAutK)A-K}g0@}y`x+|tQ3IK!2ATV4+J{kvN
zBQk9gctqpga}HUXG;NxG+dOqi>fo#uMP>IIKFc&)7nCt>hOwL=>h4AL)6$Ac;R1@E
zHov9vVc=J+K~0d9aQvdrd@Sn;($yEHnIgO^fQ>deC4E)HW>9T@2rg>3p@~jNcjmcO
z{BpS6u;X0@Oy|t9tOe~_&`mO(8#BoV`L!~L57CWStI0AxIlDcbb7Hrq0=-^h5lCnx
z85(>nJ)9@R_gfNgvPkF4BmPGoTgI?=)hXAn)!NjgQE&rRTgzC0x`h{(E?7@yENtie
zTn%+~QmWOHH{U!crJ%eSoWahJQjzj}M{Wl}-ww)wIFRHU?WP|u!Ri?O0|{18&skeT
zin|vU79!e+hWJ_4)rHLL`U0@;L-61Ww*94R9P`Vl#axDcwx&u{`L{;ve>URPE4fch
z#`fI*%c(iV%mIwazVuwH^KmaZSM|Phv0n=;<m%I@c1@EAjc(0#+jNqHw-I)uE=z}t
z+hEb#nXl3^_sl)NGP&r@Q9@cYb8DMkU-J6dWRLw1%@zAgEeq{J-sb2^@%vk>_U!?0
zU%HiDcAH<y4sf}CvDS+gnO$#>m?Tw`<%adX^Xw}(we`ir=|OG(Va?Dy%o)<KX=l}O
zFTXfmWuJ9S-S&vN)ucJozw?NVlyGxJ+)Tq#^Zhu-Gdiy6rg3k5=~%uNRcO?+`sWrp
z=q{YrWhB;!PaMm*#iZ7R4*L=P)apJRzQjZ}qmd$F+W%R#@UIVF|K`@_NEc~}omts}
zn#Xc<=C7N*p590Z*IpY9Ccx4p9V~L>uA_HR`hlw+%DC{pb%Sl@J61Kd#Ty<p4mY-?
zcF7;2UVP0Sa|90Y^BW#+IDbyaOB=noN0Cp;^ZJ;ctox>oX&)vO@M|%U9Y22c@`p~R
zB6c)~|G2u{$gYp_80!(%Y0T=l6**-WUcaB$*!1kD!UG>WB;6~wYU8m#bM<oT1TN%R
z3qProRf&<#dPtZe78*6`_w)KY?mpq$d(CgUG^c&d*N@({aPtF6BY#^i;#c|qe~;>4
zs+Fn;g^d6v%z4@@L9oEi>+f*{Xl)46D`G@?TPauwiyL>^5PDz&wZYaE=TdR7f@G}Q
zreK=@2L!>!2z^~I`BzPq&NJwXkpD&224oK0mr$Z>Cfqoz`H)^Wg(7@xZq-yX2On#y
zIbVtl(agwz%gviR!tcsISQ7H`%M3~;vA8GV@&VYX?3#SWGRN{?4Y}gz1H>I`w7L=2
zwLeo?$+i~O9)}K%fk-M4judyq4?V<E3?`=xh%~kdYYekU`~wKRJAMFDJkPhi#x3PB
zyaEPyX`^!;7Uj~YH!8P_(1Kh}&za@bBW_fgXlkE7*T!30d=)t5#AuO%bH@)LsM$mN
zd|pfoQtEi5Ojs%*0G@8<F#5feK|~9GEHsbJdeKn+6C6iWReLY^S0#P*|MG{}+2dD_
zV$bT2AH~aG@O1&F=m7cA^lCb(QS0<tMo~1wm(lliyomrB8p#kK?^J^nOH=LuHx&5s
z@U|IYWCR)|EWeed2wDd!1{7>oX&qu#v$92%AaVamadAu3wq}bTADEj2x+M;N#XpSM
z<EleTUrgKgwC&o}U08(3h+g?G_6z_F@P_L+)crOCY!L6Ymmh7U_(1}_afsK0zkp)E
zGh1CMEI#0&a(az%4Ux`zWa!wUwxQvoM^}H(Ah;1M1kQaQGY9uxfHP_e)t#bH7CU%*
zZ+IDkJ@>aTp9{-BEfC*VsJekUT5_QT{uBybj2AoO{s2c|FcqHnhNg7uiTC;Col#}6
zrU!m1Cs8sJ=^vzZ0vfGPVbVxfFyv*0-5UQ{5T_AZOLt|s2^U4*gE#j+C1=ndIgz~^
zh08Q0+*hP?v4&;bgnH=v?YpDvz*fLGOQy(>ZD}a>{rmSNH<D!M1mEl6>WW0n>yT9N
ztU@A--;vN>!G8opTM-fvC&ncK;i=dCX#K;M>}zWqK6Cl>58tnQTi6Y01zN-u8fMHe
zz`v+AmThXF3CiOGc^Yo9Zj|xdb>N%BhYrzi$tv`+@0hi%d7#8FTq=+YkGh-OK$i%5
z9xp$Yy!82Vqu}n@vEW9al^uW_6<cx2#feyoJmzsMF&=gO9o{%C@Hd5YDf5o;?G#gJ
zmRBs~^_NAXn-LwEU6=T3$UX><3<cP^a+~D`res7@vx`X#!kIMJsbE~t#4zN|EqxO*
zuB)02qt@U6Mo_y`O9Loqi#4n;`B>|rFCQ|mt|6I4W+u%I@MU#nyZ^;MrU#2kn}s7>
z3KDOXi6S}_$*00|zHjf^!<}|Z{?r8Lp+g5?-5B?yVKzq^?KR;-FrFvMb*HPP@F_z=
zLK^r5^j~G5PEndoyY45%ev%QEFp}y!folsx@dx67UH!f=A2x!F#-rlCk;<BonN(k{
z`mgIbbm-N|{UU^O41}O4{5%PmL+~f0TC_5K3gX7l{I#|&+GPOq53?<$S8!-@?g9EY
z_-(gk#kalH14aPG>Hust*Zo@=H3)A1ap*0!xR_yh9-X>bNW0)R4Om3Yff+OUSxsla
zMO*T7@y+WmtxH5f38g}=0HGNoc_9_M6E}#AGR|)KiDz@(d~atK^73IZw#70(QuG}n
zrGet4jS9LPm51{zn#}FsCtU;pyGXNG#h<0oCe$+Bjuqz{85pRBS#s)F;jNYpp0flQ
zyh;@IL$BbP(8|&^%ma&-KT0zx0|Xl_Cs8$9JTWKt&K(aCR4|_^M&bjf45lbm=kK+g
zQ@53;W@}D6xpv-@>I|a`)d&mldf~=n$imi?GK9iA3_A-MN`d3Lj5Egd;OFzYC$#4F
z%qloA_b6I|C|X?F@G4}S!~xWR`C+h@nW5X75o+xaZuJKn6;n{1Hutu*fJTi>$xij5
z80CV}$3PMqLMO>_mV_AKG~)$NAqy@x*lUu?$rDX>tSjR?fLmme1>xIGYi_^2!?emT
zWt?Q0*uTxXD+x-J<Nv)(j$RH^-jDfYEvMdB#OiP|g47)+FhDp*15yXR#s>pXd>dln
zTMUzbepgXhiIcziKRx!+(!$_XuZOT>aq`uJmk&>WCwA9}v0V2eh<W7Cl-C=J)-2oo
z3{d5*Ha{)v=Vc`}C`Q4ae*}`5WA0z?=qnH#Z5kgKY)$NQnPXA>&t%N$xp+gD`OtMf
z)Ouc8D)T?yb?Vj)7iUdIZPbB4pHO;rbI(SwRAqXL@)$4;%Q9V-l{A3cpLws2wcyGr
zg-ko{%Ta>Sj4qXcphXHAA`OB9x)$eI<QVkPfBN)3s2B1AP9zNll&~Kz(A<rZ+3jZb
z#f#F076&@Gxp0wWO3#EZ^oo5kyah%UQ!acL5)$$@6$RcWn^DmKQOaW71@BG`AF)d;
zGSPIMBW<BeoWuDXa9_yHs2@bR0%6skLzu?smCDo13+W-|M3`$j2HI%}50L=0h^z|`
zO$OggI0I`~<a5AYPfv_)Zt25&a$cWiFOpAKRu=%EJBU36q#ua{2ph$!8?G%BAR!?Q
zFG$$1K}Y4UAo&#Y;bgE97CGHuU~Rqe?$xVTJHGT2%Tt^;P{(cZ|DCri+%WkbN~Sty
zwdC{R2kaU0H}eab4Qvx~U&(;r0*||ZyoKp3U4%SGWtKwo2pQ5sCLYQ>PBHO-Ub_$?
zy`Xne2LTK6Xb!CoD=9(_P3KJ*Zrd|)cp6K7C>G)}S(43lo|&OXQ14U*ICU~K>KH+z
zhcF`AI{0+CqmcuwEM=2L!M2py)}pc&ve<-&P~racSi6M=q7hmVs1~5q7L=YRjgJz;
zzZ$YR24b(I9xfUWY~lz9+DdbD8As9(elxZTAzTzeeWYT5_f>oe<5=xTH)G(}GJ5eM
z9bqQR(*D@<D^IRJk!D73o4u1qYMEipVNZIx<2eX{nk^WMizPnpc-`T!y2QW^;nWzx
zHI6*weQA@bV~zX5xX=sjAYL4&(k7$NRH@;+bm?;EvkXsz$IYOLZ;#(L+jc(1Eo6_0
zq0wr>l*ke@JHcXmUW0l;3!yRS05(eDG<BWdAQg+2PSA_E)$|UbIM?BtR09&}2dMuZ
z2?E|1gJ+S7<g&z<@JH-dh9|NO$dPwU`08dcs9i^KG5WB88&tCmZrLUkB<e@3ki_FH
zh|zeQ{7$nL8z77!MywmPBew#lUr1k<b7fi;e2e6-w&4B2^{?$5{N4BopQ~2wOHZ#$
zf`br>Cz=|#V434Q>>=hwfQ&!7A21s(xFUAR!t=zCTyb=Cw51~v=w#Q>$||)g_~Ne{
z+J8BluNR)?H1v02;NH|(Vs~W9tbHRz@49wYw=tL$2vNgp!Jf7vYzz91(Jj!R<JT}(
zLKvW8e<FE{gaXFen96j3DSck_W{!ocH7s@)?YH=Rh~mfdt9~pFxVnvs!pZW~1<R26
zHt#xh>9PbA%h<$(L?GVy&XmAFO(iq7WLj`Yolfan)ohW>?(gUhZVpdIOJ9F&E<P~J
zSPeAHx{Ud_uk^?p9*Z}DIWPDDyR+Gpswuej*puBIF&{`7BZ^eX_dy<{=YelM<H%Xy
zyBWuGuWDh`Z;P}WUbkr7vZW@{t;{>5drCm7hJ-K~(JCD?;;(2qq<~PF=I|WeGu24i
zolrIk$$!K-`pf64G0Hj7zB5@_<*U!c&9COxTFp9xIBiuE=Ge%iU(!#1tafdwSEzg$
zoa$}ve0Hh#;h#HfciTH9wXydAhkJ*|cWdWh|7v7*;-JINnmRhgbiEnpwKJ-pVSoFW
zuI;?-X9x9Io|3vTsP3INW4jib{86>}){D@los)*S86}uMuh3LiTR*6kUTuv{SAX<L
zzcX!;R_#TPLrts0Ob_PkrQXs>98_EHLip3_qmO>EnsIhugZ|?;P$-8NPha*bIA(Nu
zRZgp_pStVqy1A@6?8~h5o6l`s8l>Hs^fI{T%#))$+cvDFzA(Mx&F2j+2i(Ybx!Az}
zdhM8%HP^;lN8EXFYgBm%yvEd98IS&;>Q;L^`)Welyp`tKe5!k@(W=X}=AUi)d}fp6
zVOqz1^pD>Ert8LUl$F1Xb4kB*eZ2L#%(hSg%HC-2bJwl<XcF&OE8EZT)<m~;abp|1
zS{jj*9s9j(*LN#}Pp)t@k8rhIGTu5mr*PqupWeUnd_C>d4^=(8$1d8t_wMAbj^_2W
zA}_RFm-o6lY-m!)jlUSw>O0$f($V|ZCwDcB$vzike5tVGhtD>~$Q&Ps^s>8Ytrg+x
z8EhAIU{KwZ4MtRDr;2C(urSc8ZA0BrYf8U$X%KYWr&(S_AIAY&p>^Ccw9JYkLwlLF
yj*htS<n@h^b$ONkXDj)krIwzYcUoq(KWc`(%3c<BKJB5x|D5^{vEOg!8}VPH-b;D_

diff --git a/dev/_images/sphx_glr_plot_benchmark_preprocessing_thumb.png b/dev/_images/sphx_glr_plot_benchmark_preprocessing_thumb.png
index 6bc1620216c168b3c54d4e626673c372df79447d..69b32b2d1a62c063f7ff69ba5dee7b0221f893db 100644
GIT binary patch
literal 29244
zcma&O2RzsB+deFnq(OruDKavmkcOFzjI4x|k*uW5?2%AL!z{A0k`R)Wl_Hx|LiS3M
zEhFN8T>b9*{y)$2dY<R?zhC$Fm+~3!_w~Nc^E{5@JkHBsO+|hS4HFFo1;rMHGcp<!
z6l;R;A0sst{>ApvQ)m3|S_PR?noiMUU5-vW&o50*O^lo7w9iV@#H^$C`RGck_avr!
zo6LH?{rjmEcgzNJO5CPQpr#QCOIUcibEM?%b_>dp60;@e)#|9lZRZY3Z|`+`sU+~K
zJ*LpiQE)z1a9({QYY@9aNRn$Z{}=`NK|WM@e+aw6C->luGWhe2fS}hI{5dbnNv9CP
zK2qAY#+K<3UTEKByy^e-1=Z`=@WQTLky7O2me_XqkyjfSQwHPD@xcH8PyauAGq=#j
z3QLhI**Yw>dGFu7i#TS*!Vu^?+L|e3QoGaE)|REVbX;3SW$VoMh68+j>90?7@5sB+
zRXaUYw{O8ACnu+-x?0NbRndbd<%Yd~=X<!s#F%s1>z5|VnkoZ#DH-?lc&>_jQ*G%F
z6ev9y{CDUG<L0E4l;NeKd;b2Hzt=}5B_)NO*({eBeDB`oPoF*=X53sm@L0gW^lSPB
zyiPLcuiNre)$-zS9If%i<cxauAcauQY~z}cyRXIy3XbPp@3_-$`N1?NI6VCPcmDmR
zIg!^p^0w{SbMaez*hbFK5iicgq$GAumFP2>`Xx?(MpAYkHl*0af62+P!!xMfR4D40
z73Yy7+is<&r{A3$`su)>8f)BL?ELy#>jTq<C*rezPmRmEw!An$`=i<0EY|rBi@3{S
z&lNWxI$T_iNgczhoSc0w%#o3iVynwD<XvWQ?vMEO-b}`=E^kO{QM`1C`C^`Bxw)`J
zko(Z!prK$SOLg7~x1eB%V~=}&Md|*I@M`^WX$J>~(sWNz)^+%#wvLX(&m+^~u`x0C
z8%*D~x9<*DJZ~7q6Hb$%6{w$CWhrtlQEtnlLl>VFcN=9tZLz4Sua`+{`Q9Nh=+P!k
z&AfN-kw|5H$S$VDa>KXAf_=TcK@%sOGYj2C^M#@sYW+uk{P2@Y<j%UD)<SbjH-l41
zNT_EfU5i(mT9|3e?%lg<R~k%(PMkRL<G0Ie-9r>2QCp%K?!?6G#kKvgf8$n`qnlx#
zt1Bodn3a=rI<pm9Cv2>(eMnLd>q+Ik23P6reY&)2wQxcVpY~jnXV#^}cC)jBUWV2H
zzFIN4zjBv>ras=MmS$HrYHVUc|3_jdW}kD_O4Hx(gM(_B`r>ys@4lUu#;f$0f2iSD
zk8wxd_4To?OG`1au@Ce!1*XLtt_VgRX1c$=Q9ZHQug3UYWhF<?6u!!2>A`~sxH@Id
z9h{-uJxf@g3$M-9OaFE@EDrwqm0oP+JfVl(Y?@Q}_QaE2pZnh5P1Q`@en9Tt+w$@?
zIqmmiVq$E!9v2l&)Jm(VsVTR}?f>;Fdg3?JeX6vUfO11MkH?P6`I7Svu5-UG*MxAm
z&9$4YTepsG$Bxq$7Cg6XV>?$IujA4fHy=N7g8ul1%~Wemb58W+?w=5^F4EfR5OZr)
zbVHBF()E)!e^%hjokuhB%|9h=ym8|O-Vm>mIvr!?y!2(nelai7kp(xz(Oo<vovd-h
z?t8u4692D1oIY<6tyWf<>>oWnzG|g~W9PcXnQ3b7+#_Py+oEky+10go*RIFX59htM
znN-vXl<|FUjJeo5b*=TKzl8fAzwZrEfnPH&2HxLujE2=GONX!Dn^uA@=H$)ohjd@l
z{r&TMM_*r`G&QTGNR&>2b-a07R{W3loRo;emv8_0lpKgV>#vU#O2Ct06BWI9smw#~
z_0`XE%8`Py_M>0V3R`?RW7&~+wteNr`81jLcecnrWD&2pXjQ`T#$k*HdxoZ>0AbUd
zrY+E%cl}~>sk>|T%~35@A37@UQ}z?xdc}X|IucalBog#XT#TmrE8iJqQ?vTCm3fw#
zcfH9q@5sxDIBt_*-u^22xOK0T*I1@rk(T|~xAV$RgcXFXx-XH>xK!$Pftt0VNph9%
zTfUXRhX;FkvE1w`F()~;G9TaXGW&z|+v}?b-rOAJocq;&z=y8CI`{w^JG+c>^l|mq
zRz3Q!Em{<Rb>s^e@SS_6ylt<j!_Fv?>)VkVcIp*5(35o{f4a_(pEvsU=4RTDFR7vA
z>VCAOJwER6D}qkiudB#0u)D-HP~`eIKYTBDrvHNn3<u;N>_mE^zy9s@wj9%j?b6gX
zeec#!EzdLsI*fhupBw8yl3c*rS0KAqMp>0|`_LJUd`eC*Yl=1c`6V^sLXK(wNJ<>T
zkt0X&Dh&;diijguWD@1>S3EuCUBR1K%!W+oR5df!mVJfo@L@G1sa=0O97jIMlI8L7
z@$nm|dKl=vftJDLl1S9q<=M}wwKn4Oop$}pi!=DdubBn{x_Oq|PmWpfQ*C8F$i~Lz
zLnobnF`vI@PBr>CE3T4*{GP1pv$Ij0PeiWskX7AG<?Zx6(ySu*fV@wo5%-+iw<5<(
z^OhIk=B+PdB80DokezefW%hYiyJi2tLrJa1rr|hG{ferpVbSl2@(%-;j#^Nws;X|=
zzMT!L!1YWylI_p$QLZ~%_wxL^jspiOZ?E4Z6UcB#1`AiQFf|}+Veta%yf`x)xMnSt
z-;paH{65^@6KFH=!JphCLMzba_fP+tP_DpVzkX3p{N82Y#(L8JhuROboeT_|y15n{
z2?+_fJF;8J20AgU5`8>g%n`{x;Y!tmgqx#Zjo#i`(~o$;%4ntQu)55TACh~>a_Gs?
zYn-v3E6z5fUo$9|6qS^A>^*5uC+hG^jb-#>ythuVQ}%J^=_G`;|8#zHv9n#a=c)&G
z_`rwzJCq*rsq5PfR&Q&LKfM7(i^F5}uVZue6?t;&WLdYeh#kaJUzqIcAI&UdklyL;
z9(eygJ=t$UruB3suJa6An1tzgwO?w^+5Kue@^AN$cqY4N_3wlyE>_=l>}Y)JsBD^6
zM#VW*@$)}iSN4aGtTW2ishDY!6u3jXkDp(^_#k=OFSIlH8)HPd_!t7)a?BnU*bW8w
z`T5aZ`EYL=xm;=LY_ld7^)#(R+1EQnY<_;>ZcbL()%?mt>9R0WB^Fl}k3&XF>rsKt
zz@3kyzm00cxcfgPE0KrH5F_fyAeX2fecVPGDbnxI#XP@{AJvW+zNJu4)!-l%d;i?I
z6czs+Tq=GM5scZU4NT4H7leX?gISe1L!TRzmHrDT*SYkzQum_g7xP~h*pGyqQBc@M
z0tg9l+hcyc?c`4t6_x%U&57&t%J3O|zkcyatS;M;*g9f6c&0hiKoYAjxw4Q*QSq}S
ztupsotBkq%bMv0klC}byL_b6(mUCyu#e9Yf7cTT8cBE52`_Ff~s$ME~Qb)3rCmAm3
z*|UJZOY@tK9XmF)vNRD`_gEk>O*=CH5F~)S*2mY^pH^Z)O4$6Pl(DI4Kvve_Z98|e
z|GSdkKhN9z_{eHA^Zo3$9Xk$u%e}@`y1L@JZSUSgr7M4~kxUpI5pi&3sb@7{ysIeC
z&yU(>aoS|)c-6h#2T1zDRwb8w{N~RvY<d8zK=nkqjjTR8S%zMdzkkz9E>C(FSohr~
z3l<^nnuixXl=ySz_4N*|=o5Bw$YrXUX<BFR?G>GSFx<fv=f+0TalNUXSC9MO->vUj
zTF$5IWJ_Nvw3Q|QAqSSewc+64@JA&0-?~LH^`2JJk5mx%r8)n$HXWNkvse2jCImeG
zjBx#1XXN4|<{$TCoqOD7&X$hJ%gFeV_~TG|<QKS0ARxcnMM*PVN1a>^<7O(d`$<$>
z&eaVRk0Zf|FyjJlVkdtB!c<NTR8{^SZIxA13nClSFCbt$^6jBX*=lp)0CI2k$Z9fj
zax{s}2j%WFaiH9At}G1DA}9}KUw%(T)}Ev*lAcJi@Ah1E$JGg$HSUy<kT9xxu($t9
z>bZnd-c$)^qeS}OdadpM7=JoJD?_(`qHL9aQh&I_6R>qVVn`z-oo@B9)b{P$Wps2R
zNTMhEk!+hyyZCpKUCt0FyZpP=fRqqsaTm?bV&`+kQy=yi4ORyu90Aohk%PkQQn0N3
zLyrv@M4}EEFprFkB%HpxwZFrvj2;QSKP|I#yN8E|QBSFR|6olhAdRfsWcda*K0amT
zn3LzlmVV{n!#oy;c9GQ^5<?n#<TRGsD&ydgNAj#ru0^;XQpE;Z7R~Lgn*@sYlceQC
z=d0gCqJ8_09kSNeSwDKp%8nzX7RHMvWbpShDk=<DuU<{C8*Vg0>SH^3QrEJxKwbFS
zSLMz(H<g$r+;lWE_4R!2+zEL8{5fUS;?wZRBSG%~+v%8?YJE2Dc&=9@vUbDPBs^_w
zGur!dr$af<Qq$57qox+Td1E{G>%x9V3PedB!O(ZM>=AUCHGi#}Avhk~nv~yesrf?F
zA9X_mIY#at<0(Z&8U+OfW-+HAsx3^DC{R0?nd?#ItnKaj?0+R)et(CW6=*;bk(!j8
zZ1eZeO%q8JKmr$lKep`Kw=W?vapR^<2aX;M2UQ@cOW$RL!{TeYf4e1rmU~XSGEm9x
zBSz~^ojRo)ClP~`gm<W?wS39A`1rBD3)$|{r%x*=DzXU)g(B}>7K|)#p5cs-kEdp(
zrlvN;L;dnnFA5(X{Nzb(veIL~;P+i!G5I|nQFtcX>FH%{Z3U6oI1V2U!Zsf0?R|?s
z7RT~?o?pn}%q;!G(~_p0Vp8`=^W~+;vXwu9uU`xEF>FEs0kpFl`*!r*yLSj`4hf0a
z9J8i`*3oc@IoqLHa<4-tw(JpEr}oBa`av1M!0c%2!>3R8zj2&+sVvf#cYRN0$s7}+
zCWWl_$Y=SH+dQ@9-WwKyFd`+~UA%6bs2-aGqGJUTNkY`%=|+Twg}GJT#AowgDtH^`
zxuQ_yF!rN0bKjaZYmhz|3=9kqMzX+#BcD@f$(ltR_Ci(&4h=nLxRjzA_o1QTzP5pT
zIFi~-qv*t-XzLe?o257W5*kxL=?L@6(9LB$Vax92<)y>Nz|742(Oj5W(j$6s&=~L0
zeyUW{-OVB(Ab_Y()yZa?o14SSke(Fh$GZqN_gq=z5_g?T!j}qLwgsWWXFE>lgKJ1r
zlUEHl#$3f6VO^50et!1)M%NR>+jcs-w*=r8w<5Sr@W4R{N*BNHK_+;Q6htR|uqs_E
zt-Zwc7?`Jz&pO<qFWqfy1*0oh77@udHa2|#Aiuhbb|K$CU=dfuBjpJXz(?~8H=;1V
zT#o5hN!CFAx{zhK248Rm|J6S^8i<W<beM5+e%=fvd>s{)pm8-FLJxa79=S83!Bizq
z;(n!3AHeCL?=F3*w3hzy@kXp|p~v5oxY%TkWX0O4=PeclE0>gx^_1<))xEEuIgGsV
z44Zs*ylW4T(v7Y+m53U@d-r6LHL~r7RluG7{Qdhn3+<d-UBM4j5zMJ-@$cS`l_qSy
z@3oWjz=5?fDtALeL#HF+;`V{dv2$_?I{eak_39P%=FRLpJc@-2&yth-Mn+PLKU7tv
zeB314-KL;l1|n2xnsfOu<C(K(D_dK&onMBA?%?O=U%%at?luy!UqjTf&(GBl2s7Om
z6xqMxx$mZakBNRyaix*^pXr%?TYLM8hK7uf>o|PgqRQ+xo1B~bV38XV8R<_)iD<PH
z*<+FWBrJ?b4WztH{{eJ6SL)`Bl4osa2Y$KM(9G;^V&VaCN#v9Mp`ql8P|!f!$*0x{
z@X4YgQ7|<mB(;~93Mp+k+1Z0aL*KXOn1$QKkaz}`{#;;l1!!5P)a}I7)YN7cu?W<o
zz>PaNvn*P8K#!Ch97L>2elx74+I%o;tfPv~{$$Mbh2g=$-oC!zi5wLrCEm$DV#ol+
zbKkCk>i7l)1xd$U$!WK~dGq`OaR~_)?{c-?0v@gOGnSU=wwDX^Kn9V^YnvJy8_k88
z?#U%iJAc0}$;!&wGd%k9r|yr(^id63gNtE!4px_HKs~X|kOPM59uJ4AN?dMua&&oN
z;Nh3&>fT5&xaaeROZgL@8ymM;Sy>GYBd{pft__d-ySxknSKBr;*6|sXQGc|zS8b5d
z3{uV2?&1?jk?96yvGYBiaVvk9c!v`jOb?tmu{*S;0>CZ1-4g6l-(%6Fv$HcSa54Kz
zRoIb-&581ft)tnx8H+0q^e$b>(#=@U$<byh0%2gHbcw&~&CU0OX*0$^_?cdW$bdDd
zuBnNa_N4*&ipEypy%LOFT-n(8VErbBEVo5lPSx0Z*uIGmB@&P_7rUF@y|hYAO;r?g
z9(L$<iYPbS5B&v-5s-X%)3wRoas&;}u(pEon_Gg9q*k1R=dodo1-Bus-e)=r0s){k
z^(&{z7Vz#yXF<8w+6`Ix`DRE^d^%Yaw`#+Ac{8?EmzZ}pYz`=<J)PLBmaItcFy5KE
z%n#M2qC#fqqD?Gv513iSJKs%LTVL+owr$(5Z@HWBL=20Zu_5skxRCqtA~$z;|NHkj
z1O;EconxKfqXe40apOirnBB^<^Q?>bP;L0Rm5Avu0Rt8UB?F(1TJPU`0RgC@PoPdM
zFE69KLSNZ|EGj4@q@Jp&m=5$|Y-}797UqL6M4pk6mp_-GdsO4xx%PZ31F!O*s6WLe
zC6S_zH%d=^E4B&+7Qc)N$b7=qhxPQGk2z+l7A-F-0ZAhSO=y70Ou!Juz~R<Yow4$y
zwOV!fIX2c1&Z`YTydh}m!m3@?5mhIr<C(?NGy)~F+wq@9d{d3xlB@0)n>9d%_X)ps
zau4S@-&W$9KRp8+td^<?HDV}m-&0ieii(PZaTBO23TMwAn(nxAc{mhTPU>$`Qt!aP
zX*V}9b#?XH#V>_+W+xrTm9h1~Qog6edGte$I5a1|FubG|FTEbonXv3O-gzQACdS6W
zfj`Ji=El5JY1}5!*p4PvE-o&7S7p^cPi1B0&F9m!*4wVK0G8iNNii$kxZauP{0kol
zLO@)6vy8wqek~TViOtqP)TkSqlpoa$jE_GkDsqi4s}qg&EM3KZ7=Ro(j1mLh+lyb)
z-3HFgwja@eHnf9N*|7bUiQDfM?b@YYgx8PX86erU!*fmUG_1(pRVe64%DWb}TjPo~
zdCtd&+OXUa43)z60Kgh7nkYSIy3W_fXA-ql$o-E!P<kDr2Vn*991DnSLi02*a8sQ7
z-0q-`zaPsyJxiCyMWHFmVxbqlM_JwKl)O{SKsD&W=zPex!!u6@@TM(THjv@S^>4yI
zzh=~ds%#P;!D3DQ{%wND16!VftZIi_9$E((X7P>YJ-Gu^-d+TB?A%!a{HVCP@^`Uk
zbwyrNQ#0PvSU2O*<fOI4^5kizV>jx-xK&bAVkT#2E6jzzD?LCm0_MMsDl*+^*AyHX
zsbFq?aAvrv3bFg;izWmAr87;j;)_#N`!>?hKurh&SRGorqmzF_50_Sjud4-WZZEJo
zfXzlqlV+-hFMgb^<<0yEeFvrVYRe14Tul%r_ZW}d-lgy4RbQ`6Y8Mb)TfWsk?U$G0
z@lJr|osyE0m-O^5AVo6-uJ`oxoSW!Ttqh>g&dE7vIw3VK`+e@}!+g)ty<$#>fr>sf
zHwQ;YGq0>HS;abkkEEQqjBQ9%Jd0e79MiLe34F0QI@Xb|t!tcbwK_Nd`uPBpr~@DL
z6*j~S5fzhgKS1iCAY7kITpdx`KLB<UEJ0|r^Hk-oW{ccK)9y8|E!(#vJrgKH76by!
zbj)KA+eK-OFN-@F8P6CR?kB*DY`M&`6*g|}jWH@!$lE$a4u{S@5mq0!18zJx$?|um
z;4J64QvMdi@nNS)!<Cu1)!vbj8a$askdg3qxqMH#Rkw_0bH3S&QwE-YD<Nr&e9hPc
zc^II48)5`PiOi)-(Sk+U@()>RPqgB~Lqb9bK7~492!y?v@$fBd+|Q65-o1a1?FhWK
z2A~`nV4`H6<>t>XM79JtOnGa@@AKANnBkjmv}41<@J+UfVQ4y(Syw-EK43mUIT&k&
z@Jj;lEGQ_jp6Zu<V?UBmyo)oG+?-I8*ty<6U%^9?cO96pYYJ>K7HocTo)>aL<8$>y
z#^csRiU&O=VBgKn?c<0&pFwFfwm)=^X|+&=$lYs6iK3AFJG*1gu^WS}2A)F*)%vJo
z56Lb8b~6%YTAb^!;?{o2TwY#YA0zr0S;cmGP{HIu844NpBR#Jc9RtG$=m#Vd0wMwm
z^^K3K01-Bu3q!;G40xHm@hZSj>r1`n5qpBS0ljzZ-d%%&=)AHxJT*7RKRI?f<uiAW
z8w!F91O=y=hGRB2Z^|ZXG$WxU^Pa{JFZD!`%gIe#%)5t7l;u2Qid0u$;lIPi&W?Ao
zoAJJ!ZvKt4*a7XYukHXPG#&3Olo~(Q6%<6rF;!4hlyjr&<nrIYi+y+ZfzHwb3)jj5
z@%=$=%7Xrh&#ZW5QipGFa&{&X%aF01z5O868m@x}{q}h-2P5QiTz*@CM@~*p_aprf
z$^p=84dgB+CT4AGYXs2n<;8iWb|PU-&CVtnRR)m#4IvAmQXfFid(fa%42w1hNyBYv
zEFWbo2k8(WiAQ$lQztDAO#<>y?b0?nI;pxxht`nC`1#pcXgMqUIXHZw9`F3KAry(i
zmxlg1kU4hfQ3H=fj%#1jSq~gYd}}xJL2!EK%}bDDG&6L=_jxQpQLhJ%Mh&g3tn|et
zyuvyFsxAOy?-n+v!=|Np+tVZ2Gq;zSdEsYTrnQ5^cK{YM;DF70Pwv##)<zg3Q(;-U
zrriD@*#gv3qNNfK{<LnxhQwy`gV-TV_wRtZL_&2Hy7rY1w7{im;KsMt+_?Ai9yh+G
z@5WXhgvR-+E!!Jn%|l?!wS@-95lu;A`G6&eKKaE$02g1*49LR$6BA8P0UB{7s>zDs
zL?sfunFmS-8c|$a+?I8DEei_^0aqYWYDEs$(I){lB8v*ib*9U)#|8m&+uPf#Q(&LC
z%k0~#s=HXMaO^svtDll6ZSXnL($dp6MZZr?Pbc7mYj>S7Gc$uq9hS*kK$s3xq!XsQ
zcI^TbSOni#KnKiuyl|N8&NW0?oz}-wOnLjep|y3FsHiA*W4it2p~}at4aLB;*o+Ox
z9ps(lp^uM`FZ}r<=sIWlV4q|oDJ*CGXuo*xd+aIJW|`+EWY2I&mmTFdSvitVfmbV?
zu1RdBzN}lNTeA!F&~u;W?y05=n&=T|JfoDnO3>^C!p#o>8we1faqs!8`*aPLQSVzX
zT6akzFUPq}*PQNAy>QO-O;#-v>pIBjtU$?umG2^j%oZj*S1%g52j<rmd5!hF(#@d#
z&ENLPdZ?COVxf0!baXUSNE(-tSRjZuuix{~lP!jJOF2?Lv|?nGA8w%vu`;wjtx^tN
zzI>U8B%K8|-p(`M#b5soJI}*ft8@0DAiJ<|SSXjOQLgS)^b$+IyD7ZE$3k30nVmAY
z&INXjUw?`}eb>$Lfn+TjHFvk}?Z={##DT<ytfeTLuCWct0uZyhzCH=r3ye7Lqrz_0
z5NKK<5fNv=m04=%tWeM(zoOcOf4V-${@=~shqAjKAycuk#@ExI31e6Ia}4A+AX@7Z
zgBZg`c0j~faaRpgWXhQ)4uuewqu`e)X}EvvuhUoWo=d7?^U}%C!Zxa#-E#<iUjb4%
zQKOVZ?-_}U9I&J<`X0!xprNo`I&4va&P4Pidc<5`5<k+f>eyda_>{=b#U+2?mvV>?
zouYcB{8)4ly3mS2&E{Z!RPypwf<5A_;n6_Eq={MR8WCF!iMai^(@}q25B`NW-@Daz
zJ-)G@PsID{(c-L7&$dseL$n=AvYse?3gyk@vASG$<gtnBV7MShNBv-2li=d8kTKIC
z{J-+b;^t6K2_?n3)BF;g;>|vE55KIJ=Gm>A!5}JHB+7qB>#JDs#)`U{Sm&nJp)U=>
z`Uai>t*vqW`0=~A!7c%=B~dG>kfaSiLERuirOC`k1_zfz$OtSpznGx~2CZjaY0BNY
zBU0)M553-Px5Xd6Z<e<)z26sq#BEku@6Ec!1dj@;Z1&Xj?b3weLA7rH;vi}nlqrGP
zLhNxvWH=6{xOPiU35n9`b`>-{i<icWWIwnG7#SI%^~Fk%a%qe7zMHCpjMP$!dHxM4
ziBk?W8B=A8_QDz0!rs4E&yz}eRc@H~YSn@*Uj1sAquo>Yr?f*|<C)aY8cYWep)xWu
zprt2(JbjzZ2T?DGa0bXQ_AM8ZKp%wrFKODe;fk_=FJKnPXrW<Y6#$aJ9_T{x^k}5}
zZj;V(oxg#;ivr46whmuGVWAC_e_Z8rwfNhw7(+`+N?zUm4p}?w{IRH`*PihuyP?DI
zYi#T)FmCqJ)-78q%gen`jr#%DA(qj^bPe|QN`X#=(R6^-UMg`3M=DeUvNKs<gO>RA
zZQH!c%E~kjXJ;`6UJ+(OkwZ6N517}`MbRPkIT_BN*UUmzmd7izCwG=Ih7_4Mr}f14
z-rth4V5xScbN1CkT^_x5PTrY(J;Mes>v|C{8uLq)-c3|T+1_?6#^&dvnLy;2C&E{y
zwX_&;A#7q|(MTyzo6UhQ_d-ET0Hs9J${%T%P%G%NzH*6#XJSz|0F5DDJ^%jRg&M<(
zdOwiUByo=6Vl6Mn7pVP6t=87oPeGFwmX@Gjp!}F%>A-hIEZg3qsH&EE{Jqs_a|_7h
zVA?HRJ_cmjjga>K%#I*WhJ=S#uCB~WLW<TlbnX-ToT6G~n$!IH>N#N2CeexF#B?gB
zA|Pu{<%qY4`}RURF64t}DCg;y3PYemHNUxe4WiEl;J>35UwR3n?|bL#<l-_7MDrOv
z4wHDnsD=+na4-l&hXjF<pp+Y<IuSnh*uVo>vQbPcX96LapyibkDz3CaIO+5uD~d;3
z&8ze5jyyM^eWXdXyqBS=b;G;n=bArq3wK2i^l|fbxQ9Pn5|*-i$n_H}7BuTSdhHcG
zJ^N522yOhVDtQ)L?U+^fAimuQR|UHL3i^@0Q{Q@(Sg{%u$@WrrQS^ZC?M64h{4E$+
zJ@#X&L79YA@sylbpwZ&=kXNUP?JCe~md9Tgs2<gL7pYE=qrfd*L4HTkPe~t$2?~<Z
z)nzJi`JDhA9)1F3;?wr_!a#B#jIt-YT_=tJ1~Z9R>io$5*3m)IF1A?}a00~4i}4#}
z;26M0g*rocE=VxpxyzI9X~{YxcCLs-?LKLLkkCzZPJ2=9Oe_4hK^Mja)84*)8y%?#
zWlkzumV3?Sn!2KJGH7eJx-HdTOqjEolHsJ=wc(J`hCwT73Ho1E=gMs@k~Kx53&R5{
zIX_ygPP|KReqONiv4YEk-49)(e;sjKu*T)T$E`Mx{;rRcjFVhl4kgeGLTd1%N6*qP
zbc36VSaqkfKS4B2VxJ*&PI#_}afbS%@}JAKI1di|4tF=5OXWjXywD#A$H-PZnQrId
zy)JXV{ON83Ph>ew8G-*PL2*P*g7~7zLl2db^X!wuxC8`(tf?s{3Mxq+xI1XoN1_@C
zy#iFHcTNZC!?#m_S2$O#PsYxYOWX!JMS=eDdps5RZ-AxLp@~pHLRti&y!z$&HX;lF
zBC+%G1_DkK_yf#Gw5(5*_;AEjoVLERZ2M!yWS7Ak41A5qyhyGywqMnI1rNM!Dc`zb
ztRyoaRU?)0*bQb}EZQoh;k7bfw%VL=@z{rZyWaz{Dj6HIQ-G5VqqTh*0GW7ZppFsJ
z;JaxTqojuz%p2_N?7iQ=-%&}qQXRy)Uh8MNR>qTQs~D9OWxehqM*-k>GrTojHy0hY
zEVoP{#?7<8+Cza&58HiLCS5h;+Decw@^Jv7kXHsqM=uU$ck2f)-Kh0Ce)1&bv`Q3{
zja#>xB6WZi?3S08M>a+4o)IYSS5H|SAW|qwj$M<uJScUfxT^>ZQD!U4i(-FgKQHoZ
zCa8&5S~o*0U2F8cK}zwu8W^=q)E=KKO&8s%qGQSF;K1Xv<uwz%fXEBK?v?Hx)i3pm
z03#2e20{x$-#nnjf(SR!CvOH2O^V+f@DG)K5gm^Ug|-|Nh#AsI-MmL+bBu~S5Iu2<
zOioS31Je4Af40bF`0>r<XKIQQSRJE;+i}R|wY3ozxlCYZP;eqd9r?i;(P~4Il0rU3
z_x&Iw>i0D@8v&{x@m+Wah4h5m!eKC1-BNcvh9S1t)}vaCxw;vhkA)x%n>I$*;Hsgx
zEe}hss(&yfWE(=70>Tlsa{!x(@4~Bftn2W+k99k(&CpT;{|R(kegFRbVy`#t0`}Gk
z_dmjbXv$F{W5EWyXXDe)MEpl*fbJ=L_0u|9TH5`NH4Py2P{CF3so|l#A|j8_5hltK
zddp#BaG1nEmDoW?r}oP>7*ZWR>^{_}p7U-DQTN}shHRX*`%uL(zxH0!Ve1njp^sX`
zhhlzwIvpAjL9J%FOF333U*p1?8Ja$Y3k4_5M|#o)*FHJl=iwp+@dPEfR#qJnb738G
zRD-FQxHu`V1qBp^hagncyV=mNLR42bJy%#**kx0Oj@|L&#|KCI70;gK5EtJIEf#Hv
zmoHz!!W7?Z{?Q_ror4375$~v|D8ZuCEO!Cj*VIU%VB3M6Db3~;#)8~cH;dlir4@pQ
z%;WEG?f)3AfYSy>M*JZcNmKtvCM5sT*XM<Qfx`#;V>8w1QdDBWNWX^<<ukOPx{{_7
z)OZDZX==6u2f$;sLTXF&TNU4*zUp=9jlDm%36vYpETc*q(4ktym(%Ls`HfKep@IVV
z3VJL%;f;~UZP<wDjI=vD*6|o<*cN(MxBI*vI%YM%U(UlZjz2!ezhCPw0G!t$8N>O!
zn75AVD3xJtlUX5SXrq<Y>-QZO=B4HiD6GnP*N(d#P1v11Le=^E+tSZBwQ#Zlq)2;J
z1->W&=1}YH$W~0|vENg<IJ{r*R#8!rZF7T?alUHZA--qt=DJ`9GD%N-?*7yMr2Wag
zXt8q%3-7!y=S@e6@POKT3Ia?xLqK4lQmIU$Mrv4GOw6j)_b9m8@-}50Mhu{vI1;Nr
zbI|GF#v~*mY)~Kc7KZqn;65O}GHhxEBv$u7v+*z)!TWKahMs4#hAWQ9d`Phs2>B}T
z8fSzS$sow_LPQ2Z@5Wcfi`U|$fqHTDugIlKdYmiPcaDh+c7L%G6Z5V7yQf;TIa#o(
z>38$^cPE`26Bz}e#P>7rP0b2<x~jExK6Xb!SkGyN{k|=K(1f^*4m6%J+zY#38k99c
zIWKfud}S-7{`+T3c78s2AjpJ7N237pt3lBK1<@?kg9?~~0)b|9b#-+?%7~3cc)*RD
z%L_l&?@4TB+0a{e`Rs_6eB-;2q$+iQOeImDDh>ZF3G)*@anGM0)OQ}Dho(IRfzvdH
z)u+0ZHlkIYdT<Z*(y;C@SmHgVqcrG{LgofqEKPCJu&ZBo5V>Q!T2}NkKj+BnEwdl=
zx@8W6i)gc0P@-w7c&(zQhIl1ttMx|blOO9RfJPD_5JD{lx+J7_pMRlQ-qI2dutm3h
zJ0$mA){c%%t+Yg!fn?#;DbeIwSR^D~RUg$8*FTvH%fzZ<LfPEd#_r{novV94Qfo)b
z5WDM-c=jNu>Zq{wspnF{iiEw9FVR(nS`GO=5G8hCZ0s!jW^f#BM`1pK?&LG5y1-qZ
zAgxRM`Eh`#?77!=p~~{vp6nKXET!d@rc%eXmg!Tf!}zT({P1ebl5ag%k5b5N7L>~^
z8#ZhJzR@vSLOLJ<0{Y_V9|fKwDsh9o6BBV0b!oGnEV`S3dq_wPec0{j=m_qJym5JX
zVG8;VMWLgk2TZKLItxPq5vS^fnkYU(QNjk7f56;Flt?t+Y57F7Hym2s8@8%4%W|{s
zbK;G~4SBQ*E}u5CF8mqIJc0C0frPFcD;5c>1B25zVv|5tFkcRaIB+_IHTLh$CsIJh
z5EO<;!v)gns)Yf;$B-B~Pn?K^z{lV+Gn9y>q(dFj2ZW}4I1e%K<1hen(Z^FS0eYbw
z&TL?bV-LUSe?g94&g|o}JC9#gye)h#{7abU_A-si{gNH5>&U0##bLbK#3>6q5Xtpu
z?2w+-+qY6!Y5#x#0{Z~FNdxrEnf;Km5R8x@9%!W{gRY|%ciY6F@BI|LZ1_3W2UZf(
zCwzA7C<3@a-t$+jGC%BLVIlYcU{3f(CnK=GNe?2OJc%}UgJP#`sCcLcNPz@_`#z$z
zvA0jc_tyF@_g4mz@_~*Dz+l)g>>{K)pKH+)Hu?n;V*vsQX?4f8ZKn`*Bj0j)AtIeX
zpYh&4$<nq~F`B`cA0e7ldrM<0Mn_d=^fUMCTZ}eER%`0(+C|TK4e5N!>=U<|095LQ
z8cw_<gK)2cMZq_>05GbS)<QZA#psI@`NgJRhTs#Zbvmf<VEed3;CyEEkx)W`i-fGY
z#Q^7^fjfKY>X00Tw4+!vi+qG+2g8Z!(%cv|D`e#i!I*uvW>$CZ-X%SEHJBXW-$neA
z#mCb`HBkVs@?4(UfUR}N)}#sn!{+l8?g`?ofc5w>7Kq-d8;d{`C4%^i94Aac2cU%A
zg|v1AEe+k*=BJE|*s#v=z*Ny<&LL0-K@7@4V~I?T77*z*qXnL4c>xy;Um7u>COb}a
z*Lq|ksiCznz9_^O2)lZc;B&j{26Fko%~tZ1WKxDE%RcJx6o?*<SL$`YJ^`QuQcJkN
z3(eF7%>nm5-(6>vm7!DI0m1Xa!`CQrxe4r115n+B?j^w&FyV+EyV2R3+p7QG@bDy*
zRomGg>ZCORBV@uQ;Tcm!trwab!xeqeZijzq5JsExFQ(>3KHvTE!`z3C$ajE^2RY>X
z`}@x*DGi_<{}k|=(3F>YN}wrC5=(rLv9X{+hHq~frA^)O@i~kjFJ0*0<N>WuddC_4
zqutPK2$v<TRN@LG6cgDR8XY~}3!FKFfG3U6(my|WVSkZBf2>J-o|#C%$6*L^2O?K=
zgfW2kqacFB5P~bQX_ZP;y^_P20FU>q?v~H4>w_aqjIngWsXxnyz4x4}NnE&*m;iKm
z4}h3#qDz-9EfCO!ZMOh>8lh`IH;Tb!$N|}K+?s58h(6IPn*lkfJtv%}*|Ft_(hlX>
z8kQ4WTpHz}Af$;{;$Sc{s|w>jM>>cURS)->VP7ad)<OF5vM7eUX9@-gWC@q1w2aI;
zbfAFO;B04vpsTO1FUyjqm3H3L+y#<tHd7{GkKtiDIywp|^sp9jX~b4tSEt0ic{iF?
z@W@{6EI2|86woRlqmwQR0<;Zm+l%20P_WbD(Bm~Q{ax;_@Q1@E<Ky)7LpDM`?wz#b
z4IenBLH)8<(e|1D*zf>j%h%P?yyRwcCtzi?r7wScdW!6Kh<4m9PG<EH<tVdWt7#uZ
z5omC8-j_>c-M{}9xVzxxck3X|ol#VT?P@&$Hw1#|E!3M>pX-;rna)9>dDZ&`lMH8(
zCn6<1B~Tr|qtm?DFC3{%j9J8pgB+F(I!vNQM~4v|Mybr!9eef!=I1+RSGl?#?G_DJ
zZ5{oMYGk`Gd6{(h(0L+`7myysm{MrJ*1d1nP*PG7t<j*&V>6SmA29k1Dx4tTVyw$g
zZg@4ObET$VOu^)E_~uW|Z+X|FGK-fIRsL-hl`h4;AuAQN?glT8zfrIHejGBrE>3H0
zpkRz#y*ynffPVb|U^Upl;i!gXaI+yG(~8PU?%y%kKF`mkY>o5y!wuB6!S*5th9nHZ
zzz_{Q+Aq^J2d<+)#4o|PReScWGl7(V_nFFdP1g#M;Gs1Yq6f9lZE_9x=dWLu-EaYd
z<<x?R6NU~O1RBbi+t`l$cEWa$8cpq*{2ouvdkNbSL;9|+uEeyO%#_(~`5l!Du5Z#9
zd$3m&Zp;lJ3&dxCsmS3z{De<6QmY#qzoUa7pVq=qq&!C2XXxJ1Nn3+*;!FSNY)+62
zvnb{mQ-7|@tzbRh;zZkXroYbpSj2Dpy*$pxjdC|iEDx}aKbX5Wp_6s1HwI}tC?diS
zlO%xD-1>}oYM3dgtJ{>;@*<3;wx)(vTwL6sSt_bQ4$uhwN$?ifCdL=WB#s`XFVW9@
zEk%Jg+!<BXs;Vma$o{zCU@y7EQz@Uf?c1jc1cc12sC`}^X2;6gu&bbVz^D7#56d(}
zHS})o>S4yP-_@%lFwCL<rJDL7>d_-P4UO%HC1gcbpZ%a3Pzdoav9YoEm&+Kqh>8^#
z6PwOhREIvl6Wao_5Q<0SCCgTMW7yNC6hmg;zMh>=@GX06Ymg?FVdRo|a^5}entobe
z+>J87zcY)@;kGl+TYgICt4F_6jB#~#re}O#P(pK~+qNM8T&m{!xh@DW|DgEy^Ykki
z-Z>5(149s)1j)$}YRxoAfg4kCzC%*!OPVIn&~OLu^0)SOdZsHjC~sjVhgi5U>ZGyz
zcat$|Ap2k|`btF}H=veNZ{6D1dVOekcwXm`j(`H0hnj8Uy>aT~$VyG}JW$^MeaLCV
zf4@)ful5{3;hl@o)zxQ)JQznB2N^L2MO%qv3MZgvX%%?eZb^@2@l5WOr|5X?;NnVQ
zvyxec!;vHbh&HPhlG4<qC+zU6?G&-2q3^UeMNBe)RHj$8Mz{RD>Fl;%syi)3eY~f~
zSDU&VC8yx#C<7h=p{a?@)rEG$FhC^}bepLk1IHebU(csKvRyr`p%J2yI*-DMt_~DU
z4Z|lBl1O31)NT!(mh}BG5~OHp$p?iOcw{dKI2uOX-Q7-3PITBIE-oh_6G~B+L-qr~
zOCe(Cqgzc-f@P$oDKU)&28a(1vC^F!gGLZO@)|e`^>{lH70LxVoA_qpp8}l+G9_>f
z*c$r|%>_1IUM1(u095Ik+S+#(xzp&h9<lgxF!|f$z~Gc9n}Q2-gq>lP<?-3wI%jXu
zyvVyFVc<1f(&N8Uw)*!W>6S7xLp@^$c7rR~Bsd=(enB`Cko~G4<D_a1=;d0_i$vXr
zfk+T_2sehx0<$%yN)~RxQHNp~NST{O^hNmFRk1KgK6s>efkmg=&Elr;m_9)`!^}aW
zK-uy;cnU^Z(sp&^TbWICmk^x?;BE$;xO3S?vM9`TSm@M?`8VRL@?ao-rV>+oYt339
zIW}AvNgX^{-FKk9m&|uxK@$-Tn@2Ea?#b0XD<?;VFE_%(#}E6HX!iQl7?ZIFboYs5
zn{8N5iS~+bTwI*SlfOtQrl6XNMs(7>ux|oT+%7AV1RASsYI+EB$`oT~rrtqPh4|jQ
z*|GKSE;X;YRnO0~J)4#o-U-Fs{@KlNp!OoeA3})GhHYza-v-eiQj!AvK-}C!)sBTf
z3T5#viU5&Lk9#a12UZ(`FOVHtI93xjLNbhpK0n9t;}O783_3w0b5Sd>i9yJ${%gvD
z`gwPs2N|fsEuPbla^!kbV@zDUoA*gX1N4I5FCy(P4u-1Ih>NhU0};Cn2P8875zDs2
z{|tuy%`jh<=r@(RFCm3s(&GWPHk`K=P|yHh37!N{4-N`?3wJcRPU=mY5@DP`;gG*t
z{@T2m($jO*P46611I&Cw!^M>04|)HsOMuvuj_HrxTJGA{H)IdL4chw0wJ6OQQi2-_
zdhzPY5;p%~Y#4-OIRL4=we?}Rp=#IXgRw0GCMX{528|$g=TDzMpRoTy2Ne~P^%KQ#
z9#}xPl>VK&n5+p8A?rH8G|Tvb&Dev8PK;1Nv7%-TTbH1b3T6l^{`S3li606h3RI9f
zQc$O5S)leLk_Ur|2n(TZM(KcHD_D7LWe>)uz>G|+ORyVI*|5*=B4wil!Gs-t^xD@+
zurUPP9%A@`RtgtO+$T!-ET9Y>CUK>y+<k;TufK0ViWKF*S=lh&*1}scFDHBG;WIdL
z^%FbNH6vUs#72bYHjtVUYXoVVEQ!zEyK4zYMhluedUTGZ5}Uy?RRJiV_@bbolaE^L
zj%v8ce%DaAoWKL!4B~}BY+_$vuT+`~V`A+db}LlzXHbCv)Sw;(cNCVaw?3vPD@_gh
z_yN)}(gB<*{(!=$@5-?L;CdiP+(nXwRT4^LIXd<L{6xp?b{Rc{SsX>cF~Z#+GYd1F
zE&ZmWl?E5%ok}BTzDHSqx&A%%7cF}qq~A*7ecF6G%d2+l&);=DJcUZc!i%<&T*_y4
zG{cY=eaa1q{|YUiM^Gh_`5%GyL3-uWdlQDvOBn@Ru2IMx_|5?R%oIE*>;`~=?)l5;
zw>-v<w1E)>u$?rw!3B#~{*01}il>~Ql}3yO=vCug^pJ*g+D`pW7|f-D+=nq8LrfA9
zV*yN%@UWalLV$tN*vxDOjTt-W=YQrWRAJDHkZ?Z<Pd@NytjC|Lvo3%4ZuksuNG%c+
zfxM^hY`%<Mku3l1-_Ju@oH$a~bzMKIPjQ3gcGtdB7EU+n;5syy_!C<tNddI&|L`G(
zHV1}>Q|dJW0s`J)By(&mL-Wo0YCM8Nhlm1oume_0v^qCo0`c+VT>uD<M~}9c3lp0x
z{tik?%{oobbuTdRfT(B`gnsV2HtBKK@aSlGE31%`Fyt!tfVl?jXQnbdH1sq^903;4
zJOC`A8I#x{eHhajXoH>w6ojHrz6yN@ur11`6_1}hp?NA6drT#%#Uk}m;j~^ZCmiuL
zjg24RHw~?k!8(S&%y?%MiaS+sv3~LT_T{Mk;yjM^?@K2Go4Vl4*VOu2q=%PnaxaA~
z+$%5!f}H&x$Ar%#VMjvVJ!@sSsd}c+c4(SI_rBbF;Kn!sXQ`E13|BHiLT!u{uS1m0
zga@mhIU|*!b*{|AeZS+-J5Pt)p-M;B+uof^+T+hGm&R6h4-cFnK~<;8V;xF=WevJ^
z69wBZ$AU-CyxSx&c#Rv{tr|9|bSqWx_(L)sE$)C9ji6*)y*t(BDmMHG<J1bYT@XoS
zWM!w|Y=Iz9Nt|={nF^Jx$2;;LLOjQH6YI;(pI?Xx+zn2!THz98NS<qaR^MLx!(~DY
z&zM%2IxHPdl&R17Jj@66|M*djo_>MLZypLVNQ`~~83{%vCR7Q$59&49@^GIB8C6i5
z_}7Au%mB!KhU1686DUpUgDWgmY$mvJ9ck*uILXX<A6{i}Q5Y9E7+Vs@;$KSv0+8MX
zsAKIF<Rz#ma4~E^G!Rz}G7+jxFq+7)qA5a<C-jP<Y;{Exo3;<$wPzUcahq+HU!)0X
zw-mwl4ELSb=iOc%GOI(}Ntmjn2wLJ$rS`gecLR(lhjJ~7f&9;n`*PPKTfr$kSN8Hl
zRBUV`#Gezcb9}(IprOBFTSGl}ihVgXTm0u31@W;XPs2nagb<?I%y=s$g$rfV1mj`g
z0aKtfwwQ@R@m4f7eP$biU)@hn=R-vbJ1LAbOx#{j`j9BC?ThE5(%4h$YgKOhWOb$%
zJ0JR0FjF|BTzsu-=DQCaTGDU^`{G*BK-Hw7f`gs7mk`$g<6Qjw50Gp?7{DJ{k?io7
zAY3_M7PNW{6Q~s$#2+LVi`FQ!sKY&c2I;;*Tm=&(lYj7nz)SxSA&A?A91#*5t0E<J
z>ys{E8rR{&S#7y>Gvm!jArStX;i6)j$T$D^)XR2@0`vrQs(~~}wks(S2YE&{K@I~r
zNkjot^z8<155kN$QuWG8<*wKF@R7Jil$~vutbth3fJX2ILzl_K@p#UlVo^y}$K?Y^
z7s%<sxCvBX?CTx)+xZ(`Q!#`?48G{nzi(_*Ni{>O0OcF7(4+%Cbi$q}P+VYCoxSUP
zFhuj!%L%XhiSfgf<{~skjqm<=^!Bjm>o_+>EkR(p06+&b0Wn<zw7@us85InNKN2t?
zUkYd0AokfX!kCz3k#aFtNThN|+3MqiD=^(+eYXxb#hJnOx&FnJ1bVh443L}9w;;1S
z(Bh4e{ZaJ1Q(|2Lu+BL!)M1-QVMrggcS7FCu>qov;}ytln3xG5k`);8P8Ul^U{?TQ
z2;=^b1lt4<w<+U;=#>wf0bFE2GKl^Q91N=|LM8Hq9VbeJB?1?O3qvka<P|Us;@yK#
z*`ds7z<*7YaRN5x#=9;)WtxEWk*c0ZMTP=`E;5;-Y5+CWtg{usSo9|ve~evFpF+a3
zadfQ0Fa!7+&?PVs8i|e3C%lo9o101371c`q%o%Ec*%WNC^`++rIZ~>!Kir%3+2ls^
zq-5P{)DzbOeTxR=&6}j3b+%#@LG&*6GI^AEY<PU6XWv`y4Jii{l=%H7(bXY-afgZS
z2ACe|Fj*9dK`@Q`j!>IX>+unFq{*+QMu+h=p2=eo^T~A6+5@>dd@u(FVqk+hSGNHg
z4^760BHJNFGIIq{V-b#I43N=dK9zg6&4&(s6ou3eqHYV5Y-v*#xw^?rR@lL%7RBi1
zDRyPjN-hU2EI473v=L?WJ=oHZ&O#xWYZGku!A^JfxlVS%_A)w3_<bnnUyuxnFCTr7
z@kqWI9T3n*(!*swZhZ^YA7<_|aT4xrXzr2*rMd8SW@a*@1?__tZU0L27vRJv5Cq%;
z%Dpi<*+d(`)5Olv9yBauUJYUqom2UEWzAsHyM03O8hVVAhnzZlWX%CLiN|@jkSTHD
zkd7wcHnC-3e{*8gt?=_30ynXywR%ulTTL-K0f$Z&hF*aekmys~7N_CiA<cZ=LqWx5
zmBf_x(dI$1MX^Qhn>LGL<mG5d&sa=*qK3)i?SWz<kO`3fVCF=w>pFk58>tMk4&o7z
zw|9709tI2wkQy}dAjfzEU825|sS<)NL3BQ&3r0HT&>c@;uCmnT0sy+-wgd1+QuTs!
z^#O_lDb3bgRO3OyK=afV!=m7Sa2Y=(!uRXW1kLAaUfk!N9Y#<<8Q!{eE9uFATM!P7
zrXvzA8PR|{6(#`mJQo%g4szKbYZ7I;xw(10BGZ{qJ6QR5CaBzgC~3^~zD2LF>%#o0
z%vK?AKjdjfL1StFMq}JCpcx=FnNFj?eDzxti8@3iu`R=u33*Yi(AMOcY8*6w4u~c2
zFhgi_LVIoc=77`+L$&0P`!>zA7U)cbezjN(VYnMb12#C=@P~;e3ptwc{)Y|v_w!Lx
zmI2g&*FvMCNmT??V}s8R9n~v`88IWu#=)^3kfO7zi;x~t%dE=&=GpGKos(k+IZ>Zh
zN&i?Uj_A1aSbJMb_&yt7PCEE-fQU(2IvJyq8dT`M<lwQ;w}GH!FouBi-~Di)sHv%W
zRqfro7yZ-v`3PW~;EgpcEx)rzg~F1Gw!71aY_1>6`<c(6lJ3>hO&LY6d#`Y~;d)PL
z3{o8k<Si5ssN?%#uRx5DIWu$!2zCuxa@2-+4|(7PU;iw6|8{6YlCv)`??l?NXbx4h
zwmwE{hM~xc)#sCMc)tD_qFVoxyMci*C58Sf<;j=_s3}v}$7BpbF_}!R+mCk=xASKJ
z8n+gw)xw4ju8Gd^xE3c*jGQB$k!#7IgHbjqiKN`%3rBG10jbjfx5#%G`XUlAcF&je
z3+D>QdgG9vs*)5!&0!fKZgQA3kM+3av{n2$$n%;h6DPo+WW_^nMf%`2C|Lq3#Zdhz
z$i=DJnfm@z7sKS^Et1*G#We>?vNy~L`08&e7otcvZIjr-TzBej>U?nzU;vaANCeoy
zr$(yEpen+04sMAF^-pVq;2uy^RP+j8e}Ih*RRR^JD9tqsEiZ%+nh|6$tiiPIm_)F4
z?$?fvJy8wM>O;^jJ^)WXax;(Sb18Ix0o@Eq&I^z-H8UGd`yLe(^fc_*Y6==SL>hsY
z_Fj!K9BIt3G$1CxA{E`Zxw$E73uMs`@%Q&fVosh<LUf;~`0xQnbqq`abgARDY-TUT
zU$i()q(&Fj7}p-_NJw|u*=??H+m&zlM$YX&dF5AGrPi;mda6ca>X6@{6lR9&;|rZ&
z{!<w6`=0h;&%S*Ro6U`34Ox5?b7&Jw%Q_8XrlU~}mTg&H#IKs7x)0>73b|qAWBgjg
ze(3<SwL-`W$8Sl~T@rotyT&1+W@ZWi1=k)E8R+kqMvpa|;lb<#eWVn8{qG>Vkkc4!
zn?3-q;H-ipOY;*cIL(7&cM47_(wl+B1nNri-Vb`NnsrC$FKik`ktCxjkR)IXBGx%`
zIQQ|8IZmE@!+s?!sVV?xK8(>N34Zv`IYNap8pfL{P!?g3g?@!qA|{-^zEfz6#-|0K
zd29w_4pwga?%j*kdVEQDtBeJ4UP0X;qn%BF@_u?AP4al6kK5cv;wNoe$jb_<s@k;~
zN+I@EXqO@E-<b<PayY25JE7SeUO%V7Qq7%_QsB*UsO|uF=E6_h9Pf8aWN70!ro<MD
znU<TON%H68H=-F~y}V#U4ASV^LGsn|;PQD2MdM-DmLue>rV?&pufeXvUvS0&u~wlu
z^I4Jl6kL;v!e>ApQh(w1fQ3S6R)KLt@jj(c1rES2P8q<wmgp3u^XyW>g1!?z+~OPQ
z*g~CtWE_o8*Vui|m=bwA85t9;VKq=4+zyp@-vh#}(6cuP-blK^7(9Ip1QdfGZALzE
zkgG-J&<U9$^u<Iod&b7y-Q9U4`7z^Bi?CPE&ms9MRC3~%;g@Ceq+t5OLml>9UD^kJ
zK<1i}lrM76^O4JJ53uwiz6TJM?MzGo$V})&;%SoPVTVW!xu=fr;PJ-G)~#Ppjym8S
z-87tWg`(4@<T5^BWJ=qda+@^iIl?B=#b$tDz_^9%iay@vQcVBN*95{9Ko=T{joKg9
z?dRjW2Yg_Q_RaQ<YUHD%Xs&w!7?U0XaKzgX4yDP-Nese<fX#Y)uf@(~J9zMU(iK9j
zYJ;SAK%RMq3nWq=Oqa-ocWR7@ss^)c-Ai6vQtFRWvtp3F649pQpbNm;W)E`DY;vV$
zRTN!Eeosfs;YF%6Ol-aoS8d>q-S24Vfgl5*y-S+%=nwAq!C^^Lu!2mYVMnZXWSmqA
zUOR}zy^&_Iq@BO`Y?~5pA$j7#Mj(D7k7Q#g112D-;izu8ZLI}GMMB6SP{F}D*7O3q
zk;O)8oxw`xShfoio(AkpOrvDZ2-4#g5CMeCE1X?{U+QEVtw%=)a>n!Ozv337)c8X2
ztpR8EJCAySy7>}*iqU1f9cs@ZheQl?BtZ}Xv^e;1abcks!+!)gfSG~65)B93FA7aS
zWT*2uO9jM+hR{$6_a`_JC78HhJ}C*<z=ncDTwav`RN;u6x1{k>XqQr4h`o^NLoezV
z`{aot=JH5?2o+TXP!~1_*oh}B2J#;o5Dy(h?b79GC8T09|JmIgi^c?#usOvbKVRnO
z5iCYIG?2l;b+>?Tp%CMXfCDHX(Dy;{h42*m<OvTs-b`a7uZS1KG)(=HEC)Udu_6$O
zPSAF+y69VhVzP8b<Mly;17KQ%u|ghSNw_T@<-+13nD4s5JSU(xqJMOBU|eOR6j~=I
zW459Im~=qV2h>`B3z!VfIO_>{0c?=2e50bQ=|_2bSbIc{8BC<G#eM<?Fgj-O&veBF
z;)S6;ARoASh&hK$)*x%*2mq9qO>o*=0Y@N4Y7jCaa=p;XPy`zz<8!1lhKAuY!um!B
z;%-cQ!xjor{IGXoEwLHl?1sI-_Xs1*7>yS+LnsqOZ;#9?!wO9dZ_&qt0o&m2@X^gM
z1#7~!Y2XMj91{>B<}8RiBA#fV`pLfc3d+iZ_m6e&M_Us(Ts&wkIbM!sbNIpUa+{!e
zA=VB@Dr36bMEO1D_OUI%meq{B7`WKjZW9$8vG8fDETY`YY3Ivpl@6CvTP!gCPEHZP
zB;ElYo&X>kYmDCFYJiJn6e_u~e&I*(N)uBYPBc;j#RLrr3cgDPLHN-QxfWGN8qul5
zu0~?fvhd0#VpaiW8!nPuYs)+LLi0t4-+v{Y>t2}gCKH5N(BqNzk1*Yb4L$%t8xL^`
zS@XZY&@tNgH^vs5F#rd;4sQsIC|hq~-%8B(;+B(MjUq(B|A|2t&l)LFnwoUqkzEwo
zB*=x_<8j!GlkbEu6@x-t59^1&R@x8(*7nzFlBOiQFw28oSqmdH>5T&FCZb=DE@Vbh
ze<;4A_PNmxKb(t(VR)Qa0GLh8V(=V2Qu?Nd52)m#!~70_yf+5s$q+9-08b8AtD*7V
zdEEO4hTn051H3@Ua3pFFkiGr=|N9k(f<R-@i#Ur!gi~JDlIXK4U3|v8mK*^Xpt>LB
zm8g06Dp1!t9PJ{FCiw}t6mS9L(WqB)(qZSLR-u^SNEcr`6@cZz{crGoO*cv#OpZa8
zfs>fHkg?=&6+OjP;GmBqFOWm<-@u@|y}dEUd#G8D!{r0+QuX<B&i`c<(00ICerTf-
ztp(;tR#q<pJ%Kes0{-jCp4|@|`R~N3CY(3Ir(ev75tO?u5#&qq=tZe04bj$I#X=xC
zz}Xw(ca}Va_W{?vz-nQ!mW8AV!O*+>7N*JJ`QS}mz+009U$m`DXt9Vqe3=rigT+FW
z09!h}|2#kBhZ82+<mWGYtH=q8?5T(U>jcK32WUy5<4p1g@aDKn;w}MwV!%gLK6o={
z>)w+UD7b`|{^%+?2HAua2>@G`aI+!D4O^Kh_TzvNqDqhh|G+Py<op%bdJbRa@)5}z
z_ewNuj5Hj+(Rm#7r!oHYT{I>tZ+vNQj|9*J-a)LcBP&fjLT+&3i2eR@4s{WYWmtWl
zLF7%pkaGvm`w@2k8sZ>9_E`W&008a7#W_jc{a4Vb@qp1D2AtQ)v)qkDiGh|_sFlR?
zCUT<_r{nR=-h@m;YACGV+z+qj>f$>PG6ZG7HMh3#cOG&HnT}a#@?1F$DFZ!66s5yB
zstI|lHtX{H;{Z0&e$w;9y}j0DRsV8kijmpnHKZqx&m|QV=^V!qts!y~hQYw+;Ap=v
zcx_WrZyc;cs0J7yr6g8lG8PNw08lUu!BG%i3=~ixLJC|RanDv7ol0w=#DqLKt%)?u
zP*|&t3AzzyuH*~?Lm<K-0-0n#%!cCZLAXJi53ceD{3{MU)$MO?@?vOE@kAI_kz`{E
z;?6<p^lG=11JDQ!T`Pq;h=;T|m(n^)YVd!s{3~Q{S225h)kx1lk+pE;z|K()#zV9G
zl63z{`Ef1)PG2B~HZ=R;YQ&^8i90yW!iV)s-FD;jLo~>779SZuK^ddN@ipMx%7j~&
zd5A;sl~2~-&ct-5Ce6tY6%|=nJy!`Q@{KEq0+e=g5J+}*_WbK+pdBLFgXdxdE;-~d
z*cWM&0UMu-bzNC@#?cD(@JDQuCX*Cv$VS7c0MU+Mx2Sxi8r((pK8Gqt08=FA{JUkq
z8p5BzIB)_BS_9yj((vR2c4g5?Up>;fGEwBb(k13mgkBN?_XF}opnEJ3abmxE!AtrM
z-(=YPLHnhtedzG+%~bF8!tKibCU~Z-Q|q)F|DKC4)2J!Ba-<UD&DLnq;W#HBz)Re+
zKx*5+SWRzR$L2$@J(=OaY)&W)qL?LJz~3-(dnlEWU|_-LZKr0@g(L?wU;_|0JglQK
z)aAH+C7%CE-6BXuxQp5b*C5wb+3r98j#&*&YvbnwE`gF$1v3RWCkx~mfPl{cjmVWG
z6C{ow-!uyS`58zKDc9H_7+g+sJG7lVf*SiOT^(R%I0eyqQ9#Z`T1di6aj}nO+{hj7
zK5t2h12)N6wRgD`m<XM;p)k``Ead-AxIx$=2v+jIneIPJGQ#^pSk^cm^;^L=^Hgs3
zCHmS%oYMH;*>U{1Uu;A~H7<nA)&5I!ZxQ`riUoM<r_j{4bs;E3U|?<7*(msmXZcF>
z4gRN$Y?R4tB`pcS$LBadMxm1AI&sSJHs4(I$UVUK!F(xhHJDxju_rT(GL)D{45@vF
z0tRgwM|N$&@uD!NAUra(cx%X6v@W(?HnP(2zY=pB@v0L;IG!aK(f^c&C_*(z#zAs~
zGDnexgL$^@leolIj_+46(azq;4%HIRlITDBnMCk{%^w8*e=ilOO%SA@>b^J4*@kg$
zG`eBBa{2F9I4bW4jJks5C6JXIGz3i*BUCy6^E`F#=L3h6%0fm*(9MNBqfmjJ#2#)V
z%Nc|`mW82XWIP}rsd4fBs4v?N$ib%BwSAKYE|bR<oD%`(hIw#e27nCJ2U(8pHjI7D
zd-o~{%Hg9@H}eR3kzsAC9tq+@#1U*5u6hQmBPN}HKiC6?P6QK?C^DW5HD-3!9^LnC
z(&X$Kl>gGwQs6uEGl;1K-93oTJRL;T<>%jugAbrr?W<lxm<6pICL=Md2ZTuutpQlT
z!JCvo4g=(5AJ}w?nz7!~=;OSCMoBD%P{k{d-E~UcPC#!1P6R4ngj|U(9|5}9qyM2W
zPoe8vDs~D+t-_(G_$`i0xrP7RutN3kOyZR43pz;q_yDa;{RSK_LJszV@;|yabb}O5
zIKbJ9|E9wih`y^+;&PPO;sGh_e}37B0X^6rNt36?eSR-?0>n27wD(?N`T)at<g77r
z$SEL}bMO-EMe{a4aIc@r)Qu@|=*d1vV}|Hdkuf7A9Y}lixP2U$$?uQ|Y(;>bXwmI0
z(Evg#%QLEI(b7txUyW|=TWFXhv>^tfD~o4{<DZyt*a4m`nIXn8Ydv|>wRIOWzAl|`
zz*8JCIQVLlQfBMSmvgFpqoZ{&IpEYhN{W9YQmaKg&ky<>oNPl$Bo<;6>Do$3tHMiQ
z@@TS~3$yvCvE;+cZ;^|kV)ZmTJAGJs2&e+gL{U1Cg|evm4x0%OISHcWs>Ogs?nwh)
zq%P8nBclsdCB?;I3}gb20+g@{cn{Vd3W$N^sH3zNo{s6MsXocoMOsXCu(81d&|MaA
z9!vG+m}7D9qz5_itiNL8OZ}2s6nLEEkpxbGz79E!1}XcQSUzMnatsa}40)FA((wPF
zUr*E>V!8m1B99hFg-(y1MkxOJwfR<BS{m~PAW5Ffw1>PbyWWIj5<Dm*<Q-a+q;UwJ
z(LEONCn#myO*mBa06ZAT9%K}f6jTb*pGW?HgWC|`5G|R^>c8|~&;Kjcmw2WaFS$de
zix9cagx?5^sgW$`C*Su*%kqdUNf10(E3yy%zmCWLKRdwszsIfrA7^V<ud_Y&s-N|M
z$m*4vV{fDNPEKK)hp!Rz>bx&$_Rdj2`e#FDoWKed@9Ey@xa2*Lk=nUKHV)np-o5q0
z#>p8aYojfeF7z+*yk2A|i3*}FX&l&5-Szy_cB++#4$8%=?3!2CyK8yps9u%F{c2hm
zQx;y_eZ=s{ZSOtCT&GkluFB(fHDBPL_Y5B^|6gsLX<W`}7sqcVyJ9TOASFwvkjx|^
z6@?I$EsAJlCrPO+lVll`kYyryk}af73x=L*QkE2Bk~T}yOv_YArFy<6&&zqmN2&Y%
z-`91nbAH<ukaF*C|E^6#JWRH4pENCLQC^_br@p65DlJk?FJ*TMsqcElW7m$NpZ`$W
zzo4@6qnSzOEWOe%MNaQd=clVT4Jm_pH+vD}t_aw@VY6wjNkmptqRp7^@ANG1Usd_h
zZvTy&W1p3`pV)k~F?VTIa?qq@&#YWN?J(RV;K3B$v$Byxa=P0{j~1^E3syDsC_ky}
z-ZH6E|HaA<&hMJ7*csmr?m2Dxji;u;@g`xuMMK{iKVLgKcH6bNDSSW;V?%P4mfy@v
z=zhk^KFJ4n_}q`KUI|9MZssR@9NJ!))h8-3;PP8N&Xj-)dykmVUx~4h*6jl8QNocF
zDCp2USz!R=^bdnqrdmqyFLtLk?^#%s07Wsqj2ek_#l?;kwGYLwALv(Cjw;RFVXS&!
zR`F}c^wjG<2UpoD8-1Ld5E>lqm_E}mx`)?}(~Y?|hdVyrH8Li-S#v0R@ciE5bK9B@
z?b}xjBp|X7DrQ^s$tQnYtICe}FRUe9n}qx^Pb$-|$}8lcQ;5BnlLb0gd_x2_#NBVY
zJom~i|5*y1I{P;#Y^`&ZRz1_s*{u7eG(gY4U|M38)9-8cTsrEqy5Hcvr7dUD6oKjI
z{?=Vpy{2-f!^#q4=h68s#+*c!*$4zAypB0Wh?3Nnvlo&$NkEv)z*A{tEDsR!d~SXO
zrz^0QE#R7hifRJKFHwawx#D;wfV}-7i`vNLGqOf+F80#z8~4lY+fEm)12^c!v{<&i
zcE!7((ITeDtN2bXn{;w@6Tf-WztHb^<gPpwwL6ZVpMM!~$Y7&s%!#V?dSG>zyLt|T
z(Ngt!<ZP?ng}g>!80qFo&mDsr8esrh5Pd{M<X0U<{aAyvA1x{rj<`u7R*8d}mz1a=
z=Esu=(J~?fCECy;tor(L+lYHs4qFeHM<kw&pL{QQ_N#|`@<%JjwRg>NU1@Kw)^PV?
znSD)w$E9cbp6EZP=|q{jVI_jHWMZ7$(Uf=10BeXNVkMKQLdavdtS3O<&(_4{cztWe
zlv%T7o~O4rhr1eyOk!t-HvTQb&|WRpO}XaPlej5Y4SX!yIY-<}H=mlGS7-e)^KkpI
zpWbQt-~RlAyW=#!zi(}>TEeFH>N@e+a1%N%qg(lE^T5bB@*%_+hZ*SMjTr$->ODtv
zMWKvws*|#EyJA{Ps0PaC)d>rbXW`SM%cUu+`$0wj_Ld))tY6xH_E2xNxV~4sjjEGt
zw_IM3QBl~<Cj4>51?`!I2SF@DX3ifo<;<=dlLidA9UJCZtZv!mEvUYH#>nfX^JJqi
zbS`6*KiF@q3gaCf`BfBTC~*lx2kmo#{eiso0WlTzJdK?k1RyhLO?D;i>tpj;{eh2R
zS^3G2>-0wLRXTil+4-dSo+DNA8jTj7(Rub)$ji=AcAFP#&L3mgX!_`SUHmMn^Y$0h
zZ)|C6pZBZxEEgAF|0=Ts3w~+Nso&>0Z0akh1o{w}l@LIa*LeEOnR*&`@sL6dOGpyW
zh@h#19G0X3q0EJ-{l<iY-7d*(xaa|Z)c~XGeA4Z*9cG(*G~F$lb6|nyAeG0>CygR9
z3p$Ly+o5;grpEP{uR8W{DYi9?QIGX+*}3kA-p#+Z+woB&_<9A^g=Wc<Apb5CDtSeJ
zUa!9!)cE=H6JSxZcub-uCMNe%I#wq~d+Z7668f=U;)5cuKkhf()TE8hIIJ@EQ?Jnm
z4e>Jv*l6bKlr|6LUuT7DJFoj-eCxr30d`YCe#%UrCYm|c<(Kqb_dI`iv+5wjMzcfd
zE7#4vDG-ACp5u}4p5HdAbJ|ejQn$yd$}~;BhAfG?lU&%xYs7AYjV8_$jz!ex9y*jM
z_cwgdOI(oAR5kiTs@7qhO{cz8ZR@(Jto<&XgzShVp7tLDvWfxea#AE!;mM^RmNb4+
zI`Kx|`m#wowS-^qfBEjOS6+9=_5x9wxGW@r9xd3hzUWVk>H7<p`1;QGeQuTVdr#}~
zgzii8UU8;O)DKBeIuhulHE>+NiuJuc|IqH<ab(*0pyfYN$ODcK9qD73xAq^m*z`|X
z4R&p@;2gISP(C1(ue^`#+dlr%!2^%|)na;wrCA)$HVf0PbW{E`qT(NU>wRXw9pF`$
zRAOhaFfAZ`W8mo(7cNAOiHz;GRnM<CWiF)q?4R1Ud9PYNwRFJJ=!2@`wljd18Bf^c
zurU7VrFpX12Nzr%I{xb=7_;S>aS6r*gHBBE$J{&eGP(%?pdIwr<Jr3A0gnbWP<I6J
z00j2C9(etacm7*WK6-aV<r)F`;{go}g0FEOg*CgEv76MaiaC~kU-C5yvbbtMX3Is3
zUi_A5H>C5eJmcjQG_sj&12dB8x>zl3C0rJnjHUi<oACJ&b}(V=z1HN*w+)6im*+~}
z8c9B*>9~g04Ah=fH??JRBqb4Pp>~DdFCP}hnouhc8_tQ!LM+!_TA(4{+MJ4pL6*iS
zvg+uTu%Ea90!YvqAwqb6%gcw)HXf}{JR!+0`N{{<Z1OaZX%ijE9|=RNPqvgz-_|W8
z)oJ7iqGO&HB)C`fRRE)nDw$?kC}R=xtiL}|7?FVIf(6i$TN)j+(VSE_w085T>9c3H
zUJIgrHQl*yq%<GVAt#lN@E91lkiR|Q{s|CCfxCQ)h5)!9K0K$hb&xJ<1u`1Yaw@37
zbhNmf!_{7-tS|_c=tE6S({b)Ub6&oFqfwNWv%5QwrKg6**^M_(b>9WBiqCJxsD$)<
zr%C%Z7z7LJF1c=~Z<w*3#BVIhQTh8EgO_;V25V`-l}g+|)$Ljpd?J7?LcA!RAb-O!
z@<@N@(VV75U`Sk$FhY{Sn63p^WKQp`sU-i2;BS~ljRYog5o|N+Foii&XGEwB?@--(
zNQE*Fisd{ismy@G3!$|j)|?YEXw<yTK#27&>ulCnb^)(n2%?Y^?g;@J)hCU%{uBD1
z>kjr2q>M78w?mTKx1<|}_kTW_;Vunj(-bQ!f4phESOz`lCVGIzwZ=FzpAFQ~vS1vV
ze%i?6dTh$}VMv=bnPeo`a0mcfDt}Molr^`o*uxwju@zO8Ii+*;-g*-|T~(0=N1;C3
zM1pnTks|{iI>%t~ZM|uL>A0u-9#|%chYs&w`OOwQL=qGx8S;Dv=GciP^&pjTC>33h
z4)j4PgG?Iv??dRvW*FtCKXxke+k(D;$K?w{%+n8tP~x(L#Ml(CVG;v|X$(vZDtj4Y
zE4mb(K-$Zf!O*I&k*)BKQK@fTy|?k6`P8YksEo+C-dK#<7}W+s0aEmPe+{wP-Reh;
zj-9+c6lOA)m|dRKa#UNQp@!4N$?aoxF^pHhNSpm1^Da;fi}GF>&tXOlr$>^QH3lea
z=ut^V!$btW@*@&FOrKp5!vH{keM4uV^IeavK8PUR+q-dUQfhJm(gDfw5yqOa1*M$7
z)kWJK1jT;NeH0YG=-Rf=ul9;=9U%%3jp+Dvbh_Lz_Bf}fskG?Yrzj(LO(jf@qMiV^
zQxjT?DI1)F=!UrQby@b2e@=2w-+(I6GTi3(9gt7h{Me8sRZBWnPx(@CVo$oU4|<xn
z{Y+-gm_ZgoSg%1|2~;0((*ILi>%`+%%)PoWkUbTCb@IA(<xU<Ru7KOnutNDV(Mh_x
zanlD|@(`JV=Z65-GwbP=tkTfM$3UCJI=%;t3<u-FVv*Qc+@8Qz3bHy0PO#0)HeLw*
z$}t?ZDtjPd4_q)~09`0LM|7`k5|@&Ns;_=4>yGZ$@($UH!8pOpUflK^!&(QZz?`-?
zZ`s6NY-5rge0imOD6+gRQU7R00oH}<!*?SdUnW9XktOBj58;;pxrsv<jc^GciXS>}
z7!YZF3B{9)?@TWDkxv=`81<2)-xJRw^S&pZPg1XCy+LUTy)43D<W6?-?R4ql<drz?
zsD*f|aS_yrq)Chv^og5!VyFuwX0gIW!)SKuq1||^B}Nx@Yz?b)4)|-1O4&JbGbPss
z=bzi++aI4x`ceSgTr|Wilp*nA!qSDSRiqFtQ%}n5dqS^4S0t0JRJ1L?g@XKz9UGsc
zQtk8L{{3Q*c%isq4D^V49^m2r97ezbbeXQqyZkpph48;$Nn3e~qLVxPa=abTAmWub
z*9ammUsSLnxo4ns7w0=vMQOA$JL)Rv>G_9$yYp#E<wOa?-yS+6Gz5_Z{zc;(6>TW5
zt`tkNohuE3vDi%uoMAL0$5*T8zPZja*mFyU9<C2grc6Zfwey0uOY9IG-5?#EzkSx%
zB41<bdF!)2QcoiMqe`Z6KSUNKL}N|YBgaak?gq~Ba<flxX@eF=GJVsQbC9Y>{E^9`
zokia+8Br7g?2W=rN|-qA2+=t8H*)8EcZ^#kP!Dt_cR@VCKfwc=LPdf4FJ|q5O~6oL
zHI~zv)nH3j1D?cVozqBu)0{BDzFuza!Hb%nlHyAs(^EK!wqwt4;Msz$^ab>V`0>L<
zz%J!AaazLD4&`$}dLaSZ40C=YT1C4q;m3ei3>Y-Xmqm_}GH%<;*(7oC(uI?{f2}F#
z&oyfhxZubN1vrsM$3iVxGGMyb!nb|2g8ERg4ULS%Ho~u?CUKg8l8pj55gbmO1E3^K
zQ88>i##@B0ttqeyq?OCiS8#rA#;44)7q=wyal2xKD2@P}navb4w$EuYVMM3-Gxbpp
z1OUl2+_;k9g5_E+7LY*!azOBZeq~MC#+Vn(kV3!F$N<gBl~c|!qtTd4Vi8y+pkG(f
z_`ve=R~LRir=etLacm5NF5+BM&26UJ;>SpBf~}DZ5P&9O{psC1h_EmpL7dOctAj5O
zi*7eCs1MX7>)MqH^nY&!^x4DH<BkeQ3p^!pgVeed{u5G2$q4|>kHI0!aq>F?RFN9;
zkQJ^EZozt$yi6cy96S#;l%PycI5A1dKza_7B#)8IMHXuq_g=K}WpxD}9P!FjaY78X
z2sX`CM-Q=vLlR%;v6I%wP;92@{_U{P0C=KUfd>*E5h)MXWPB$wH@XHMnmi78N4e37
zY=3?o(Aj?_PI6--gXMY7NRtiU*~7xX=1C9;DuXt-Q>Vj|!5U#XICj5OYhof^!pyET
zQw;PH%7dY!{>uG^h6Y#c)d+Z$->U8=165MqI%=MzhvdvcUxrZh*!p+t-<&NN_tj35
z@so`@5Ggg3iw6+sbqGcEs5aiMBi0Zy&utDq$<7{Kv{uuj`>h+MTk+ozqGFT!w4lIY
zfA*tC%D%~=x^0gK2AX0j{C|Q#{Y?Z=%(My#A;3utDR^HBuA~PcA>xIimP&Vz(!0Da
z&|#s?Db3w;MsAB=szf?dYtFoP)tz+UoPZbWv<wZuXYvzq>e|RV7VLVGL~!9s%ggpf
zILc;VE*$4ksm5_6q1uGkLy?<xTye@tQ;By7RLmUxg7!yWiyK4&tS*B451(<Nu(@i2
z=Zd$r&ZeC-kCj43?c9Jg5rZ5dF-DaA5>ySviKQW7RN(rX8c2lctT~@Jc_o01?yC>n
z6gVTnCfuuX2rL>FtlOJGN6v5Kay{)a(36teiLF^Og7FecdK)D@LqdOPE3x+IBfSt`
z@k%t@AF5h2(}YSwka`NHk^Lhv%+hH}>^)6Mtz-^hk0PQJc?ln;WRLKj=!O@lzRp<_
zC!$_t%rUs`IV&Y=2bu-KW60%_iFNK6p6C;v5Lj2Z^^G#sj*^A*S~ouaQqA$8N5R8z
zeq~XYxVm9HWsRj?Nb0~gKMl&{{@~z#Y)i35iP8epo(+x2!1UUDxm~Da;o!1mN7H(R
z>!++UI2sfbzRfqDz#zQsT$ctPp<sk(J)u+Q>OAZ}KOZ=7z|}M>Bg0ztNT#=gv$Gc8
zfTVy+5?q&29{I809n^el)xyk|vgC3WA<bal!Z>OjoxVEbOYQgMx)MWcv*SekzIlaf
z4_OSNQqn2V$3_=hFFDQCaDZ&+dON$B)5q_pt3W>v@2m3Sg;+96wl|>t=YBqu-=ca_
zY{i>974~`{kkiJERc$lU*2MMD&}hlM<}onHLHpFC*5gsLLpGD=zaEqSf-IM`wCPv<
WUXfT)Qp~N8is|N7Q?8pi?)o3Ly}Awn

literal 29473
zcmbrmcRbeb`#!FT21=<^c4TEFGm=nbB_X_!okT|Vh{%evE7>bak|bFPk+K_PW~*$G
ztnYF4{{8d&=ljq1@%X$xdb@A;{d`{6b)M&O9>;M$gEiDnZ{NbWg@S@&yV4nXO$v&2
zck$m|s?GR~gF&(z{{N_w{7Eg>hvVHYp1VGOdo$fTVNuXAC&x&Ah;^eJeY#8f8Tw7~
z=|N8Ne23TjQ5{x|=Hy{vIa7N}^C^qpuCbIT4Yp(Hkv&nlBP;B7!#nAzu5qtxT$r6U
zeBP1ZX5k{-)X3d*j+*r@hf-vENrv~Qb!Q?ul<sidmnFaOV51MhPbYP=^%3|v5v;<3
zS6ij?*9{8tDMfOOJ$)}lM}8*OZDhmGZu<ZG-$hW%<L_T{3Hy?7S&--afB56{PaJen
z@BKS$yjeQKgMy6z&W+t`uy|@v{I)&c^nF8v7t7LXo#NtRl_Z&jprD}B2bHs*nSWql
zIAY-1TNED^b;`nmQ!cva`lp$hnR_CacYb~PUzM4#(B)Q+#-tN#8uKevv?rRg)S1gy
z<~swQSFCq)b2BqD+x55Pc4(;S%;5X<%uJc+z1uc#xPSkCdRA6cTwK=i)ut0`Q}4Nw
z?nXq|8_mzw>@k`eN%HB5yDDv+!RdRON&11??6CCRtG%!6Z|3S3nF!y1rk87GX&Lu=
zYtVZ$lb>I5t7~gd{LoO|l-A;E6y@pQAe^Qcmg+dt=rq<EU|8mEKhagZ^m1kCy_s<S
z<u=a9$ViI1#zt>rqo=mc{ngZ&>Pc#|!wuO+6{{P1nFozt#2xuhxi<Wu+jPyIvG#oS
zqZS`!sZJ^?ZjKkT<K*HR@vV)BiBTxB?Y8PEl@KVK+j+I~<<M-?iCUBVYXk4Li`w<v
zt~7onuvFjBP-7*6`&iL;auQ+onrk_=<YzOhG4DX>;NY;ud?lWmwXVMY?UyeM32Hi{
z(+?jWc%sc49v=Qk>oHrWR<@Q^q28RkG-p(Baxx18pKfw#kBw;BXY2R%^>R6%8NSI3
z`n1bY{Td$^Vhn5l_Kjh`si7g0V%iQVsS>#+Zr6r}&f@#;%{0|iJUl!^7*!*#>hm#B
ze6l`v@#4jRM9X|#I=SQ)tGbULwdU=F@7FanDCB*`r?11}>gH<O*x2CO<g(g!|4pbd
zIhpf0^8Wqcu(0j!WlRMfPi$)6WloJ@C+a?YIF<9+#L^Pi?=x8<i{rr)v!%>1@4%^(
znmRe3+dDhcG_ze7hvH(s;-G!{u{<f+(a}*;uD)sHbY=dUM+FYsrzaPqz8ZRLx3shz
zZc1vZi(v0~ef>(rNYApjrI}gs*PnKai41~_VSBgTVjFo>Y5c}Yq<?TwYt&VXC+4{q
z?(T&iKkhrNMR(Mz*}CxK{i9jU-V=kK4o*&5Jw<*CN5sVTM7`G<Jis3`Hub&g&(hLS
z<2Mw)e*F@>uhQP$et6_YS{l1`;e)O&13reW*nj}TycVlxx_pB}L);a-;+gSD9tC9{
z3&M6i$IBOo_pjfuAviRYou7ZZtc1GlYKbUg7~c84uTNv}02TxRvHLZ{u2RZPUqkwz
z(ogj|PTi!HNxuH`%K;hBdkZ}tcV1ur+27yqck|{3o|wnYZrab(aR991H;wozXK42G
ziwkJ+?2h76Kk{O-|EZlEl?o^Q%a<>e*RL#CUd`9V(LFNf_O816nfHqOEn4RAoE%;?
zHMJV1NiTNg;FME=A=&4%7~Ga;hCZa8zQdGy^5*7Lr6^95s$1LTs8~N*6x<WN`oOCD
zb)i-Jvy{<}f~;50;}7WMsB%8@STrT_TYr7ZFM0h3M~}~%SIf(*`Vnz)Txv-&{NG+)
z<;AhBj^WjjZ_8AzLB6QLp%?h^DVzPJZTDjvpRv}AROj(;siw8z{bdV1^yA+O=@I4%
zCS9d&1*2WX1y*04+_!2;4QPLE9!e({R9bqxCFK<5bR{Ko5R<ff(1T-FLW&(nwiI;m
z`O}%Kt*(&EPQ6%QVe;wGxzuxMiv4eVHz>TUu>Q=`^7KC`A@@0}mgJKg{(S~g2o<aU
zpP@J-`A`P_>YyF$^2iG{@1wYCd^b?aBbpV+MUxAjpXlcGr|ZWlOEv!x`|q<ALK#x+
z2i}?VmU{)5?2~eS;yO`0QvEJ$e@!qwmwbuyxI7k50Y9sIeb#cTUmzp4;DolME77+U
zJ6hV$jh<umrz>%pWDqEw^0WH(BAcx5%!BrJU7>4zvMo<89&LGX`TR7J9IjH_W#ZxJ
zm)v-yk7BYMf95;w0_f!U3|?v6J|Lk<#ag|*IIEDQmQel5en5WZ?{5VpBzXgahgh>u
zpR|N*+6B*LsU2)Vnw@^P-!2F%6XRNbP}*H<BPC_%?c29adM96A?F?y2I~^L!uOEW_
z2);>4%iv+4opWJ%dA6zE{`&a03lF6|wDDayi}Fa9@;5hcm!Iq@Q!q12$M<~B(b@BD
zb$Xz-=IMVW|6V7{`e%ATq0IevHI`Mu&@j;z39=@F{WQu+`S{}8La$FK)+}_mAwHCR
zH@Sx9W{pdQdPwP>DG!snUtg!Erlt-Emk<%r+PG;GwTp{O%X9Oy`F6cBLe9T*TM8`I
zTk?!fw3N8m?KpUl-=g8cAx2S~!#}>}3G{d`U5$v1<;2N&cY9x|PM)Dj`?E{^9hOPE
z?aF?~iaY<hH`-fK@#tbf=H8<gx9i@&=bkb2SsE`&y^y0_<E^-3#}2Z^Y@D2mxalvs
z`eZw!9Vc*0^^RCyo<xrciGLfKqa$Fy^7lG6G<1)^zYX0hY!>v$sG^)~T2M#`&-1*w
zIj5G#7kKj>N7RP$wR81?ac)ECxzvKNnmj)Hw=;^+EiFv$k)xXaqHh<B^2MDe;V>9v
z_4#oO!k3|9ZMB3PG5HU%{5X63)s;6XaRTNhdyPETRu<%f^o@G^2L}F~xLRf(K10{<
zo2EY=Z3;ScHumt6g!|m1f9Iz)J^0`G8Mt%8pH8lHaX4Ns@9V!Um>=)lvy|AYo+0Ur
ztlN^SFV<4w<72<N?3QoaEqN|m^Uw|k22SLH_7a!8SFY2kLAP)3!WpM0Yl-bgvJ2t4
z@HhzNHUx<%glwf^7$fz~N*1+;;;dvto);9<;FKU$?!f`uz2}Gloss8sfK^*&nBd-R
z{a9BvK|u|hp3;l{fq|i@!qh%KJ`o8C|8dNdPaLSd6Z-0vc)m%^mU9)}UJ>{2bKh1>
zdvqZumShTX$Kl)U<z6L^&ZXUYb?v*~8CBKYs_~+`&u6OaAm2oO($LVbiHN+Yo7Z`w
z%X;A8!J1Ts&}!^MHOUf9iPBim<+(QX^>kQd`Zxh2hVS3M<1Gv%5weMjYV%!uE-!Mq
zRUSwpH0|`AEeUE|oN5mb1IGwts@!LLAbORjwY9Z+b!90aG&B@oC-M(qNp;5AIQasL
zhU)5IdIfoTf09gHhwod;Yiq{>FwwEHvYND{D)hHzob7K;Io1F7_fNJXN7O{@dJLAQ
zs%Xg<lPxA`jg6aI$#doR*VI#iG;G4cnuyF3_4YLTMOAL^6_Ts2t`3@-x@JE!sDz^k
zFteM)upE`pl`nkX$H)1-m#0qy*hr8BG(DD;w1w6Go`hp2$+6;Ie_ym0*(E*F%}?Dc
zWFj9t(ivyu&Hb(L3YQA!`G{UGT)^9oj*EPTrMd>CuII>qFL09T><@8qk+leU^G0?W
zrz+$_oIt48(tPlrKd$yaK5_4$qhs-2U9|l7y$Dj0f^c!XI#2mttkl(=IagqzDug0Q
z4%&2&$0YTM6DREd&Rr%oM6b~L(EMbt03XALt4&!XPmHx?g>Kz*BnUsZqKMo7Y8SE}
zs^7h1=T0_~qfJaqNV@%RF!XMvG2Kzi#$CW!yIWdX-Wm%AAz(s7cJqedSHX`S9nME7
zB!7qUb4V@mI5*imPSpn-$QA&dZ$ErE`>U(?{KMmJn#X599!<U6mPu*}*`QSA7#<Ux
z7KNUlehYc(NirrVW6F`c`zxq9goMt?%gYDhgM!98i$X~@_n5b7$yD8cNi@DD{Gimo
z__eZn^vZkXwd+E+OAS7hWOChSvj1>JBX3?Q+bx=dJWsT*q=*X(3(Mzd=T@W6k!-G8
z?pZuFJ-uUTejJ(OAsuSC$+s7m+1S|RZtoXUE1hdSi+b(7@>_?bnxW%=2cy)h<L%11
zQHAA!S8H&@6g)jk#a*Y8BVWCCnLNTEV2H|DW7td1Fi@`i?;oFQa`MV~8Xroqe|h>J
z?_-_3Bbu6;^6u`hNu27wcFGP43){V4)Q0Z&&#!yVojcbLe3Yu0q0DytxB*V!E{Vpa
z+)s19ySR=Wi@|9mpy07~t}+TmwpR8|T>7cB7L6j?|4=2~p%Pqkb{+=&lJ%yvL5z$7
zJQrU1YEgHW6;L*#H?1$W$GWh8a<U2Ql&zVuWy9ueEcoETK{Fbr<8?=yj-Ns%eq>lC
zi4d*o=_zk7kHVp4_csO@K$u1)CN=_oM6YaPI(`qUID?287#dQrvEf5{PtV98kl?Xa
z_S@u>Hy;@k3v)(g*UhVP(vxd=b7P&qzrWz6w;SJ9RRPE<<Z7Q!Q{29JJEOd@F$+=y
z2NzdVObjV^K$->>-U+x}f4YsEHw&YJ<DTnBThf%yo*j4_uoZjT_v1%BC9|jOP<>2r
za4_qkLjfo*I}RN9*lAZ0mXL4|fMejq+9EA3*W%CAcdf@-!N{NIo*GCv|7t(!?k;Ij
za6duH1qk|;=b|vK-qph+>h9e)_m5gO|NO1I-{Zcp`74K^keP>AfDMOLk8i3qLYj1+
z|D|;14AntNCymYfZMt8_i1m6#A+iX<aGx7Z5jojikI=aI!fFRSr^?}0KFY-gCUX0I
zZ+ua3?f*<&(ma2D>%p(MF2IljKC6pd4e?@GmQ9Jc(^h;+X<1oE;gvmw)}IM@#F9;|
zE=@WD;5axshT5!s%0B<<)hj{IKi9~T1TuT;jvAcL`5f?o)%LoKxrK$W^{2yR2e84^
zG&JvQL`^L%0~OQ011+Yfr#F|n&9bQ~1I)U*x*FTr-APJf#{WQx!d;#Yq&YaXurLBB
zmwrA=?f62M<EN+p#TWIshoWBYN7qW{hxjJp2aKu;beXM_$E5l|Bn1EnSMPw+&Ng`+
z_(ZqDTUswS7Wdc+)P-d3M<*v?QK;82(On|6cN+&M=kqIHkNDG}FwrwJH`!IJ+=_~#
z*LiC2eX?ThT}@2@Pz%CDBU?+v`qLQ+mmar~gF};Z7U*n3Yu-M&Sm27ReGy-h<T*p#
z@ZcD`fWVy_Hz@utOsZeICYV<?&#0uNgig0LRbeZzJCNL48_`)5kJd5|7xXGmpFVvk
zc|8PaQzOq%dU<6fX5d`TXEO^61`n^!3ZE0!g^Xo}O-N4J7YjInDA!L+Ovo!J*bmn2
zNKH#Sm#ww@`>PSUXZk&RPV4IKO-xKg`=^;Ax2Zmsf5|vL@34XwOU?U_ALX;!(3B(}
zA08MurLE0?i$Y=X`}NBPod-_sxg+IcV`HyMN_g|8XJ&Zj<<2#`Xf{tg`fQ!Amy3o5
zaO+l4QPGS6B_-v<hYv$I=vX%*4VwW-;}}qeDW=VB4_dQJJ7QJBXB96N-=M7TebQil
zejX=eSA4QRow$?~@5(k@o-QB5^XJd$<obq&0zO+K^r9X-P`0%_!lj<5W!MX3;_2mu
z3#zQC*;HmodjoAIJ_YO1|LfQ7z`($r>S(@E?v?c`%F3j%dN@jV@d=2Lkm~#Q?w!F$
zSvEdA_xC!&**`B&ph;$lFFQLMi2AO-|Hi-b;~zXG%W9V<E1Hlq?@M0ik&uumMI$!%
z<8w~kOS_3v&0|jWmI?9kq4DwhDNT~n(q(l&x8iur4#(RG1DWc*w7K}p5#4!XV`F_j
z7YE1PxHz4`SIf)GL3i%x9N8vz_UzfJ+S=2L9W5<8!W3^-8f(Zj`HgdNax(n&Oh`xw
zU3qR&sAuOUV{UG~`-cv&Qx)#DpyM_!*2sJD5U=)=zN{o~w!?>m7H3BWzJEVwwj?&$
z_U_$gb#?Wjk&ho$uw^kxUY?$USmxfLhR(JzrvSq%mX<CbWEyeT&1i)1sTYfE4@PmS
z_J7tfy3nYQ^I2J0d5dCN1nP@%p&ky-wu6$p_Uzd+Wa5p8&S)}4W*+_R&c|>zrNWep
ziwpmVI7zLYvpY<&>NK-gH2}$-sHpQPGLolHpB|dcFD$IFE{u$iKil!#{Bm>hx_Hs6
znt$1Te$ENRmLcJre198od*9K`IK8L>+4@DcDGLR!e(LM#J=m#US^Qr!b8KAPX-&<Y
z;4}&>n|P9R&~YJ8XgB5s3XQH;zPNsIL7}IujXtgAjEc&(lP6Dti9kVg9m|L#=?bWS
z2$=<^{W)MP+JjB9#STN!B|GXWth(M)h4|5ua#Zf=w)*#{z>o{D0>`04+`S=NabTX=
z4=AF)RYm0tzJ1#a#FcLD7q(7*EX?%p--md4L!+a2A^Qd2xx*zX`MPeNb#4DyTm;Ug
ztGm0y{I84PV$AEK&#m6u^5^g0{)vf3WP*^=Bq1T8>UZxP!2Ec6dY(~IV&&!CYG-GM
z1CIov{KU}E5GOhE;ltZ^?$C<acCm<x#saxS#>T!Y_gV^Z(x%+JxqoczJwj^h^;QPY
z_yeLgdr|)e(4dyif4k!J<5Mu8xS;p4>$~uSA0A)Gxp%@x=D!kW{??Q3vmUOqMdxuw
zju@7nLCx`9Zu;As5Vnbw<NbD}l_-RJMXWUPo4BvddbsBdtOq1ylX98hoB0cRpul6n
zc4!3f33LO(E1;k95sJFKy?y<N2Y?vRukGS^{;S#dwY7oB8mJt|6Kt%kzW46!9rCnp
z%iMnT+Y45H{;)lUuD(e=tM|WG1@_KM|5;elK)m3R9xWeWV7LWx1)PdP<efS@CV@Fe
z`&!3YiNU@;*^$PC#r{x%pwQ4XxqvOQtG%Y!%xf+#0wT%DH!3PlAl5!6N|&^oiu<e{
zX9(SdLkX0UUsNO@tebfQtOqhd&Fa%W*VUEPg<l;}U<>RQXUq|+!FW-Qiqs)=(qP9*
z*H)JR%5DsOh~u5S85npv|7($2f+TlRXT<`yKMM;Bg^rF6r^-Ez!LzbRs32w9E5&K$
zvXxl0b7BCypF5B1nagXSkr?}uyC0R+7z~5|ty_rc%Ppy!rl+Ut>0}W<gdAe2Sp1Ig
zGe>>$oO#a`Ent+0LbQI-XWJ&1y?56x?dsz0S}y3Y87>}4GzBob&3qz}@tE~9n~vuu
z>Lku^1}~PmA48+OjM57v@}I;yu&rB;WrH`xKM1lxm$8jm=An*}SImjkKR55)yJxai
zhsuIeJy6gjGk~_(99_r@+iphm*xNRrN*M&{auxvbBjRW5TOlt<K;*Zhrth|a={s}w
ztm*u(4sz6zy#EH@y-SC5BjGfvkzyBg%=%L@B8_}qPnk!-rK-*KF}$Zy^|+17kDra@
z`yM9NlZ^HR9BkVwds7th+Q>s^_X-+QbeFhrA*^t|Zf)OB4m%o6wqsYmaEOTPVrFK3
zn2>Ps)iqWCA=FNE1_TU<ii*~c9;~aV>pK2xdf2WEy~j|S`iYvJo<xvyxWuYZfpXnJ
zX_Yf)jDhG-S9o-uenfYwk@FcHj9f8$iQAG`MOKmI(;e)JQ!^g~3cwaAh96J@@CHhk
z1aeA7yG0Izkm);(66dSstADQ;dM}#4(7T!v;X)C{c<e0@03bz6_IWNeJ0o%<8A#{l
zce{RgZlR&!6c@ioKv$x)$8*zKn#icAmN6%TSJ!+&Gn@kuHcvcdY-}8{Fxp#tRfKWt
zvFvih@Z5N39AM1>>;(hA9-(!jTNK576xY0SD~%7&>rbPX0GqJ^?>UYouxWp`4mB6d
zT2<J7vFMhtgHp~~jm0zvCGS3b_z^L%_-EkGK4CK|U>%dU{?sB?%{Q)meF~z*4V_(!
zm54!!a~PN_&0M`>AY*{zq(eN1<*0BD@>T0LeZB2t#I?oyDbN$eelgoYBpTV(#g}I9
zcVcG)frLhylCscP)q7kLVZ_~){^<`@cxsocSE#8cv_)pY@6T;Tc3fB{`UHZ+aV$)M
zW1Yr!p1QTI^23L%32L=K$>7sv`1N0UCcjTd2Z3v(xIuEn_Whz$0Ldg$3Gu!#(cOVN
z-+a>-CqpAsWgmK!M&!apRBH+Qet+S2z1D?00j&FLLW6^X`oJsPJ}4E7=uOegzIOe3
z2512*5k~a?m%lzuaM*hJ%9XQVc2Llxd3C};@PSBbKo3s>7f3{*+-uZHawxtD4d~_0
zm;CIf!>c<w_QfbGpq52vZo@xNAP~?ev)b~FE7#Y@2{dJ@#-m%>4w4KfBcsm4RB*3V
zYdSR`vdO@^uosuxZh>%Jzu4=f|I#L#g9)ibJI_#6R+a*x$?mZ*aY$TTxA^ea#}^12
z_Z-|I5Z}dT#_J>#XlQ9^!K>yxv;p4X(|Zww$n*X?#)W)ejW<5a&#$bix(WQ=k9Gr0
z0`lV)TU%Rkaq(y1O_1MGf0ZD00>TZ9jMU;_ki@~w&5g!>uaS`v;0dSzkt<)GRJOH6
z0a%!tnx4|oxa&~DymO}<YD~-myP)7*G$!ks(apcR!`y^W0@sp(BU7_lX=ZMI4v8F>
zyNFD*I8idGn{Tp-P`Ziw&2i`Yv}=cu#sjwO{xe<6EOcMxiGEQym;zwMso7amz;R&I
zS?o2T31n9Pm{P1?zkbWr-p0moB;tY5(K^6wH6VbouX)T!_5hwFcOyLqkF<fQIjsMZ
z50XnJVo@v4@L-tYDFD7^E0JY{^{<|?cy*aYe>4O!u3h*l><(jn6PCd8edHlfo3ZGw
zgzfv~0m^9yeZD_BpA|mS1$K_a#Lx(~lp+3w^`}QCu}$bMq)sePZCG7hMdY2_C)o*Z
z7s-@~iRp<^1(TSV80f-UbhnT63VG01V3WQ)xp)eg6hSwH3PY~0Zf&L|-}H28Y3ZNw
zqF&eEpLO<0yE{dQ<8u%Me4l>lzQI=FgLsWt4&tza3r)%F8%gvCw@h?Xl(0bcI4&*S
zk#9;_u{^UC<=q@{Ng-m}rRzrMD9ypY!{g&&fLSQH=N>%U($8yUVffmK8~x8E?BuWZ
z{0-P~ga7`Uo}V8^${a$+#i#%BNxQ$RQTLknBG=8&*8C!JfXNa>8LPkhKJfB%e@#EA
z+2y37^MYDp$BzB>p?w_vXW{T;a+#-mlSDV)Jh`}l@K*Tz_=19i!wmcF(Uv8wz5@Dx
z=0Dy5*1YA|4a)MQ*33^LmtsWasDM$<%E_%qR&UEvpGBW?;>F9F_}wbTOGX#@VksrJ
z&YvS?06j!iWu-3|*3_>*!MJ=#qxl)}2PX`KqyT~e#Z}m>?ylTTr9{PrpLQbz1%hg0
z1OhaNW=U&vA|pmQNK?BlZ5K5y?Fh&?)B@0wMx)NFmtNxwfc;1Zxz^^qbLUQR`~Hnc
zUpyj?%l1H^wGc^Ox&P(?DtTf3d5eHR-syv1*h!**Rshv2)nTZfL{0n2ed<xOBTZ4!
z(S&eeuA5IwO$99}h2*FGpdpd-|5IcKgRR~^*ULp;8T)#DFf`h=t<d1~X?TxpPYl|)
zbN~LcXaOIACXSdM!K-)nBg>#=0p!B@T0Ix&cvfA0eZDRq&QY0GMGM~I!p_4Jf&z8?
zhoJ4x;IT^{&Bu%&B{Old%4aigJoh>+ibKg=S(-+5T3wz#mP1+%-FZw+BZm@I%B~BZ
zU5(UGl*d?w_in4MskvllXY?bUD?N~ln>!e>S!+wvcK*KXM{Qn8fkWqOYN_o;mZ`6c
z3C{!tHKi-vr4*f^)pwWOQvY<1j-!&h`);ivep`v*)?eABnwi7*_RfCT_iowY0pHF0
z_&=eFhZY|NEYCE!y{V~9&w4=DpZ{9+3~iuxPR+Y_nbkGT%JEskzOLf!!e#o~)eO}~
z60UQ(S#~SopO)@LjCdiobR8t}91szKj~+b=eBFdz2V{`zhtQWbCf`vAYP4-)XQX4O
z<#RP#M62WPcVBtNe?0u^cl(dO3~#<<?RmsppvI@flj~2%_uuPi)>F3xp^x-<&Z+_f
zYyWcG1IU9K$ZYM2o&$7-ez-Gq*`c&MGOx`)y09NP65df@dDN;oSuQ6)W+Jg(hVI6v
z1MKl?HT`4JMgu-=*}4xl##A;K_V}L3IF<PR?dn-2|Jw9{pC+e6jRidao5-cg{A@im
zH`XSvsHlnZ#VBSA^_P?>5CEuKDhM4VRn<e-PcT-gn%QU0oM90Xia_TX_3)vJmDOQn
z6cnR9dLf14a#YTfJ*r4$R$reUv?$nzRxO-KTG_zh01DX!2Gi$-g%`A&OFb8#KmTC?
zVJIde`py9fzua7Yz?RqJ<yBQx`2__7XmVZM+@KL9n4A`a+PY)cu5_(-6q^ye0vZSj
zb-Ved_dmbp(eK-*BrAJEQ!xM4Ub|Xj!M^_fw;=UVXb-<|t{?c7t->-^%-QpwPh{Fx
z&Bgh`WrfgNc@m8!Kh<YclPv99K8RY6wbTpg-OK-dfS1Og%53+e8<rnRrd5+9H@Zvq
z{GNw0SPxWzR`3We1lt*ioSE-3X(+<DJx3?cVs5l0nqNN_a?vcD1AS<!aEU-L<d@v%
zGjTm~5VfV8fAs;@vh(rXwkuy$yl9i19IXM;_HxJbL(b05T8}h*fgvGnqj3NFR=71r
zxdzpelzeHA`HeG6>z*2xJ$|y@S~PxoZjJ*bkD8vdZ+u+U*;&+Qd72WLO5l0vHDCM|
z-5_C=Al{7NdbG4Rl!6WW>IzuZfw=cs`Mn3pGXtRv^}rwUSQ{ijFs-_U*1OTIdP3($
z%d#IhPv%eG2IQkWJ}nSWi$8Mm0Qzo4-UV_ZbR60TttYw>$U_duW?a^D-H6CfJX6;`
zO<&0S_Tq6r^&6cs>w;s)nF?(xBb9xncTju!^f59*S{GgObNr>pv(?$CKa{B{x%dP9
zZ@{X`mX-)``~*q^&p!gU`rm6ObP2xL<XN=wM?qWz(=Yzas~GJmlLFst3>nR)w>$y+
zK@>$a7JzvIRNJ?cyDMFqC{Z{PQeIvzyDD6a&zFFjTGiBaXWvna=E5sFprJsdA$uhP
z2lM=N1<?_in5c%1E?Ya7(Y-8jH?KC`{{0`e3Y6aHu(9Z`4ki#7y}=%jCm{TgbwdcR
zR};FY0J69VeUM)6JHP@sAn@fi&n{JsqD3L_2@OUH`nr26oY>G>eB7I&UhfZ38k=sc
z+i*r*Jqy|sq8c6nw0ZcBJvS?pyT-v9pu5;QUSJ&jjjIMr`|#Hb6|d~g;m&K)%g&#@
ztPHZZsX40;>9fTMXQj0Y>Tl8;_YwHW7#6Zs?0H??vG2}tH>H6bn$W1<6EfY58^Vnf
zSIP`ZD-mB?+uCA|eUQ5TqZ&{mTAqH_u4;jbWj{pzua1JfVTy)czc27;J$i#XyjbdL
zpHi}pbtB#&46?QM-Md?~CzkI5!m|4J0epW<kcvYGcsDXq4pjl{ON??rrE#)t_iG4(
zNzj`j!Aql@2Zw~bwG!FM#1szK3%Z|Z?(@U3wU0krQ*YU_{!MpxS@ot2oG(CWoB|3E
z1@C}&h#vvK1Ks`xI-qE57oZRg#9kBNByj3SLD&M8{egl+sH_QD5SBo;{pjj6<})<2
znM&UK70qfH@}GCOJ!izA9LOkB`rBYN_~o^QL#tGGEQk6wzxv=!H@0K;+NX1a!t8H4
z8aGRgcjtv<!}jqrw+LDwl4BrxE?`8TDKPd&aoS}5j<Vwnt%K;a2{fn~S{<jKU$z6{
zWhloGrU#s?C}03eDltl^WepU5HROG+X;~ApJI3dylcf3R474Fty!#&Lyt8pf4zaPN
zHvhya9{rR}FYP{O4BdwaZa`4?ATmusV;=xmg;dbf(^GW(OFXYbuaX2Ebf@FTk3&LX
zLE0P1t5{7nD0YBp1=MOSk`kKmOVAz&eUG~I+IhSla!Ngzx_T@vIT?sDZmmmitP2_R
zcC?!08|UjXElUp3w&2Xoi8B7sb{YsB-!Zzjc4rztx7q0JC~K%PdafP0ntSz_oi_7p
zMR`vKQBfZM-7gq-3w)hEW#_RlGK$JYx<S2M2JlEI6oEA+msXb-AzwwNr*oJyya1y@
zE*IBAc9FtqqU%1n$G<=G(%QxzX{4;5EL&g#@dSA@z1>TXFP2SJ9}1QwiNncWW_^8q
zb90qKy)d;bf-}&)n4mF0o&_G4K|CH35sCh4<a3blz6lBU#q5{>8^1#tA`)}Jd`gQ|
zbg1jeHeLHq)`h|XmPlqQiO25)v!VlC#16;E+(X`-!be0zMOFE2+6pCO3jow9DqjRh
zw@WXWNli55`sHgNEKDJKA!q`@`9lY(MCD{&iaD7Sw40ipoqgX4@8d{4B?Dh|H+}5!
z_T5w>ux{#$<H_5$Mi=IN&(LatOnh@S-gwKyaAng~qdmp355o!)Vs(DTrRl89be-KA
zRB6m2A#t(z@Q>f_EI#*5AtRKONTId@aI>tbvGDTdXgrjo!YPYx(K>SE$e{@_cJ>X#
zLZxbO`SN9$*ZRiBg5R4#FTD>A3}p-T8iEx77l^WRiekHqCM6t)!3Wp+Q`6fPtKY1=
z(PE_){?j6mme~S1b{QuR4XW_bqu}2wySoqKi~Z@)TA_ahTUgo9upPgF?+7o0bl)8^
z?TjGC!9zO)!Wnb`q#@p5HL8;^k)eZC)+~<u`K@YRc0x8aHB}cpAY?oEMk4$AjPVPQ
zgXO~9S%`?zskd7xz$yhm#3v23zFk=WkOGi7I_+yvf*y!mev5kGZDgvI^QP)#;QPp=
z6VeBqgx$_$)E^x(xG0k>GriC4)sMo3PfizPv)a%LcCg*)eLNot6+gnRme6EZyBaH`
zBG#erhzYel$yVZ~YilorB>~NG*y~`?w=A`+Q|P3xeV2pmhPqD0dd<mc5N8@(lTz_1
zdj|)eXe-#bW(v{<d`_2N7J1MqnzFkVmN*}uwG#J+fj(c3yHB3*fm&^UWzP<ch7|-1
zlvr4j8gOa|C5;ul0fyw6RSO%Kp7$V|{@@Va7q@34sRcEOkQ4!1_oTL1jdm7IdIdKb
zzkF`9w%g+BTA)j()@I{xUuO66F>DswDsMSExUC?H$w#K~j?2;7o0=8gD^lLJIDj#W
zEOJyfSFfVGD*x$!c=x>QP5?P7R9GS`yQ!qL+=VzvkPh06m8Atr<Ia~?ohEw{;KVpz
z>|hR`mYTIS4=h3!Q+<^$u68oqtbBtUVtZe9%e&;>Y?YhA%yMa?y|31rN@=Z|;kvp)
z$EeWscc{6et9zb9iKiQK+uuj0T-l_X)#l=Bk1xT)<~Cyn^WWm)NRk8yQqb>g{QRo>
zjv4}mg3tvNLe)faqd2Vd^uWG-`vQ0_SeTpVTQ)I4D1eHnaf_vgn%3js&p^?)RqwUA
z{}X<C{=zL$+UhDpPFmPlrKV-+>l#cGAv(a4ag^fvk54IJ^pTQHu3X94cBKG5K|Th!
z=m^cNi9By5@<1+)8}$Q>IK<e9$VdmB9G7gZzL89UxqAs=nRTXUZCZ1s@4j303oWiO
zITtAlB@|IcaX{LA*Z%$ck!^_N1^xzwZU*%Nv8M!nfiMBknqjQVzuGB^rO>lFlN=up
zhI@K5v-clXX3r^Kz6gG$JNYmy(9_e;YAoDG%|y#?D<Rcol26CLps20=<y6>D`x(Ry
zvAYhwj{?C-hc@xy37<sl#B;DcSWd`hW&ow2SeoHR0wto3UKiK`8EzjGL?l6SuqbJn
z<kMON(Ie_l<fY%wjO38^l%pzNTlJ7Tb!r`Wn@b<>2?3U-)H%Ygas~=Bj5S|Qg*F)r
z(j7dgisnBwS3L$f1E>(L4NgSla?<>628MS4333o^z-aI~&kPNW`f||0H<PKB5Q5kR
z37()92yz>Y@;fu(@595H+XiOm<_2L4V3m<!Lcd_{qzw%cOf@^YJz?|uU5tucO6srE
zZ8nUU9=*&sm@?NEP?K(&c5X-ic_%9yC8(eQ0mScAAI*IVEd^j5(I#KK5b^W#qXORv
zdLMK@(8Mj}3^-PTtE=VZ<m5mS5rzS>KBI`$jj}SY;H9o&M=tO$ggJzui>(BGw-Kih
zVhPWM%XUxSd5nKM)|em_XqYzwe!8ZnMxmn!H-*2c7%y*1I&lYO9uWk!g%k&q4}qw|
z=LuaS=M6szHcbxeh={9q1ayEblVVa6qHMX0N{I9CnX=c8OISD(b`D|=ME;Stu;2uY
zn7?W?EAGld4KbAay1A`$j(sy)h5%*eUC2by!Kd7L4wgrLl=`VAl<!D&^TDQTl9FL3
zdBa=SUTvFo|5E;Q9QP9jz6!pPrn`{7&}qReWd^YY2|8B5s1YJ~P*IT>y0(7&^G!oT
z7+hM(n%Psoe?u<fhQ0>7b7zsAC6GQS_kwHR-?9}xgIa$Q&addmF%ZWJ8JatQmXRxV
z$UOsLO<n|Pdt;eVn=tz5MAC6zh&JR|fIY(bg7b??NN50G2LSYgKR&lMY=0n~A0W2l
zRNqO0uk^r154sV;1WXb^`rzY98$f^|YVtk7OY6bKa$rjV);01?6yWTtd??{~&C$^m
zhD)Noqu_y*0y6==Joya&6HryRpz-iJ_OMh03<J8ltn7<bR5$0QSK=A}ruEz6OaX<3
zO_{8X`w<`i+VfvNhc9$)?robtV({ulXy{h3`5B&zGs?$$AjA_=1&u8M`H%t$mrPV`
zpujMwm4a8liM+JyZN%QX%{GX=|L}px8tlL&#P$Jc>+qfizg2ZahB?be%OtON_;s{(
zDR3X;H3rs=$k?zkF)6=~0KtvSOlW3eI02Bya+9?_D^TVS7>$*L2>kQqXIGH7@4;0z
zkp9AFbvDU_{>;f^Jy0FApBlV}7EiiKG*gx!&44NQM!lB@b4e`XM8rVa8Nt<aAy@$3
zP;H-R4R{U3=m346e^3SYPlQwy0!P%gs}9!Gi7`jMs~8SQ*F2N=Sun+sN~vQrS+?#i
zwtPR9_*QL;>_lJ306rz4?H57}gS8>#7ioiW#FCN!;8x*HV}+7O$c>m|$B7Jr!Ux;q
zcW_}4ir@!QTbvmxhPwn8C*VNY3KJk!=@uwN^h_D}kK%xo^KGynys9S9!xbJ+<NU>;
zPDUaxk#^(uZ4MY4VAL}eVT4EPj&OB_IKWSR%q$m`hpTIJ`)O;zy|_bg$aFW*zyNKZ
zK!k)sv2T?G>-H81y#d?y0U)ChCk`dzHsi4n^i<D@6VrtSS<h^=IfVjD3Gt02f&?=8
z@Zm)Gzoq%%q{UeKG*h$e$x-f$iZ7GOD*G%H;%`m*!%YHrF}s*poQ&7sYdGx0eXKRG
z0!^eC3eQxpbtxM9k$^phvS}@Jd-v9X_$Imtm=Sgf34;5aBo6|g@_l0E^H0XPt8YR=
zs5k4y?=;|ywD@?h668BrN|O}vFhzFa@W)GVU&&lT;uf)KzZ(=pMVwF&gpuEnuX^TP
zk>B(+7oExs?*Lu``elNT21&gi4mea5h{_`XwpuybVH+rEa8YOA$H0fC!*J&LcPtA^
z@-5O@mwS1jIB)It-K904s-j}n^~#<Qks59bwF#Ia(b|%5TiJZHe&EmRcA?47?oVjL
z`lI+Q*G+H-li*oK0|0HjAC@RwC<uAtE+p9;L2&qY0!|S~NJb;C-@DN*Y@C@?MmDa!
zl2>-iFfR*j58@JsX-|oIXiaJ~4R<rrD6DV9P6^;vpAf2?fl-B6#K2KRCwOff8iG6B
zfB)FQ$fyjcgoIiRQWtjD9ZXD(sJ?qeZFEysR;4a=@sK+zEG!&q5bM=?JpDk0)1vWV
zaEHyi?(PII_0M6Xg<$>%b_?Q%BE3R}CTSj|CQEN>=ah{L7b01j;P+Il;walFj~;B2
zElJ<3OC#qFcU?Z#Q>7ENXxn>1W=wOtkC+FacBN%!<AAl@ht8(m{4BbWh-1(+@cR=m
zU9)vyU;s6pn2_>yqviZDgFvQKco<R7h!4d^bYOV+R%qzi;NFS0)>b&O0_wNJ8yOW5
z;TspXhck*AA`cKf)&*)3jymG5^7H2lmml*y(!L@ZZ-4zdP-z(H3vdqzNW0=DxZTaA
zXMCg_2B~m7bskS=V*CZJfWSaXv>jBeb#-;JxM%zZ2ME7G4c$pk{~jOQ(2(2wfVn6V
zju#MC;N-c7M+XMdmJPKBVmQXiFYoF*Sw%r>evUg#ug1UebI1|l>w#M)7+1%KL)$Bo
zj5N55Zs_G6ao%5a-XPnNmi7*t*IqH5O8&!FosPyRUoh*1mV5rMq-|l7-{ZHv-b?&2
zgDIr7fC;k)R7XK}8f`v#*?Y+)*gZx$W7*R&z-a&ecoWmogHT4yL*7P_fh3-c)dapl
z>kR?NY}%*7lR8V?93kWxKI*8itsM#G%U>0Ik6EWy`aGPLJCgofkp_R{00#g6LrsZW
z<fx!eoH8-#=TD+Pcrf>4V1zQ~5{9bWS-#{MH9^MPDm@I25P90`>y?mR0TBMRm6hLP
z>35(`o&|dXN7nnb7tE|10l!TF{k5_+1E7z@hz~B>b6_khMtk^p&~YmJOMSn#`tny!
z_Z%t3cP2=k*3#Mqz2{S|J{Tn80RSo`T|dfh1j+{r)rH4e=Y~&^yc^@Lo_IW1J0}AS
zjl!+PReh*{sLK5?2tN6*Bo^rgt}=BK6E<`!l@J$mwL`PAxS-o{z&8{TaZ*DA(-!Do
zRH2jLQ@LMm^z=nXiQN{8Z-8M1GIF<Em7kq<nfrBf@vC}zjG*gC{{^!cQWsJ%PBRU&
z%<USJ6z`S4h<K>bRq*7$Z*0`=$>~JB2C-wBuZtv33HO5b<LxJu5=+@5)46=P_c(iR
z2`pb1x<lh+0B5tQ#H-#Fl{w-eK&d&0F9cQr!~&T;leD%>2_lt<`DnrcWiA0nAV+|Z
zg70CUkjX|^>o6E(BDlBx<<<RAbl8s{e+b0&5=a3B9unSG9_=S&L<<o5Q;yCZaJRSa
z$ovfg^F;<Xh_%&yVL}z#^p9L!TM<LsYL3)}#*Pw+lW>6m$S{E`=GVUTS@Q-@ei|AH
z@q@s4X$q^U!k13WE2%sbkAS~`_!kN93L+RHCE0rQ6Dzx*M&s`g?nD(tRu+Pj28IR&
z?6{1KjPm7q7_b6hc;^W|N#zUcCTS|xty@<*Q_uV7&!1<QAuG`n`fX2!`eGF0R{c&H
zZQyBMT@zcm;!{=LG1ae={JNwjhyYsva}aB9o0@3R%Ybclg9?bQo>fBPKDrcNSiX0l
z9ARmQ0RsTi6tvee+BYKC!>&L$1aM{4pkNUt+YX37tMgM4Q~!H3zM=lH4?}1Ggh!dB
zUq{j0tt~eBM1N)YC@;nsMr02}20e-j7=m7}g@d>u^ZZ&)|73tIVlP4ZC)`lf{reYx
zaVUcQLE$3pl(FD5_utl_GEv=W(Wl7fY7-(8*Px`Lk`BMA6Vz4IIv7k907s*x?g3)#
zq@&Y#bXhsA1!lgCWdn`m8Kp!2mZl|T(S_+-{Nu^TS6O7X%?Qi-xD-5C0&DBi>s6bs
z6h&|)@G$!2C{W;<IBT|DuTl)I5fT-|(^IX1?KCvQKs|@p*>8d`g!ur%;8v)z24(Is
zzzT;ml>O<bScw@dWZV+lj=3><aHVh*Ql)Uv;a})bU^oFg0Pj&9up^9J8HkXg<DxmA
zL;mMAB?D>NIS7#=uM<ez(V-RCHBf@eBkn-<Xl22wZbo)THQFm?dw>}85?p#x;20;~
zNr0gO466*$R9hEf=&iP|@@9;t(570gu8=_W^$^{%MOu47AvRLmIMu98h$38pLpi0S
z;&D73fK>o2*GQEoju@;7Mz0ttpbwj&pplVF_&~r?P*G8_u(A2&o7Sebje#RN_jtM-
zZg7PMp<9&Gdc(n$!w&<y{YQ(VDJdxcdvHHcQ&IH+@+5;SC)UllIF}FOU7nQJxKtJ7
zs1SyA@E&0FgcD~G>w~O*+SOGYZ7c_H)aa<y|GZsq-@gw=(YiL;%nJ9uG$?ms^g%V_
zk3N72!jx~i=s>ZQ7$0SeeYPU@?}i_@t_$b8H5i)Q;`hw2ezWyFpQnyP;Og?My6Dw!
z{%ToiD))tn@Ph(~Ax7eG4ubdehlzxg6g@y9^z%g=&ULQe1NKnS(q`e<p=E+~0eHSi
zdZA02c^EGGw>XrfpM-(#&DXDcaE6H~7YU#W`3dG9!ZAa&E&ymlJLJ@<_FJF()qWsO
zA~k>jYsFX*Xf=WIKWylBs%=E0kTPN5CImeRQ(|U<uZ!i#5gO!wxX@Aa4>@O|D@`);
zS&6}78+wc%gGKDx2Zd)$I?oyNIHcuW^uqSs_!(%tpmL@p)@S5g7PH7+hp#Kl6hKDE
z^~S>Y;qO1E$X!!iZ7jkF=}C*Hd;R}>>}qgO##}{52g;715?9y0;bG^~r_OKRyaCoM
z{O`M%x1>weuzyQB7!2OR`w(qz!@5?ctfX`@?<)|@DGa&-O`74O0{S6p9>SO-lqZme
zKn*pbNz|;Ph--LqQs9vR7lf|@Gm(O%K%wkOSeN>NO)K&!Cy=|lTe{`JjpM>$ZYLKz
zJA3}Y%aBmje;8wxyLYc)FV#MwMK7k8HAbEj{$*ul&!6`+V4Fg`%5UC06%m@Cn8xkA
z{}B8_%FIgkRafkeaiwGD19s*rrd?`HR|<%v-1QU#t~pqTLAXO9prvc<TSQlcbPdH}
z{fy3$Wta2%Cq2cu#OsnO9JtIo?dB)NljNbYYhKRO^bLKocPj{?i~Y*}n_w6ogE1jR
zY7_80>@r%vzOl5HkxA)vu5eUaY`OQROUI`ZKjxbg(rLrOo1JGWt5c-Bp0-$3TZu5Z
zbw|nUIE^7}``@7Q5DPF-q@kc6kaT*~Jc;V60x|?+sJs;5>@qP!i8e754aeao^)qMw
zr35&8$hh9V-K?1P7VxJ-dC}fSt@9A!1%86rMC(owWh-U>_wSXYtpo^EQdieuQdd&?
z4q}VoWYC%{KKYC2$7f&}fe#`^EpO9S2KeHeAlEEnc8U1-k#Yo_eZ=m(xXY34M2t2P
z*ZL^#o}dJo4hD=}@wThkXIBBE@+ThyxEs;n0g5gr<xE?cnLWd-GvL%sBsd5gfB(zl
zS|dbAHR8v}s8{aPcTjaG6^Fo`Zk+i!AiH|47=)=HY=7{Pe;~95z5re@ORxcGa#~>#
z8g5L$<mNt?L{JYP0&vd0qqZK3J#sg_R#{D$LvfIHi2vRd`vDto3Hl};mof>~jUe?g
zNrL082uoy)pD#S;aO-P=aKJze%KK&rr;oIFkb#uc)HvaQzI}Te&`}rw7Ti7co&owq
zk=@Os)kgppBuC76MZ)xr(@)?Z4A;m8;5lIiI|MQVe~tOvn34cEzfptjN}Sy)4{R^!
zP{I2_VHOX0h7!k3ws{N)TNFMVSY#(kd<KM5<bOg%=6tS4-<qQ}Dh>M-Vq)XQjdXO^
zmi%Ht%L4(<f?lRahePrQikps^>(s!6Z}{8SZsGk%?3f<`!5a%Gy*;$XkIoOpoJ`%J
z=sFI6{EiPMUQ59Hp^ew=?JKQBOhn^btP5pV2h%ZfLYCp|*^(TYJxV;kpZ*Hiek!?*
z@6n09{f%#4C(<>qe=Sh_vtb3Gfs}n59TO2o7^sKA`w*dlid7eE1QHqKK$I;vY~r7F
zsAjQz7yV#4#WAx$39eU}Kx>`=ef=72&3H{SozV^e`ZDI(V|XsSwJv-Pu!WAk8eRJz
z^wpPp%cU{XXbg-;!T?yO06c64<0N#<H^`3xur?D41g?ryfQ1^SPLw->8cE*_UJ&ai
zX!`E9NzOE;)(FN4M5Bp;6)VUd$ae6(BmlmeUb*rCr->XY{0%1N9-;yYgRz2o9|DFA
ziF**TWFH{H5CFpw%`g}E*WqU%qh{+CGcFOc0jxP@>x=h`?b)#exmMhL?l6&EF=znS
zX*6z01LCdu@Z}^KFLGl5+-Tr3?(+%>?I<%edX!j><_n&{jWY#am4Szp)cyPBHGJrn
zg^u{JeedXf)3ZS@yez9BARqwTD{)x+;?9vlk%5|v?2NE^@9XM}kvTj;3=xGNoZD>c
zSphQJCbKw5k0nDgP=(Y6wF^M{2()WFE+L6+&riR7T^g?#^EzxY(Q|x!C_xXl85J!w
z_gx8`nVYxmm4(=;TkLR%VC0@sw;HB+y7eHyG8pZkP}*G#!?ZomXIDo&S>VDzSWuA0
z4{xve4olRb<_aGlL(gdi(&oVB_-`2BjRQJgO;eM4uo0DSSeR-=F%N0|NINq9bjW^A
zb|-{0je0taokZNbSBFkwpM(PkX5>MS#e)^l$kFD1`}Qs3MO;E+8j>DnpKhbpBVyqK
zq=CH`;9UWlgzZI9Rxz=KlLu~bNK3w?X|`t=%&dI*zRzfbd+xd-j}j`-zjsiCXOY>^
zPweAVPy7gkd=Z8UFm;D8E_wfQH=MX2Ix|1EK83o1TVTV`7!W%;570*&;8Gy{$_Igp
z!!9hFa%qSr`!XplnK4f<xBTj{9>AN%MCr5g@*B~_q#%|54-dj&4hJSBWuVmKcOG!>
zBWqv^=T&j>ca&DNW)vt&a=F?VFbhBiMMFV+r#OSpprGizu&RVhLHzoUU6eEj4r_(!
z<b5U26aWxgNA?J#OeRol)kpj^fhGEJoPl9?BgY_O74f;YQtTp7UP&_qSOmkbEG7-W
zdulyMxBl`(2|Ep+qXCA{fRx$%laWD6@jwj<0zr}e$V3W8pc-%m6K$+#TTS~F#j77u
z<WbZq`JOGAi7%M&HO#YI{xgligPCtv^6UXTfyL56l7Yn{Vk`yRa3+9uP$_OAOqd|N
zgDm8RP=wqei-$d6^aoET05A5!uD4v{D9x_&4U0v70)GESlhn~Vp&bE*cu8>YwQJX4
zpua&HzDMWSw{5QS%6q3zMlgVM32uRyk)NNBXD*P8NoocNLr%_H7-R>v3}`uoeH#SF
z<T+JIIXBTAZ~gi4_t8<^L7M8%pLc_a5~=b61MKSBmHK+dbRw3T1M?FoXAi(b5t0UU
z3=~a(Y#avSn)3QP$Ng#kA`9vWtn6d4QU|5oU(8J6?6+a%*qWd?l95mskK>VZW<k=_
zKRrgo^nV*{s?~Yp)3YIG6JyUxTsE}w0=HQUXj@ZLQ+@X>6Ip@a(b>i#L9?;5qpjF9
zL-~?4m}vHSL&dM-IU~=W2@;41vJWp4${kEo8_3|!34N**kxRRu?9ogHCGClrd?;@3
z2TcW4HWZRaZcz`6H|1||yYK~~y(MO22si^s@&a063%#AC7kox5a;8^d!bSg$TcM|;
zgRO=WeG;wApBuzGr(@^_os5UfH=?ULi3EeHUJXkPkUsRsA(I6nE}?)z?5Dv&lgD{=
z7_95${8HP(pEGR;13SE!fN4>39c?gN!wZRweEHjpv4jh|z1}bdK8}gp=yEP>;fG=S
z31-Qr%?q;6?inw+J`>oG`>y-9cR@h`9*F^gju?hB4z8hffD2}5tI5fu+MqfyjHRH>
zfJYO6`-87*IQ;SSFuD{#Twpb5lNiO3TcO`{;fgfm2EE++!`TG&f(ygE7l?^Nn6F&7
zVKbSLkW*m!m*QqYk7_Bmt?46^?>+7c!Qcf-sRJY?Fq4Q<`3z0&>5R<G^@mr;;2UU_
zl+V`L8YyzY4d+1jVOjw;Zam@xa2LM}&<{88FvywixgfFNC;FlFrC|NQl;YW)UFH%l
zIh#I-t>jX#<N33;=Jo^f=L~H6&9Hs%Oxlk%B>=!GTo(xg#v2@mJ$lYBMO+Q&>#nw0
z;q1dcT8nMKdK|^zHb!djbb@WrDO`1hlv~@BR`LX_U8b(CDLIRMb_J*&L#jwACnPl(
z{U=@D&#aYna^5AR{Qu_N$TN3PNl&J=Jo8+1kaYg#`r*AK0PY=-_Iq$$%V{(N;oVB-
zjW0WOZgd!HJw&Pw0*!j>)-;H>vfjadFj*0IDAO*jOLx=PgUc-FSZ+TQ*~v+VsVhV_
z3Nl(s9CKvDfFJq*w<8A*9Dq3pV^M$eOLWiBhPPPZ{Opl>Tqsg<b^SDEHsOi_We9Ss
z5(4QCIb$qsQIQY1Mfy|dRVF9zR2sW}N;#7eq?lIO*f^2Dq-o!|QP^=<1x*<&4lqcV
zJ7+1Tx&5Niid5d3tDW=7DJs3TgP*<*(wpzHoeCLRiWUS!bA_yuSeLy>P<=wN`DXOT
z>t-zdlO!A!m7vk1<3_=ssS4J>8+c-%ufv5$JE+bCcs_q>D|v#F`|+-q+mU839+2_e
zD<vg`h6#QU){PK{P?BR`CEteCc5d+X)%8ls%4CqASp2~lfxLMXeKaEB20lYw?Dx1g
zk=_d&hLnjpq0B=JTH}6HNNCBiuibUY^;KQ(+_;_$nGjbrp}7hyX;Hqt_S)mIPf8gE
z!8N;zY&zb;Xhg;=kl~SSS1;9Y;?)?FqOuKcm??)WuniFcLuW*EG?@zcgKimY7A>zL
z-j==V_4vUvMBT#F^j)K01jtaJ&PdSzhu((U<-<mBb?B6qt{U0o>zY}<##NpF5v!^T
zL}Uiz4MzX-n+Gr=2=|VVW#a)biOjC#1~tc=K1kh#rv%#F8>9t*+E=e%o8;?4`K{^g
zO~UhfR4<;mh<CdG?Gp9{3TOcUBDOaIGf>U2t0Y09lR5Em?;-dJG#^zvyvA=oVGsf!
zQTnzkmN~svKA4`GnSr(XKj|a5A89>W4qt3ltXPlhO@Kj1BvQEw2w!_qt?)#GRSFgm
z7Q~DPR3&6qM@L*_XVlb&kqP@U;tWkt(NOhdf;7lidN`e?9t7O<oNGA^M>)ENI#@1k
zJuJ!iHn<ymM@RN!$1b=Xhi(Tvv<?S&-5VfyJbq#uBoYo35fDG?p25BXd$D2ZJ($3t
zEITz(a^qUNeGYNn#oGj3CJbOt7x(-li0z*&UkZQn<cWUyJJ=;LnTf_H^SDL6?jLwS
zNoEJ$(TS~<hT{xGXBAcwfP@Ugz=9<K;~P=~2#z@5=bem<?jO<*eW*W6+y#f6Q<G3O
zaB-NQS2r``09#F1UKC&lhu7m*?8^J>x?Vv(I3Nj85Wq2}7I_ki%*GjdU&S;`>5*mx
z>68LQG#Da0!5~I>2APqJoq&A?3uu0MH`XlhN%hA5@$m-I8d-^;O@SLbNI3&f7KwXh
z4~|VQ!6(WQ&vXbsAR&iyM@X5|;RjN%qkvA_EBldLL2Gn%b%AR@+1y_@N!tSb<cqP(
zwQI?M49G1oTm3=kOpa|Q4^W#>4W>>9Hwx+b7C1YM2G_%I`W_Rzfj4hf@f$&XL`TFf
zEuDbb5+Lk-pydG3<#V-XF)z@HnX^Q<;eB{cOdS@->eHhg@D&pb4c~z#jLzga8D!w5
zz+yXkgCkl#XY;<E2a`^L1z&_{Hd)n)2A-okdnbJms`1J~FQK5Yw3xz85s~Pw$A*!w
zL<xIhSoQ!PE{vz0Whgzy9ixw3-wa(9kE(Em<&M}?@NARKWIB*E0K`R$-uWg_Pp^Xy
zXVh3YElCTnPiUq32Q!e)8l8gjCPUVZI5+TY0;Jb;_5>g2i-?E-Z)>>kI}Y*OD~|(D
zuN(@0E6f;1o~FWW?f`lYvtZTeq3%N!*3S8TshXU}7-5`8;`asQ%ZC|CW_juq;n+da
z5JOZk2DHHX(6XxFz1c6g^J%e!j(EHXQoX&iGbhZ|K+4Fl(X55I%GS25>W!@!8VqMX
z(TJ>$O$3M3<2tY%jVu6|d$8k462M&NgQ=_GJ_hj!$B!HoDxmCh!#AKBefOn2Os-4q
z5GUOYK(rY^O?bz`;HE=KL@@77P+LeIz$`<gGM4`gWEZ%rH@(4A&fw>bZ*bsu!WU#2
z1gAZNdkkQN8=yZEc;Ja%;TB9vUNrod<aA8d!-`i4KMdSLFw{fIXO)!HgJU0oGo)<u
z*1GGJ5GY>KX5xs<AdLuv<bXqkS<#cEI_?Yj1ZU?=K+pD$4)O#da-tH^J_YWG$Hi%d
z#I*Zg?|ZYZd}%@oq$?;HVx@#7=put)G%{d)%spAGBFt!qgoSsewbY>!t2jBm_$43r
z@6~qyA<Sn%_$Cbl;6G1(bO}Cp&grm_FUA)A@E{!Iv3=s#Sdi(7GcHyTPY(R|v5<p_
zB?^7OFrXa8r#vGg8pwYCdl9R$2t@x3<K)0>^z;~Qr9_pF$xy+kCz{|mz@1FS6o*D|
zE=h+}7m!X~a=>}oDF=cQ<K&1|Akni}e1tA7y9_xU(LB>MgV=OW%s-+wLvg^#!NU-!
z_UwrZ+>u1q1kPJoGGU83@r{GMVd9dKn((=G1S5;jMe_>zzA7nc!}xLFj!<%^d&zOb
zT1SSkLo6T<N5sBJg2^I-S7cXFUtL5tbi*Ho+kpESV{M@75&J~bNAo2vC3PO+Jd00i
zKavDoN)!mb{^8-xvOr!ioT0%O7#mxxIFLm?JqZ^Fml7T)#L(+Gi|3w!7*mAeLcMKU
z>ChE4u0&}jH5;r&7T8hJYC)aajIBeGAbmttAgv`R5zjy017BSEN^^s_F;Lle0`Y;$
zLl?nz^k@|5WWT<?z9pAI5-@9uT>((iPLZK4g#9VvmhC4KEHVPTyk}u@2*JGW1)I*7
zs(1)ki`6bDxp)*6V73C#e!zRPo#<?L0=zsY&k@2c<LNJ;ONoh^@GyA76Uiz4NKh5#
z2JjuEx=i-CI3C6~XMp|rs=RVNw_1v>pyMOb4IwTezh<C%Ar5_!I2G?OH6UvB(l36f
ztX!AetYMU^O~%_n1WA*5PrREzVRYcIxWbUbi5V4yG#M2^x+dei6yQ_|dxZ019uJZR
z(`C0YG7m@#Y_PzarHm_a=?niWi@bCiOScbm>;U3g-f{4R(DldWtt?EUqoSgwCW099
z6gHPId*B?a;VVE`lSc=^QAKk@FQK>A&eZfKU25|@vJEx}+;$x90uEFM9ZGV<-t2qM
z^7pXWJ71UWQ`zetb6Nh<L>@B97j&I6e(f}-Ip_l7yLkM{XX|64qHEm&hzvpm5i<v9
zNa8co%GJBD=ml8O0b?m#_hp7ev!%d7z?zoP{1TlUNjVhAEqKyOVfrZ&lCHu7eMMs5
z`)TMHn!lY2&2Ki@Wo5&B-D#ob;Gw&CI7Ty`#xxY3%z<hFCK($^<vh_v#?cwWZlUcW
z&nAG&CJ@{MbS)x<k$FiBLWAxg!@rn~AVb)Ip^?DSu*o7P^zkon#peOcUhu!+<@o)r
z&zmpno<YE!_oi9>o$Szg`rvo3b0+Jjr>2Z?X9PQ;5oGa)U_9M&nz{S=Lk}|M0&$hJ
zNJta#Lc&XNMnz>1(3XtO;6WI)$fod?brjh#qnjpY9ZziAaRUrHGO+}J4Rp;^Oo}Z0
zeuI+4bgxt-Xv?PGs)v$3F$$WW99+%f@<sI*viP_+WA>YwFs#kC9%AG{KOp);kISGX
zWxIp0y#pd+x0^wRCV3(mqDfmbh#cQg#jW4;pTwCh4f1U@G+7TRi!cg!2n*0C7+3C3
z5d<2pgyypQmu`$(@T-aLwYL@WbCjU6U3-*PVyBELrLi%hbb@=w1m-;{mm_2}8V|+5
zqcj6|q#-y5vR3KpRBxXD`6hZpV|lZ?$*R>8F8N?;@*oHbVw{1S@2OEmBkWn|k^>Fs
zk*&tGZJe6j*Nb>=aEN@v&$5=!Rd+D#ZR^k9YhJ!#+Zn?Yk6h+Ovf(;VKe)EAkw?gv
zaF&?xXaf=k<RCp4U^QT~jQ<p}QhMv-|3NDZM@x7wiz9}%?G?O%T|RNUoxHC3E8Jo;
zCkF?4iYVMAc+T5l5*%j2(xd--{YkadU6@CXLcs>(=#Mb~oLhL+JHNcaIz}dXBIBds
zB*U{NT<b_cs^_7uV!NTNSwe*eC$V8sVdqUhzlm3(vG|j@L2e;mu<s-#!lrfjeC9Se
zDuf(h4hC{2E>-_=RVu${<W<na@@#Q!VWdm3c{EwM_B7)Itm%rD$@&h=Yl6T>MSk48
z{+zH|mt3ntyUe=CBPW;k(dF;<-oLqNKJK3^qYRh_SO&W-6Fl;9abK%~#-_D1=t~7@
zUxxd>I1?nfp7p=vajrX(!dQzXtQD~}AS%evO7uBhjDx@?mD#-Q`WWYRO4(mZ?JK)C
z9^ZOUhBD!NumBl|d>DOCmQ-%=z#%XznF(Va0nB=l!B+Y8jjNk4Rmc{K-n~XM@45M)
z%#vLa>QF0va`h!G%z=`&9;2|BS%Q6y68MXj{bg-iM#9uj!AD(8e^<9Psoxyvtukt3
zx^9MLUAPeJLLM6RG3f*|w0>e*0i*T@1P%C=@F(x|4{$MCN$z}5PAOTt+@fo}y}fQ2
zg*B1SMTEW#{-{5Ti{w#f2su=;=h5$TUB4dIn_TNyy~D|Xo2PtK&B+ID7qsOEQtjd!
zP&Kw=U?XiHs(=s2InrrCxpc#2;2J#G&H@4;$QDRqn3gDgNQq|(|Es_-h6r0Vvk(;*
z+6TN2wCp5~vZK+olZ1n`4{Cx26A@S}%&vfbM=|%$%^j}_Iggv<F}IDE1<Zeo^5O<{
z7SF4cK!QU4hhoPQ^W##@KXfNoq{;%SjT^M<CCuazzZp^-s4pqd229%jLs)2p$#kTo
z)2J-CQ6x1A@`w`%VP=59Mcr1&ylC=Rpx=N<1Ye*I>I6sz{4WE>nlX425_R6&?GE~f
zd_1}d+=vQHGSTD2^+sHb=(DD}9GkiWs{oB6C*nG31{xqEp!gD19aU%wtpeHL=vOUZ
z-iQGly0JJ+fD|aSWX}Dmfdp(RHJIU`le@P3#~vIvi7%8XGEh!o^X)}&UisfGa9HCZ
zG7Y#vyW$fa57DX5O?A)Hn1MNaqMPqWoGs;E9tH*mq=f{rp9v#Fd;6}n8LZ)X5CQ0>
zlli>#Q{*;bB7jB~R&65I;OS5ZzE=FD;{U1a+@oqv+diH&DU5Q8W|UGU%9%k*g-Iku
zNX|*o(>QcMqv${sMv0uJLWPi1<1nIxWUHLz7*e8SsFWe4{d}%w-gm9{UC&zYdi`T9
zYumrQ_wRRK_jP?w_phBtpmLL;A0)GwO6&>8fd=Ipv7sNI<AiRb)w>k8LY<ATLV}I>
zvir{a7ph6A1w)J^yaDT?okp0pD!>NU1ORXrchVPg1O;N47rP&28jy^AO**<zCUm24
z10Y$DXhwz5hAkg>QO?4_X7xnYEI^}z3ULimU^c|cy75gT+w(;OFEXHgvaV#j-A`Je
z{3wjpVq2n37@d5lM?kyHdzR8mm~OLQ@znb?&exWU^7HdIvY@*ds<FbjGhaiZrtqMh
z^VeEB(I0Wyk+{W!z5{k*c}V6RJu#fA35E~ud$YQPH#nxrQ;~!P>XnKJ0g(Zjo$BU3
z!n`Ap85^mmwXEt<E+r1NL85AxbdNS&hT0&a!X`8M*vwtDN|N2fvJzHHXvJ+)XU|3Q
zFW@>~yqYJ)^kfm{**tKWbOaiE7zBEM3aHU*!i9V+H>(lHV9$*Zc?!r8oI4J>f5u(1
zcz~8PZ7{0Q{w<M541NOP=eMEqkdh1|!#>)2l6XqiXf%C&J1`IW+k0>v-J(%AoPAVQ
z|M_!=8S~882KiI3FCBMnR?yy62K-!iw~qUNMu3+t@ALJWwlkFVCm*XQwvWo&X4i>&
z>D<$>{k3=TMXJ_X;Wf%;8#R{)t7b*74)_1N0^7Y0yZ%#%`>A@h-`mf<r*ZI6>&CkF
z!&bJLVqslzjnAWRzM_Sn#qwiSmuLD^g(tsFTt3I^v$}zql6@yv&Cf!|=+8YZbknq-
zcA@rm3JxilD6?S80bx&XzSs5n#qiWFwd0FILtj_r8=TFkpJ*p*=~}MU=E7=?)s80<
zFP&)EbG}b_=E;lCzuvh@*D<-}HQsgEY_o=w39U};`OC|lhRoE{1OL0s6NrZS`@h51
zMGEl0^@Sv^Tb|DT#i(T9<L`77n|`%CTyK8wm9F*7k5A4QO<3;SsI-Vp&ysy}o1c@X
zs=3~_tC6Qo&c<$DTcOOKu9p#e{rZldi~Ul@8e3>KHmV+LP#&qhShhFEb=MenA8#HE
zG^Ur?t-vG`nPfpAfNk?20R%neUQ#xa?|4N<Ma^f8Q?i+>fa#5g4(%L@XGmsohR$h(
zR|d{;A2{R4%JZKFD2+Xe-BO!fG<AEK+xf}5UuyhjDYp#i)~l+%g^zb{uSV<QEAipi
zzpu*koA9sq<Bss1_djm_ra3ftDb<hmD}t_6#pm^PUBPi2Q|8elicMK8H?cq)1cyYx
zVN%ysBu`LQCnE%ynfRVpt?xbX*7c7CGf!10T?(e8+NiXx)(tol6Rr{YNPT+H?MJVb
zDfi2)w`=>(DPayaeW!m-Zwwa@k^%AK2#sbod{J>}3z_E5@E|M?10@>>$?$>%G86+U
zGG%oY6rXk}r?4;%vDa<dL-$W9cb?V_2@Xn7*J?4Nm$GZ8QWGt;&*_hg9*_3ha>@J4
z!!?H+6n<MOhsvg@c-%a_`NXdwiq-eMzg9*SD4*R2K$Ms=736#}2EjRrF#@_RR9j;3
z2zSx4;e(B_w<n;_tdKbdJT!(oM}TSF$og}737ghE{BFDAzT>!KcUE6o*j?dvV7Bd$
zCsS%JoNQiuSUu`_U1|rN6FWb2tvS4WK_R6v@cQst$68T96D&ye{?>*8Lk4&i*i4CJ
zl2T5kdzz_XD84CoRmomr1E&EYVSR-{Q|(1vg;lSW@1_M?>Dc<6S?{*QZrvG;eMeFo
zZw`L(qS?Cx7a!c&th+<GbL*1Ed2RFqx<pVBUj7;OgEsxartyt^;M7F~i0p#=J8iZB
zY>r8Li;PT6kaMmDe@B@NYALCmn3Z~hmLwi9?c296f^1D2gszyWF3rk$@WYk3vcrKf
zi~7Cv2++z7`1zyS@xwlzPK~$1ZiPABIA0XSW#?7k&LiIm3BhGzCkdt}9jqCGORTY-
zhb`^F%}<825$`uMoY0W81cHGeTS1)P55`mkjbc23IoUP%-2=~pO`~59&pG6B=zZ@M
z9jXp(Q&RfwP7)gw1s<=F4H^XcA@nE&BujTl+5#IKGMljJM-MRXf<(_vb1g5*vc@E(
zzL$TIMIam*kn$+qCv@z_+uBfZ>B|{_c65uLDn6}w%%A)DtT~HQXi`D0UtLg`$kb8k
z(Yxu;hX3QRhTKWhZtA@#+0?6XXua}nSnRSy|M7F;D?NvESi`=Q0{p<2=iOc5f5W#i
zJtj*(vgJ^pp6hj={an(J<<LtYqz#tK#=Fi>bt~STKl5zN+UG875?t0i7@fWDW&b}d
zcT^qBmIimB<uXm<fe(N3uy^eLHcX?>mHpP2n@VwCr&+3Lf82kuc*(|(2R_=UXis?X
zvCYHgQW1AwP)oY!U0!&ii{r5G{l?e54fFW^dO^=h`|}k6XZ6`FfuWWs1sp8SUwy$e
zc$ki@{h9T7&!aN#bkokVnAHT@1P*JjQQFt^K99u0HPhM@(PN!!;WVrLgBydqw>juj
zb3T<Ha%|d~GPnLycbyzm(^q5)ey1S+P!F$YsfpD{CkK;2fF`jZFu7D$n(Hf_Qtr)d
zI?+MP{9KDsM_rQdd(#s~4~wm@7+W8&a_ULLg~3~MYa@-)LrTkPUofTtbd7cD`)q66
zloFSzg$mIBHn4>m?;?)5r0!z$!)BC|pZ|9I*w?<|u_Y>ul7#c5Vtt)a@Lekt;YR=x
zR7K{;l8+vmq)cdt*N;L5N2>c<JH4yDhqnzdVBVk%rd%mogm(%RY4N+S9uA!|5G>If
zB!LnC*Jm_Pj%#Bhi8#K-pQ0P$_nCAHd%B4+)K2g6sv2Xx{H)>sQp_J5*L9hOR(M1F
z?!`p5JV+RZ4}dav<#}W7!4=!!$@y8ZW34Pmd^*+XNtv1tU4jZj-alX5c=(jRf7p=S
zJLhId6OjFpqdZ{jR<5)Jx8t(}aSc&WSy^4UrV&GVV}W$7tIAf|&YwR&(J+@>D2j~L
z<;cb%!2Y&3(@~MjOY##R0`3tM)A7wGijk3FakcBO<26Qr8t}S+m0g5BH8HV1qTSWZ
z$<`zgyp49OJA?wYg=nIYK0Z~X_Z&M)|I2Q+*CiFG*x|Q9>nZJi1XL5M9hu`!F4#u8
zS^%b9c6#q;nZtjGb`iR!weEm$y0IEyS=HMdIDm(DT7}7!j>sZcqRbRM7BY0a?)Hr8
zvaew?!kDB*D-OCj8gg5I+1Y?nX_dLp3_Sq**-&<@YE_;K4}=XGhF*_O7>bha{?@=r
zlO~C!9k4A4E{-l#@5Oe7IFuP1TiP&Iun|=yx6Z0<>lDUDCNVsb&?>@?Ro}Fz<eY>r
z2eZ%pEHUKtYTBT90uoAeGk_gEo-quOv7D4}zVd<@3e}oOqf852CGJpJNr(pBnI{mi
zOhK7ykN0vt;IAAeKp^{H2eUKg!6L>1w}m2d&*0J4;pXzb=+?Uvm)1w#7dGw+lT!ol
zJCLi3&$|RL9aBLy9p?sME@wy<aY0J3KCGcJW0wKF$EV2T%uKp`Us&>LCZ~-k#OyQ-
zi7t1EdC5!`N+{Cdrd)as0T2)pWpW2Jb|F{nCY-bEINntT8iY&ebNRNTCQmMy_c(US
ze*2C*>?bf{yQjS<E*`;hq`Q|m2M{&7WMGh>g+J(E`QdO6C)S(<P?&DpfR+Mc`q0E=
zbw*QhM)6b)ub5Ezh_5z+eMs^|AyR<RG&bgpM7<-}9ULuPGQ{?N=l;`<8Y8_D)h}W+
z<jq)obr?QglN5)j3wQf!MtQL~4jNQDF(PQju!Ja(u_iulId9NS;mhGKOl-CoGGLiy
z&Y%PkxSng*dDWYm$;N=Gzs}y1<r<4;4wfY?{i4nS9x*gg)sT6@WFS3Hx!0^m?kivO
z3tVY4o<@}1vI=1ok+y<&#+HF&Tf5YJOJ5&`Ok%*KdU5Oi_@jth;v=RX{VVNDJctX+
zQ|2s0p-|#*@K}+ESNIUGc;$btZq+Rg{qXC8!hl8ls>bw}47a4j*vdm=49HC*eN?qh
z&yyC8hu^B?;QJel{InFUq|E*u7sqTrjzY1ysEF7#*TaR0OSV&T5d6Yc_7STLT?%gl
z;F8=Bqu?|hmy-!!zkZe29{$isMz8{))<H_pa;nrdSE~)obPhT+Xq=PN0w#I%YFkCj
z1Zo(=w2h+T8;A?~0aZ~{OTbo_cL~sm_Lp(R_V()nMRZA_NSTllNPYu5?<(W!?JiPW
zD6Ot!*pYJ}@G|S$YP+TfM5*lI6yvSvlJ0xwkVncQ>jzvclAGYq#VuHOwU3q#)dEkW
zR42Nm>RK%C6&xHa#RY%a2NY_>@83HDc=Jtz3KE~E(UlKCks%=nz?={RR}jCWk~)Ee
zoc0vpZ66P0v~AKKuq)72++O0V{UuozML{%rMEQ_#!W3y~uPIw~2eUJKqaCHI0B<V;
z*ptW(+6nUdXO#~X%OJd{G<<*_EKzPWiqsVa5fctu{@7kK3;Q@4pCvK_5E?)I;QCVE
z{&35*N9ef}3kM6Pf{A#|9j{W#VF@moym`^dU@w}00}T5LF6>IMAdd+-SXF-_HLa+6
zpNDYiDtbvrqVBj=*~IJe8G#5z90^*vfGC-0Th(TAx`FG3mFB>ba>JSClkR(yIph3W
z`D}uZocEO1aOM;HE4UE|142o$-h*q??RGSeLjTnLO%^jRl19rCqaL$%|AylWVs(y_
zZC7bCmMX;p#y_-2enMaHKaR=zplHORS@da{dl9Kh__-Ta73!DXvL(N8X<F96T@GD1
zKO?Qr!JflsGw9iGqB7m)pbkFRG9GpXi7Xp(+*cUXLy`*O!@8?Ka|1;aNA_gYpUEsa
zGBf?dnO7qz77DyFUA<awnf&6=&M`fP>myf)Ks$q|2HT&R=QOmrqX3V6e0>ecDP^{2
zR+mH?MRZpM#5{?8Z3uWKkp=rNvcq=RZfHp*OMs-WY<g=bC62X<Aod6hfED?H`{2yM
z2-q)UHFvTByy8~nRT3aV7JO&cryynm58)smS-pfIjGHAGheU}{Fr0s9<1pfl+O=&v
zg4dvP_JqnpQ`^JL{`KqE;++I7ChA3#rN==Gj5##+(g~@cyvv(43GiN{Wy>Ut>=Fk;
zr8FIQwELS8F$;E1_J;I%QC=R2Fn~%zOAJmUwlPsEQ%4<k_G<<wh7Nb<zy)onN-)s7
zgeVK;rpum*g@(u|j=36uC$!J3b7~hU&#d6nzh_aYP}YdfgiTOIxN`(}?K*apC?h;h
z-I3Ixo!Ws}-iQ5&q?BxApsjM2fZ2KtDt-Mr$t88#nT5I}Kwc$ghEc)gh^veV!YcuC
zi`k!DZznVXmjR>EMP1jO#48B3PLG3Wr@q^yj)@G#KwWuqw8WEwctMZogu?UsQl{$z
z7jz%{N4H9wea`fqCkf^hGsfSR5$ss~$kza*yD9Dyo-ca_Md9KkS+wV*b*yR;b>mrH
zA+lr8M1Eq`i|%QA@4bm#@{;TxaA7D&ygY6k0Dyc)fJ^E;Kca}(DQ4`XdJ-VOy$86p
z1l-D~xoII76>HCry-6fsSBg%|9VH+v#6)OA;5gpcP;{(wi4l=y%HunUYOAiL?|}Ug
zI}lqRr)T7gYxnI(xm}3DPTv0O_?)a`M`}=ubN0c0t_<z0ib_}I>9c1<Uf=@iWMYyM
z@gbegdKW(keDYoLFFbvZ#HA(&1_k-kj#4UBOFOyNl9r9i$WRU2BQK*!pa7eCX4;8O
zAw$YKOun3%9)Aua7Sa#8Q)-S1dutg6dej3<f3faiG}gBEX>kq*+%1Zax=4z%y{0eE
zd-u__bR;;*IPTUD|I1h+HqpcE<<OS3XJjsjyP*PuA)&?0@FLXl0>Tr^9Y6aWFa5ab
zUUy%PA3S&L{&m_T)2p7XY>Vu{niA$NZ2fP8G%@XS--Rgys1$luT!{!TKtl;=pu)BX
z{|5|5&OkZC0``c+G9<6u%5ZH6T+@2c@3W+>qK{!2#agZBKeH{861_UldWiCTD56;a
z<-8s}48uRf$0@&7zC%HSvKXQ3e!vY;gkY*Wea(9<EpHk41ZX-vo#dqgv`XH$$fpTz
zXKyC;A6DHeGJ4FGmN5Ya&WGmWIHTH$Ob8zq&$jF+qDf%!NX?Rwo3^$D<^No;mW(eI
zsVr~VwdC|9Sz(y1rm?+3*vO78n*>Q5zUWEV@eo5p2~$}Fe3qPK6x_%mkWI>7DhNO4
zgov*IPMEn0f#1|E(=Yii(P`IiH3d|p{_L_jxw&HxeOXB6WO>x#y^-#hY$T0rU29#E
z7TR+-8^J0-KwSy;OInykyTw@nVnP6TCNpX<aV%uFabwp_KPveWd1+(ruK8hOPy7Ar
zay@vYX4I(*FAU7BzD6RF4MKeT!C$aDl1smRyLu?LF251C@IvwUaSB~VAHvw_;`k3b
z8*S51q#QUvS;5zg1I(<If5(N{xVF=0FmSSLK;uRyPfXuh_o+X@wWNjZZE!>i%@Kte
z58V2>ab3U@j{%0^6G{Z>U<6?R;*s7k$aWFZD<V_m1c=3pkNy5&%%%ET*ao(!<0Ds@
zY^mKVCp|`ULfsgEXo(@-vN6XUpKUXYICdQpYEMnfZD>*<wQ3Sj{O3LLKcJh+7LWHe
Xv>dP1r<|iNRmR#n{&Z}l+v<M<fkdt!

diff --git a/dev/api.html b/dev/api.html
index 01849dc8..a4701eae 100644
--- a/dev/api.html
+++ b/dev/api.html
@@ -447,7 +447,6 @@
 <li class="toctree-l1"><a class="reference internal" href="generated/braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="generated/braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="generated/braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="generated/braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="generated/braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,22 +602,22 @@
 (<code class="docutils literal notranslate"><span class="pre">underscore_case</span></code> names) of Braindecode.</p>
 <nav class="contents local" id="contents">
 <ul class="simple">
-<li><p><a class="reference internal" href="#classifier" id="id14">Classifier</a></p></li>
-<li><p><a class="reference internal" href="#regressor" id="id15">Regressor</a></p></li>
-<li><p><a class="reference internal" href="#models" id="id16">Models</a></p></li>
-<li><p><a class="reference internal" href="#training" id="id17">Training</a></p></li>
-<li><p><a class="reference internal" href="#datasets" id="id18">Datasets</a></p></li>
-<li><p><a class="reference internal" href="#preprocessing" id="id19">Preprocessing</a></p></li>
-<li><p><a class="reference internal" href="#data-utils" id="id20">Data Utils</a></p></li>
-<li><p><a class="reference internal" href="#samplers" id="id21">Samplers</a></p></li>
-<li><p><a class="reference internal" href="#augmentation" id="id22">Augmentation</a></p></li>
-<li><p><a class="reference internal" href="#utils" id="id23">Utils</a></p></li>
-<li><p><a class="reference internal" href="#visualization" id="id24">Visualization</a></p></li>
+<li><p><a class="reference internal" href="#classifier" id="id37">Classifier</a></p></li>
+<li><p><a class="reference internal" href="#regressor" id="id38">Regressor</a></p></li>
+<li><p><a class="reference internal" href="#models" id="id39">Models</a></p></li>
+<li><p><a class="reference internal" href="#training" id="id40">Training</a></p></li>
+<li><p><a class="reference internal" href="#datasets" id="id41">Datasets</a></p></li>
+<li><p><a class="reference internal" href="#preprocessing" id="id42">Preprocessing</a></p></li>
+<li><p><a class="reference internal" href="#data-utils" id="id43">Data Utils</a></p></li>
+<li><p><a class="reference internal" href="#samplers" id="id44">Samplers</a></p></li>
+<li><p><a class="reference internal" href="#augmentation" id="id45">Augmentation</a></p></li>
+<li><p><a class="reference internal" href="#utils" id="id46">Utils</a></p></li>
+<li><p><a class="reference internal" href="#visualization" id="id47">Visualization</a></p></li>
 </ul>
 </nav>
 <p><a class="reference internal" href="#module-braindecode" title="braindecode"><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode</span></code></a>:</p>
 <span class="target" id="module-braindecode"></span><section id="classifier">
-<h2><a class="toc-backref" href="#id14" role="doc-backlink">Classifier</a><a class="headerlink" href="#classifier" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id37" role="doc-backlink">Classifier</a><a class="headerlink" href="#classifier" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.classifier</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -630,7 +629,7 @@ <h2><a class="toc-backref" href="#id14" role="doc-backlink">Classifier</a><a cla
 </div>
 </section>
 <section id="regressor">
-<h2><a class="toc-backref" href="#id15" role="doc-backlink">Regressor</a><a class="headerlink" href="#regressor" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id38" role="doc-backlink">Regressor</a><a class="headerlink" href="#regressor" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.regressor</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -642,7 +641,7 @@ <h2><a class="toc-backref" href="#id15" role="doc-backlink">Regressor</a><a clas
 </div>
 </section>
 <section id="models">
-<h2><a class="toc-backref" href="#id16" role="doc-backlink">Models</a><a class="headerlink" href="#models" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id39" role="doc-backlink">Models</a><a class="headerlink" href="#models" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.models.base</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -656,95 +655,92 @@ <h2><a class="toc-backref" href="#id16" role="doc-backlink">Models</a><a class="
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.ATCNet.html#braindecode.models.ATCNet" title="braindecode.models.ATCNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ATCNet</span></code></a>([n_chans, n_outputs, ...])</p></td>
-<td><p>ATCNet model from <a class="reference internal" href="generated/braindecode.models.ATCNet.html#r2ecdb73d6ab9-1" id="id2"><span>[R2ecdb73d6ab9-1]</span></a></p></td>
+<td><p>ATCNet model from Altaheri et al. (2022) <a class="reference internal" href="generated/braindecode.models.ATCNet.html#r2ecdb73d6ab9-1" id="id2"><span>[R2ecdb73d6ab9-1]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.AttentionBaseNet.html#braindecode.models.AttentionBaseNet" title="braindecode.models.AttentionBaseNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">AttentionBaseNet</span></code></a>([n_times, n_chans, ...])</p></td>
-<td><p>AttentionBaseNet.</p></td>
+<td><p>AttentionBaseNet from Wimpff M et al. (2023) <a class="reference internal" href="generated/braindecode.models.AttentionBaseNet.html#r523d6c831d64-martin2023" id="id3"><span>[R523d6c831d64-Martin2023]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.BIOT.html#braindecode.models.BIOT" title="braindecode.models.BIOT"><code class="xref py py-obj docutils literal notranslate"><span class="pre">BIOT</span></code></a>([emb_size, att_num_heads, n_layers, ...])</p></td>
-<td><p>BIOT: Cross-data Biosignal Learning in the Wild from <a class="reference internal" href="generated/braindecode.models.BIOT.html#r606e26b38fe6-yang2023" id="id3"><span>[R606e26b38fe6-Yang2023]</span></a></p></td>
+<td><p>BIOT from Yang et al. (2023) <a class="reference internal" href="generated/braindecode.models.BIOT.html#r606e26b38fe6-yang2023" id="id4"><span>[R606e26b38fe6-Yang2023]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.ContraWR.html#braindecode.models.ContraWR" title="braindecode.models.ContraWR"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ContraWR</span></code></a>(n_chans, n_outputs, sfreq, ...[, steps])</p></td>
-<td><p>Contrast with the World Representation (ContraWR) model <a class="reference internal" href="generated/braindecode.models.ContraWR.html#ra71465cb6797-yang2021" id="id4"><span>[Ra71465cb6797-Yang2021]</span></a>.</p></td>
+<td><p>Contrast with the World Representation ContraWR from Yang et al. 2021 <a class="reference internal" href="generated/braindecode.models.ContraWR.html#ra71465cb6797-yang2021" id="id5"><span>[Ra71465cb6797-Yang2021]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.Deep4Net.html#braindecode.models.Deep4Net" title="braindecode.models.Deep4Net"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Deep4Net</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>Deep ConvNet model from Schirrmeister et al 2017.</p></td>
+<td><p>Deep ConvNet model from Schirrmeister et al 2017 <a class="reference internal" href="generated/braindecode.models.Deep4Net.html#rb8ef6c2733ce-schirrmeister2017" id="id6"><span>[Rb8ef6c2733ce-Schirrmeister2017]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.DeepSleepNet.html#braindecode.models.DeepSleepNet" title="braindecode.models.DeepSleepNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DeepSleepNet</span></code></a>([n_outputs, return_feats, ...])</p></td>
-<td><p>Sleep staging architecture from Supratak et al 2017.</p></td>
+<td><p>Sleep staging architecture from Supratak et al. 2017 <a class="reference internal" href="generated/braindecode.models.DeepSleepNet.html#r28b528aca953-supratak2017" id="id7"><span>[R28b528aca953-Supratak2017]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.EEGConformer.html#braindecode.models.EEGConformer" title="braindecode.models.EEGConformer"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGConformer</span></code></a>([n_outputs, n_chans, ...])</p></td>
-<td><p>EEG Conformer.</p></td>
+<td><p>EEG Conformer from Song et al. (2022) from <a class="reference internal" href="generated/braindecode.models.EEGConformer.html#rd6c0fefc356a-song2022" id="id8"><span>[Rd6c0fefc356a-song2022]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.EEGInceptionERP.html#braindecode.models.EEGInceptionERP" title="braindecode.models.EEGInceptionERP"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGInceptionERP</span></code></a>([n_chans, n_outputs, ...])</p></td>
-<td><p>EEG Inception for ERP-based classification</p></td>
+<td><p>EEG Inception for ERP-based from Santamaria-Vazquez <a class="reference internal" href="generated/braindecode.models.EEGInceptionERP.html#r37c4761d4e92-santamaria2020" id="id9"><span>[R37c4761d4e92-santamaria2020]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.EEGInceptionMI.html#braindecode.models.EEGInceptionMI" title="braindecode.models.EEGInceptionMI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGInceptionMI</span></code></a>([n_chans, n_outputs, ...])</p></td>
-<td><p>EEG Inception for Motor Imagery, as proposed in <a class="reference internal" href="generated/braindecode.models.EEGInceptionMI.html#rc36ed781f4f5-1" id="id5"><span>[Rc36ed781f4f5-1]</span></a></p></td>
+<td><p>EEG Inception for Motor Imagery, as proposed in Zhang et al. (2021) <a class="reference internal" href="generated/braindecode.models.EEGInceptionMI.html#rc36ed781f4f5-1" id="id10"><span>[Rc36ed781f4f5-1]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.EEGITNet.html#braindecode.models.EEGITNet" title="braindecode.models.EEGITNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGITNet</span></code></a>([n_outputs, n_chans, n_times, ...])</p></td>
-<td><p>EEG-ITNet: An Explainable Inception Temporal</p></td>
+<td><p>EEG-ITNet from Salami, et al. <a class="reference internal" href="generated/braindecode.models.EEGITNet.html#r7fe571f46200-salami2022" id="id11"><span>[R7fe571f46200-Salami2022]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.EEGNetv1.html#braindecode.models.EEGNetv1" title="braindecode.models.EEGNetv1"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGNetv1</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>EEGNet model from Lawhern et al. 2016.</p></td>
+<td><p>EEGNet model from Lawhern et al. 2016 from <a class="reference internal" href="generated/braindecode.models.EEGNetv1.html#rcbe3da2652d4-eegnet" id="id12"><span>[Rcbe3da2652d4-EEGNet]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.EEGNetv4.html#braindecode.models.EEGNetv4" title="braindecode.models.EEGNetv4"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGNetv4</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>EEGNet v4 model from Lawhern et al 2018.</p></td>
+<td><p>EEGNet v4 model from Lawhern et al. 2018 <a class="reference internal" href="generated/braindecode.models.EEGNetv4.html#rbd7837e27d7f-eegnet4" id="id13"><span>[Rbd7837e27d7f-EEGNet4]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.EEGNeX.html#braindecode.models.EEGNeX" title="braindecode.models.EEGNeX"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGNeX</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>EEGNeX model from <a class="reference internal" href="generated/braindecode.models.EEGNeX.html#r60f8df15fd80-eegnex" id="id6"><span>[R60f8df15fd80-EEGNeX]</span></a>.</p></td>
+<td><p>EEGNeX model from Chen et al. (2024) <a class="reference internal" href="generated/braindecode.models.EEGNeX.html#r60f8df15fd80-eegnex" id="id14"><span>[R60f8df15fd80-eegnex]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.EEGResNet.html#braindecode.models.EEGResNet" title="braindecode.models.EEGResNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGResNet</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>Residual Network for EEG  from Schirrmeister et al 2017.</p></td>
+<td><p>EEGResNet from Schirrmeister et al. 2017 <a class="reference internal" href="generated/braindecode.models.EEGResNet.html#r625b4a01fbf7-schirrmeister2017" id="id15"><span>[R625b4a01fbf7-Schirrmeister2017]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.EEGSimpleConv.html#braindecode.models.EEGSimpleConv" title="braindecode.models.EEGSimpleConv"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGSimpleConv</span></code></a>([n_outputs, n_chans, sfreq, ...])</p></td>
-<td><p>EEGSimpleConv from <a class="reference internal" href="generated/braindecode.models.EEGSimpleConv.html#r5661533ddc63-yassine2023" id="id7"><span>[R5661533ddc63-Yassine2023]</span></a>.</p></td>
+<td><p>EEGSimpleConv from Ouahidi, YE et al. (2023) <a class="reference internal" href="generated/braindecode.models.EEGSimpleConv.html#r5661533ddc63-yassine2023" id="id16"><span>[R5661533ddc63-Yassine2023]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.EEGTCNet.html#braindecode.models.EEGTCNet" title="braindecode.models.EEGTCNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">EEGTCNet</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>EEGTCNet model combining EEGNet and TCN blocks.</p></td>
+<td><p>EEGTCNet model from Ingolfsson et al. (2020) <a class="reference internal" href="generated/braindecode.models.EEGTCNet.html#rc25b3d8a3a40-ingolfsson2020" id="id17"><span>[Rc25b3d8a3a40-ingolfsson2020]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.HybridNet.html#braindecode.models.HybridNet" title="braindecode.models.HybridNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">HybridNet</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>Hybrid ConvNet model from Schirrmeister et al 2017.</p></td>
+<td><p>Hybrid ConvNet model from Schirrmeister et al 2017  <a class="reference internal" href="generated/braindecode.models.HybridNet.html#r4d1af390a17e-schirrmeister2017" id="id18"><span>[R4d1af390a17e-Schirrmeister2017]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.Labram.html#braindecode.models.Labram" title="braindecode.models.Labram"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Labram</span></code></a>([n_times, n_outputs, chs_info, ...])</p></td>
-<td><p>Labram.</p></td>
+<td><p>Labram from <a class="reference internal" href="generated/braindecode.models.Labram.html#rb5cdfc6ea4fe-jiang2024" id="id19"><span>[Rb5cdfc6ea4fe-Jiang2024]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.ShallowFBCSPNet.html#braindecode.models.ShallowFBCSPNet" title="braindecode.models.ShallowFBCSPNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ShallowFBCSPNet</span></code></a>([n_chans, n_outputs, ...])</p></td>
-<td><p>Shallow ConvNet model from Schirrmeister et al 2017.</p></td>
+<td><p>Shallow ConvNet model from Schirrmeister et al. 2017 <a class="reference internal" href="generated/braindecode.models.ShallowFBCSPNet.html#r9432a19f6121-schirrmeister2017" id="id20"><span>[R9432a19f6121-Schirrmeister2017]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.SleepStagerBlanco2020.html#braindecode.models.SleepStagerBlanco2020" title="braindecode.models.SleepStagerBlanco2020"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SleepStagerBlanco2020</span></code></a>([n_chans, sfreq, ...])</p></td>
-<td><p>Sleep staging architecture from Blanco et al 2020.</p></td>
+<td><p>Sleep staging architecture from Blanco et al. 2020 from <a class="reference internal" href="generated/braindecode.models.SleepStagerBlanco2020.html#rb3eee9d9e81a-blanco2020" id="id21"><span>[Rb3eee9d9e81a-Blanco2020]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.SleepStagerChambon2018.html#braindecode.models.SleepStagerChambon2018" title="braindecode.models.SleepStagerChambon2018"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SleepStagerChambon2018</span></code></a>([n_chans, sfreq, ...])</p></td>
-<td><p>Sleep staging architecture from Chambon et al 2018.</p></td>
+<td><p>Sleep staging architecture from Chambon et al. 2018 <a class="reference internal" href="generated/braindecode.models.SleepStagerChambon2018.html#r89163c5eab6a-chambon2018" id="id22"><span>[R89163c5eab6a-Chambon2018]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.SleepStagerEldele2021.html#braindecode.models.SleepStagerEldele2021" title="braindecode.models.SleepStagerEldele2021"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SleepStagerEldele2021</span></code></a>([sfreq, n_tce, ...])</p></td>
-<td><p>Sleep Staging Architecture from Eldele et al 2021.</p></td>
+<td><p>Sleep Staging Architecture from Eldele et al. 2021 <a class="reference internal" href="generated/braindecode.models.SleepStagerEldele2021.html#r63c3502458ce-eldele2021" id="id23"><span>[R63c3502458ce-Eldele2021]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.SPARCNet.html#braindecode.models.SPARCNet" title="braindecode.models.SPARCNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SPARCNet</span></code></a>(n_chans, n_times, n_outputs, ...)</p></td>
-<td><p>Seizures, Periodic and Rhythmic pattern Continuum Neural Network (SPaRCNet) <a class="reference internal" href="generated/braindecode.models.SPARCNet.html#rf8eed20f8ca2-jing2023" id="id8"><span>[Rf8eed20f8ca2-jing2023]</span></a>.</p></td>
+<td><p>Seizures, Periodic and Rhythmic pattern Continuum Neural Network (SPaRCNet) from Jing et al. (2023) <a class="reference internal" href="generated/braindecode.models.SPARCNet.html#rf8eed20f8ca2-jing2023" id="id24"><span>[Rf8eed20f8ca2-jing2023]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.SyncNet.html#braindecode.models.SyncNet" title="braindecode.models.SyncNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SyncNet</span></code></a>([n_chans, n_times, n_outputs, ...])</p></td>
-<td><p>Synchronization Network (SyncNet) from <a class="reference internal" href="generated/braindecode.models.SyncNet.html#r5cdbe961b734-li2017" id="id9"><span>[R5cdbe961b734-Li2017]</span></a>.</p></td>
+<td><p>Synchronization Network (SyncNet) from <a class="reference internal" href="generated/braindecode.models.SyncNet.html#r5cdbe961b734-li2017" id="id25"><span>[R5cdbe961b734-Li2017]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.TCN.html#braindecode.models.TCN" title="braindecode.models.TCN"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TCN</span></code></a>([n_chans, n_outputs, n_blocks, ...])</p></td>
-<td><p>Temporal Convolutional Network (TCN) from Bai et al 2018.</p></td>
+<td><p>Temporal Convolutional Network (TCN) from Bai et al. 2018 <a class="reference internal" href="generated/braindecode.models.TCN.html#rcfca6ae7a220-bai2018" id="id26"><span>[Rcfca6ae7a220-Bai2018]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.TIDNet.html#braindecode.models.TIDNet" title="braindecode.models.TIDNet"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TIDNet</span></code></a>([n_chans, n_outputs, n_times, ...])</p></td>
-<td><p>Thinker Invariance DenseNet model from Kostas et al 2020.</p></td>
+<td><p>Thinker Invariance DenseNet model from Kostas et al. 2020 <a class="reference internal" href="generated/braindecode.models.TIDNet.html#re74dd80418c9-tidnet" id="id27"><span>[Re74dd80418c9-TIDNet]</span></a>.</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed" title="braindecode.models.TimeDistributed"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TimeDistributed</span></code></a>(module)</p></td>
-<td><p>Apply module on multiple windows.</p></td>
-</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.models.USleep.html#braindecode.models.USleep" title="braindecode.models.USleep"><code class="xref py py-obj docutils literal notranslate"><span class="pre">USleep</span></code></a>([n_chans, sfreq, depth, ...])</p></td>
-<td><p>Sleep staging architecture from Perslev et al 2021.</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.models.USleep.html#braindecode.models.USleep" title="braindecode.models.USleep"><code class="xref py py-obj docutils literal notranslate"><span class="pre">USleep</span></code></a>([n_chans, sfreq, depth, ...])</p></td>
+<td><p>Sleep staging architecture from Perslev et al. 2021 <a class="reference internal" href="generated/braindecode.models.USleep.html#r58a5e8182f0a-1" id="id28"><span>[R58a5e8182f0a-1]</span></a>.</p></td>
 </tr>
 </tbody>
 </table>
 </div>
 </section>
 <section id="training">
-<h2><a class="toc-backref" href="#id17" role="doc-backlink">Training</a><a class="headerlink" href="#training" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id40" role="doc-backlink">Training</a><a class="headerlink" href="#training" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.training</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -777,7 +773,7 @@ <h2><a class="toc-backref" href="#id17" role="doc-backlink">Training</a><a class
 </div>
 </section>
 <section id="datasets">
-<h2><a class="toc-backref" href="#id18" role="doc-backlink">Datasets</a><a class="headerlink" href="#datasets" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id41" role="doc-backlink">Datasets</a><a class="headerlink" href="#datasets" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.datasets</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -828,7 +824,7 @@ <h2><a class="toc-backref" href="#id18" role="doc-backlink">Datasets</a><a class
 </div>
 </section>
 <section id="preprocessing">
-<h2><a class="toc-backref" href="#id19" role="doc-backlink">Preprocessing</a><a class="headerlink" href="#preprocessing" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id42" role="doc-backlink">Preprocessing</a><a class="headerlink" href="#preprocessing" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.preprocessing</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -879,7 +875,7 @@ <h2><a class="toc-backref" href="#id19" role="doc-backlink">Preprocessing</a><a
 </div>
 </section>
 <section id="data-utils">
-<h2><a class="toc-backref" href="#id20" role="doc-backlink">Data Utils</a><a class="headerlink" href="#data-utils" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id43" role="doc-backlink">Data Utils</a><a class="headerlink" href="#data-utils" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.datautil</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -894,7 +890,7 @@ <h2><a class="toc-backref" href="#id20" role="doc-backlink">Data Utils</a><a cla
 </div>
 </section>
 <section id="samplers">
-<h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class="headerlink" href="#samplers" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id44" role="doc-backlink">Samplers</a><a class="headerlink" href="#samplers" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.samplers</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -905,7 +901,7 @@ <h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class
 <td><p>Sample sequences of consecutive windows.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.samplers.RelativePositioningSampler.html#braindecode.samplers.RelativePositioningSampler" title="braindecode.samplers.RelativePositioningSampler"><code class="xref py py-obj docutils literal notranslate"><span class="pre">RelativePositioningSampler</span></code></a>(metadata, ...[, ...])</p></td>
-<td><p>Sample examples for the relative positioning task from <a class="reference internal" href="generated/braindecode.samplers.RelativePositioningSampler.html#r0467437a2408-banville2020" id="id10"><span>[R0467437a2408-Banville2020]</span></a>.</p></td>
+<td><p>Sample examples for the relative positioning task from <a class="reference internal" href="generated/braindecode.samplers.RelativePositioningSampler.html#r0467437a2408-banville2020" id="id29"><span>[R0467437a2408-Banville2020]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.samplers.BalancedSequenceSampler.html#braindecode.samplers.BalancedSequenceSampler" title="braindecode.samplers.BalancedSequenceSampler"><code class="xref py py-obj docutils literal notranslate"><span class="pre">BalancedSequenceSampler</span></code></a>(metadata, n_windows)</p></td>
 <td><p>Balanced sampling of sequences of consecutive windows with categorical targets.</p></td>
@@ -915,7 +911,7 @@ <h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class
 </div>
 </section>
 <section id="augmentation">
-<span id="augmentation-api"></span><h2><a class="toc-backref" href="#id22" role="doc-backlink">Augmentation</a><a class="headerlink" href="#augmentation" title="Link to this heading">#</a></h2>
+<span id="augmentation-api"></span><h2><a class="toc-backref" href="#id45" role="doc-backlink">Augmentation</a><a class="headerlink" href="#augmentation" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.augmentation</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -938,7 +934,7 @@ <h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class
 <td><p>Flip the sign axis of each input with a given probability.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.augmentation.FTSurrogate.html#braindecode.augmentation.FTSurrogate" title="braindecode.augmentation.FTSurrogate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">FTSurrogate</span></code></a>(probability[, ...])</p></td>
-<td><p>FT surrogate augmentation of a single EEG channel, as proposed in <a class="reference internal" href="generated/braindecode.augmentation.FTSurrogate.html#ra7c6c14d9bd9-1" id="id11"><span>[Ra7c6c14d9bd9-1]</span></a>.</p></td>
+<td><p>FT surrogate augmentation of a single EEG channel, as proposed in <a class="reference internal" href="generated/braindecode.augmentation.FTSurrogate.html#ra7c6c14d9bd9-1" id="id30"><span>[Ra7c6c14d9bd9-1]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.augmentation.ChannelsShuffle.html#braindecode.augmentation.ChannelsShuffle" title="braindecode.augmentation.ChannelsShuffle"><code class="xref py py-obj docutils literal notranslate"><span class="pre">ChannelsShuffle</span></code></a>(probability[, p_shuffle, ...])</p></td>
 <td><p>Randomly shuffle channels in EEG data matrix.</p></td>
@@ -977,10 +973,10 @@ <h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class
 <td><p>Implements Iterator for Mixup for EEG data.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.augmentation.SegmentationReconstruction.html#braindecode.augmentation.SegmentationReconstruction" title="braindecode.augmentation.SegmentationReconstruction"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SegmentationReconstruction</span></code></a>(probability[, ...])</p></td>
-<td><p>Applies a segmentation-reconstruction transform to the input data, as</p></td>
+<td><p>Segmentation Reconstruction from Lotte (2015) <a class="reference internal" href="generated/braindecode.augmentation.SegmentationReconstruction.html#r78e7a66c7d6f-lotte2015" id="id31"><span>[R78e7a66c7d6f-Lotte2015]</span></a>.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.augmentation.MaskEncoding.html#braindecode.augmentation.MaskEncoding" title="braindecode.augmentation.MaskEncoding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MaskEncoding</span></code></a>(probability[, max_mask_ratio, ...])</p></td>
-<td><p>Replaces randomly chosen contiguous part (or parts) of all channels by zeros (if more than one segment, it may overlap).</p></td>
+<td><p>MaskEncoding from <a class="reference internal" href="generated/braindecode.augmentation.MaskEncoding.html#r9102599ed233-1" id="id32"><span>[R9102599ed233-1]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.augmentation.functional.identity.html#braindecode.augmentation.functional.identity" title="braindecode.augmentation.functional.identity"><code class="xref py py-obj docutils literal notranslate"><span class="pre">functional.identity</span></code></a>(X, y)</p></td>
 <td><p>Identity operation.</p></td>
@@ -992,7 +988,7 @@ <h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class
 <td><p>Flip the sign axis of each input.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.augmentation.functional.ft_surrogate.html#braindecode.augmentation.functional.ft_surrogate" title="braindecode.augmentation.functional.ft_surrogate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">functional.ft_surrogate</span></code></a>(X, y, ...[, ...])</p></td>
-<td><p>FT surrogate augmentation of a single EEG channel, as proposed in <a class="reference internal" href="generated/braindecode.augmentation.functional.ft_surrogate.html#r52a4658fffa7-1" id="id12"><span>[R52a4658fffa7-1]</span></a>.</p></td>
+<td><p>FT surrogate augmentation of a single EEG channel, as proposed in <a class="reference internal" href="generated/braindecode.augmentation.functional.ft_surrogate.html#r52a4658fffa7-1" id="id33"><span>[R52a4658fffa7-1]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.augmentation.functional.channels_dropout.html#braindecode.augmentation.functional.channels_dropout" title="braindecode.augmentation.functional.channels_dropout"><code class="xref py py-obj docutils literal notranslate"><span class="pre">functional.channels_dropout</span></code></a>(X, y, p_drop[, ...])</p></td>
 <td><p>Randomly set channels to flat signal.</p></td>
@@ -1022,17 +1018,17 @@ <h2><a class="toc-backref" href="#id21" role="doc-backlink">Samplers</a><a class
 <td><p>Mixes two channels of EEG data.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.augmentation.functional.segmentation_reconstruction.html#braindecode.augmentation.functional.segmentation_reconstruction" title="braindecode.augmentation.functional.segmentation_reconstruction"><code class="xref py py-obj docutils literal notranslate"><span class="pre">functional.segmentation_reconstruction</span></code></a>(X, y, ...)</p></td>
-<td><p>Segment and reconstruct EEG data in the time domain preserving labels.</p></td>
+<td><p>Segment and reconstruct EEG data from <a class="reference internal" href="generated/braindecode.augmentation.functional.segmentation_reconstruction.html#rc19448ba78ac-1" id="id34"><span>[Rc19448ba78ac-1]</span></a>.</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.augmentation.functional.mask_encoding.html#braindecode.augmentation.functional.mask_encoding" title="braindecode.augmentation.functional.mask_encoding"><code class="xref py py-obj docutils literal notranslate"><span class="pre">functional.mask_encoding</span></code></a>(X, y, time_start, ...)</p></td>
-<td><p>Replaces a contiguous part (or parts) of all channels by zeros (if more than one segment, it may overlap).</p></td>
+<td><p>Mark encoding from Ding et al. (2024) from <a class="reference internal" href="generated/braindecode.augmentation.functional.mask_encoding.html#re49696d5b28b-ding2024" id="id35"><span>[Re49696d5b28b-ding2024]</span></a>.</p></td>
 </tr>
 </tbody>
 </table>
 </div>
 </section>
 <section id="utils">
-<h2><a class="toc-backref" href="#id23" role="doc-backlink">Utils</a><a class="headerlink" href="#utils" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id46" role="doc-backlink">Utils</a><a class="headerlink" href="#utils" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.util</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -1044,7 +1040,7 @@ <h2><a class="toc-backref" href="#id23" role="doc-backlink">Utils</a><a class="h
 </div>
 </section>
 <section id="visualization">
-<h2><a class="toc-backref" href="#id24" role="doc-backlink">Visualization</a><a class="headerlink" href="#visualization" title="Link to this heading">#</a></h2>
+<h2><a class="toc-backref" href="#id47" role="doc-backlink">Visualization</a><a class="headerlink" href="#visualization" title="Link to this heading">#</a></h2>
 <p><code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.visualization</span></code>:</p>
 <div class="pst-scrollable-table-container"><table class="autosummary longtable table autosummary">
 <tbody>
@@ -1052,7 +1048,7 @@ <h2><a class="toc-backref" href="#id24" role="doc-backlink">Visualization</a><a
 <td><p></p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.visualization.plot_confusion_matrix.html#braindecode.visualization.plot_confusion_matrix" title="braindecode.visualization.plot_confusion_matrix"><code class="xref py py-obj docutils literal notranslate"><span class="pre">plot_confusion_matrix</span></code></a>(confusion_mat[, ...])</p></td>
-<td><p>Generates a confusion matrix with additional precision and sensitivity metrics as in <a class="reference internal" href="generated/braindecode.visualization.plot_confusion_matrix.html#r8046536b33dd-1" id="id13"><span>[R8046536b33dd-1]</span></a>.</p></td>
+<td><p>Generates a confusion matrix with additional precision and sensitivity metrics as in <a class="reference internal" href="generated/braindecode.visualization.plot_confusion_matrix.html#r8046536b33dd-1" id="id36"><span>[R8046536b33dd-1]</span></a>.</p></td>
 </tr>
 </tbody>
 </table>
diff --git a/dev/auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.html b/dev/auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.html
index 83e127ad..510c53e8 100644
--- a/dev/auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.html
+++ b/dev/auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.html
@@ -605,7 +605,7 @@ <h3>Preprocessing<a class="headerlink" href="#preprocessing" title="Link to this
 <a href="../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-function"><span class="n">preprocess</span></a><span class="p">(</span><a href="../../generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">test_set</span></a><span class="p">,</span> <span class="p">[</span><a href="../../generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-class"><span class="n">Preprocessor</span></a><span class="p">(</span><span class="s2">&quot;crop&quot;</span><span class="p">,</span> <span class="n">tmin</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">tmax</span><span class="o">=</span><span class="mi">24</span><span class="p">)],</span> <span class="n">n_jobs</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa045570ca0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a343dc0&gt;
 </pre></div>
 </div>
 <p>In time series targets setup, targets variables are stored in mne.Raw object as channels
@@ -842,14 +842,14 @@ <h2>Training<a class="headerlink" href="#training" title="Link to this heading">
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    r2_train    r2_valid    train_loss    valid_loss      lr     dur
 -------  ----------  ----------  ------------  ------------  ------  ------
-      1    -23.7826     -4.6087        1.8225       11.7419  0.0006  0.5356
-      2     -1.1990     -0.1716        1.5134        2.6475  0.0006  0.4562
-      3     -0.3654     -0.4985        1.2625        3.4645  0.0005  0.4686
-      4     -0.4383     -0.2731        1.2058        2.9438  0.0004  0.4497
-      5     -0.5982     -0.1512        1.1027        2.6529  0.0002  0.4739
-      6     -0.6090     -0.1255        1.1121        2.5886  0.0001  0.4488
-      7     -0.4455     -0.1445        0.9618        2.6339  0.0000  0.4512
-      8     -0.2790     -0.1755        1.0927        2.7063  0.0000  0.5093
+      1    -23.7826     -4.6087        1.8225       11.7419  0.0006  0.5310
+      2     -1.1990     -0.1716        1.5134        2.6475  0.0006  0.4736
+      3     -0.3654     -0.4985        1.2625        3.4645  0.0005  0.4671
+      4     -0.4383     -0.2731        1.2058        2.9438  0.0004  0.4621
+      5     -0.5982     -0.1512        1.1027        2.6529  0.0002  0.4680
+      6     -0.6090     -0.1255        1.1121        2.5886  0.0001  0.4514
+      7     -0.4455     -0.1445        0.9618        2.6339  0.0000  0.4753
+      8     -0.2790     -0.1755        1.0927        2.7063  0.0000  0.4502
 </pre></div>
 </div>
 <p>Obtaining predictions and targets for the test, train, and validation dataset</p>
@@ -970,8 +970,8 @@ <h2>Plot Results<a class="headerlink" href="#plot-results" title="Link to this h
 <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.tight_layout.html#matplotlib.pyplot.tight_layout" title="matplotlib.pyplot.tight_layout" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span></a><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_plot_bcic_iv_4_ecog_cropped_002.png" srcset="../../_images/sphx_glr_plot_bcic_iv_4_ecog_cropped_002.png" alt="plot bcic iv 4 ecog cropped" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (1 minutes 2.861 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1344 MB</p>
+<img src="../../_images/sphx_glr_plot_bcic_iv_4_ecog_cropped_002.png" srcset="../../_images/sphx_glr_plot_bcic_iv_4_ecog_cropped_002.png" alt="plot bcic iv 4 ecog cropped" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (1 minutes 5.215 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  1687 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-advanced-training-plot-bcic-iv-4-ecog-cropped-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/10fc813a8f78253f4bf301264950f5c1/plot_bcic_iv_4_ecog_cropped.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_bcic_iv_4_ecog_cropped.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/advanced_training/plot_data_augmentation.html b/dev/auto_examples/advanced_training/plot_data_augmentation.html
index bf426dad..5a4bbaef 100644
--- a/dev/auto_examples/advanced_training/plot_data_augmentation.html
+++ b/dev/auto_examples/advanced_training/plot_data_augmentation.html
@@ -599,7 +599,7 @@ <h3><a class="toc-backref" href="#id3" role="doc-backlink">Preprocessing</a><a c
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7fa044ed1a20&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f13521e10f0&gt;
 </pre></div>
 </div>
 </section>
@@ -793,10 +793,10 @@ <h3><a class="toc-backref" href="#id10" role="doc-backlink">Create an EEGClassif
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2639        1.4655       0.2639            0.2639        1.5266  0.0006  1.7685
-      2            0.3299        1.3119       0.3194            0.3194        1.3948  0.0005  1.6021
-      3            0.4757        1.1941       0.2986            0.2986        1.3259  0.0002  1.5993
-      4            0.5625        1.1671       0.3333            0.3333        1.3025  0.0000  1.5886
+      1            0.2639        1.4655       0.2639            0.2639        1.5266  0.0006  1.7965
+      2            0.3299        1.3119       0.3194            0.3194        1.3948  0.0005  1.5940
+      3            0.4757        1.1941       0.2986            0.2986        1.3259  0.0002  1.6496
+      4            0.5625        1.1671       0.3333            0.3333        1.3025  0.0000  1.6175
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=============================================================================================================================================
@@ -850,8 +850,8 @@ <h3><a class="toc-backref" href="#id12" role="doc-backlink">Setting the data aug
 <div class="highlight-Python notranslate"><div class="highlight"><pre><span></span><a href="../../generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">train_set</span></a><span class="o">.</span><a href="../../generated/braindecode.augmentation.FrequencyShift.html#braindecode.augmentation.FrequencyShift" title="braindecode.augmentation.FrequencyShift" class="sphx-glr-backref-module-braindecode-augmentation sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">transform</span></a> <span class="o">=</span> <a href="../../generated/braindecode.augmentation.Compose.html#braindecode.augmentation.Compose" title="braindecode.augmentation.Compose" class="sphx-glr-backref-module-braindecode-augmentation sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">composed_transforms</span></a>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 17.639 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1022 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 18.447 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  1131 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-advanced-training-plot-data-augmentation-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/1d879df548fa18be8c23d9ca0dc008d4/plot_data_augmentation.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_data_augmentation.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/advanced_training/plot_data_augmentation_search.html b/dev/auto_examples/advanced_training/plot_data_augmentation_search.html
index 36c80840..eb3b8327 100644
--- a/dev/auto_examples/advanced_training/plot_data_augmentation_search.html
+++ b/dev/auto_examples/advanced_training/plot_data_augmentation_search.html
@@ -620,7 +620,7 @@ <h3><a class="toc-backref" href="#id10" role="doc-backlink">Preprocessing</a><a
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f9f820894e0&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f135213a620&gt;
 </pre></div>
 </div>
 </section>
@@ -1389,8 +1389,8 @@ <h3><a class="toc-backref" href="#id19" role="doc-backlink">References</a><a cla
 Journal of Neural Engineering, 18(4), 046020.</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 33.063 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  886 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 34.659 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  830 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-advanced-training-plot-data-augmentation-search-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/2466f8ec5c733d0bd65e187b45d875cc/plot_data_augmentation_search.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_data_augmentation_search.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/advanced_training/plot_relative_positioning.html b/dev/auto_examples/advanced_training/plot_relative_positioning.html
index e50aa099..c81e42c4 100644
--- a/dev/auto_examples/advanced_training/plot_relative_positioning.html
+++ b/dev/auto_examples/advanced_training/plot_relative_positioning.html
@@ -606,7 +606,7 @@ <h3><a class="toc-backref" href="#id21" role="doc-backlink">Preprocessing</a><a
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7fa05c1fba60&gt;
+&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f129c847820&gt;
 </pre></div>
 </div>
 </section>
@@ -653,14 +653,14 @@ <h3><a class="toc-backref" href="#id23" role="doc-backlink">Preprocessing window
 <a href="../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-function"><span class="n">preprocess</span></a><span class="p">(</span><a href="../../generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">windows_dataset</span></a><span class="p">,</span> <span class="p">[</span><a href="../../generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-class"><span class="n">Preprocessor</span></a><span class="p">(</span><a href="https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.scale.html#sklearn.preprocessing.scale" title="sklearn.preprocessing.scale" class="sphx-glr-backref-module-sklearn-preprocessing sphx-glr-backref-type-py-function"><span class="n">standard_scale</span></a><span class="p">,</span> <span class="n">channel_wise</span><span class="o">=</span><span class="kc">True</span><span class="p">)])</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa0473916c0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f129c846ef0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa0473916c0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f129c846ef0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa0473916c0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f129c846ef0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 
-&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa044ef7760&gt;
+&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1352141a80&gt;
 </pre></div>
 </div>
 </section>
@@ -892,31 +892,31 @@ <h2><a class="toc-backref" href="#id27" role="doc-backlink">Training</a><a class
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_acc    train_loss    valid_acc    valid_loss    cp     dur
 -------  -----------  ------------  -----------  ------------  ----  ------
-      1       0.5234        0.7013       0.6680        0.6320     +  1.1358
-      2       0.5938        0.7149       0.4880        0.8358        0.8209
-      3       0.4922        1.0040       0.6440        0.6172     +  0.7909
-      4       0.5234        0.7031       0.6120        0.5990     +  0.8147
-      5       0.5391        0.6751       0.5920        0.6213        0.8221
-      6       0.6719        0.6227       0.5920        0.6263        0.8086
-      7       0.6562        0.6309       0.6240        0.6117        0.7945
-      8       0.6641        0.6272       0.6480        0.5950     +  0.8155
-      9       0.6328        0.6238       0.6680        0.5797     +  0.8089
-     10       0.6406        0.6177       0.6800        0.5746     +  0.8038
-     11       0.6250        0.6323       0.7040        0.5787        0.8033
-     12       0.6094        0.6281       0.6760        0.5772        0.7886
-     13       0.6328        0.6422       0.6880        0.5790        0.8100
-     14       0.6406        0.5920       0.6840        0.5765        0.8095
-     15       0.6562        0.6170       0.6920        0.5730     +  0.8012
-     16       0.7578        0.5608       0.6960        0.5676     +  0.7876
-     17       0.6875        0.5936       0.7120        0.5612     +  0.8068
-     18       0.7734        0.5472       0.7080        0.5500     +  0.8013
-     19       0.7656        0.5245       0.7120        0.5400     +  0.8013
-     20       0.6641        0.5641       0.7160        0.5333     +  0.7931
-     21       0.7422        0.5307       0.7200        0.5272     +  0.8039
-     22       0.7109        0.5499       0.7360        0.5211     +  0.8103
-     23       0.6250        0.6259       0.7400        0.5164     +  0.8370
-     24       0.7031        0.5712       0.7400        0.5120     +  0.8025
-     25       0.7109        0.5030       0.7280        0.5120        0.7955
+      1       0.5234        0.7013       0.6680        0.6320     +  1.1900
+      2       0.5938        0.7149       0.4880        0.8358        0.8087
+      3       0.4922        1.0040       0.6440        0.6172     +  0.8263
+      4       0.5234        0.7031       0.6120        0.5990     +  0.8165
+      5       0.5391        0.6751       0.5920        0.6213        0.8100
+      6       0.6719        0.6227       0.5920        0.6263        0.7994
+      7       0.6562        0.6309       0.6240        0.6117        0.8097
+      8       0.6641        0.6272       0.6480        0.5950     +  0.8105
+      9       0.6328        0.6238       0.6680        0.5797     +  0.8078
+     10       0.6406        0.6177       0.6800        0.5746     +  0.7904
+     11       0.6250        0.6323       0.7040        0.5787        0.8022
+     12       0.6094        0.6281       0.6760        0.5772        0.8122
+     13       0.6328        0.6422       0.6880        0.5790        0.8004
+     14       0.6406        0.5920       0.6840        0.5765        0.7808
+     15       0.6562        0.6170       0.6920        0.5730     +  0.7964
+     16       0.7578        0.5608       0.6960        0.5676     +  0.8059
+     17       0.6875        0.5936       0.7120        0.5612     +  0.8001
+     18       0.7734        0.5472       0.7080        0.5500     +  0.7944
+     19       0.7656        0.5245       0.7120        0.5400     +  0.8143
+     20       0.6641        0.5641       0.7160        0.5333     +  0.8053
+     21       0.7422        0.5307       0.7200        0.5272     +  0.7993
+     22       0.7109        0.5499       0.7360        0.5211     +  0.7896
+     23       0.6250        0.6259       0.7400        0.5164     +  0.7898
+     24       0.7031        0.5712       0.7400        0.5120     +  0.8070
+     25       0.7109        0.5030       0.7280        0.5120        0.7910
 /home/runner/.local/lib/python3.10/site-packages/skorch/net.py:2626: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don&#39;t have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
   return torch.load(f_name, map_location=map_location)
 </pre></div>
@@ -1102,7 +1102,7 @@ <h3><a class="toc-backref" href="#id30" role="doc-backlink">Using the learned re
 <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.legend.html#matplotlib.axes.Axes.legend" title="matplotlib.axes.Axes.legend" class="sphx-glr-backref-module-matplotlib-axes sphx-glr-backref-type-py-method"><span class="n">ax</span><span class="o">.</span><span class="n">legend</span></a><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_plot_relative_positioning_002.png" srcset="../../_images/sphx_glr_plot_relative_positioning_002.png" alt="plot relative positioning" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;matplotlib.legend.Legend object at 0x7fa044ed28c0&gt;
+<img src="../../_images/sphx_glr_plot_relative_positioning_002.png" srcset="../../_images/sphx_glr_plot_relative_positioning_002.png" alt="plot relative positioning" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;matplotlib.legend.Legend object at 0x7f1354d0fac0&gt;
 </pre></div>
 </div>
 <p>We see that there is sleep stage-related structure in the embedding. A
@@ -1159,8 +1159,8 @@ <h2><a class="toc-backref" href="#id32" role="doc-backlink">References</a><a cla
 (758-769)</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (2 minutes 12.090 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  730 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (1 minutes 55.988 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  708 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-advanced-training-plot-relative-positioning-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/aa8426d97090e7b3062c4e4732c3214a/plot_relative_positioning.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_relative_positioning.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/advanced_training/sg_execution_times.html b/dev/auto_examples/advanced_training/sg_execution_times.html
index 05143c99..9a22ad8c 100644
--- a/dev/auto_examples/advanced_training/sg_execution_times.html
+++ b/dev/auto_examples/advanced_training/sg_execution_times.html
@@ -449,7 +449,7 @@
   
   <section id="computation-times">
 <span id="sphx-glr-auto-examples-advanced-training-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Link to this heading">#</a></h1>
-<p><strong>04:05.653</strong> total execution time for 4 files <strong>from auto_examples/advanced_training</strong>:</p>
+<p><strong>03:54.308</strong> total execution time for 4 files <strong>from auto_examples/advanced_training</strong>:</p>
 <div class="docutils container">
 <style scoped>
 <link href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css" rel="stylesheet" />
@@ -471,20 +471,20 @@
 </thead>
 <tbody>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_relative_positioning.html#sphx-glr-auto-examples-advanced-training-plot-relative-positioning-py"><span class="std std-ref">Self-supervised learning on EEG with relative positioning</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_relative_positioning.py</span></code>)</p></td>
-<td><p>02:12.090</p></td>
-<td><p>730.1</p></td>
+<td><p>01:55.988</p></td>
+<td><p>707.7</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_bcic_iv_4_ecog_cropped.html#sphx-glr-auto-examples-advanced-training-plot-bcic-iv-4-ecog-cropped-py"><span class="std std-ref">Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_bcic_iv_4_ecog_cropped.py</span></code>)</p></td>
-<td><p>01:02.861</p></td>
-<td><p>1343.8</p></td>
+<td><p>01:05.215</p></td>
+<td><p>1687.3</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_data_augmentation_search.html#sphx-glr-auto-examples-advanced-training-plot-data-augmentation-search-py"><span class="std std-ref">Searching the best data augmentation on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_data_augmentation_search.py</span></code>)</p></td>
-<td><p>00:33.063</p></td>
-<td><p>885.9</p></td>
+<td><p>00:34.659</p></td>
+<td><p>829.9</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_data_augmentation.html#sphx-glr-auto-examples-advanced-training-plot-data-augmentation-py"><span class="std std-ref">Data Augmentation on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_data_augmentation.py</span></code>)</p></td>
-<td><p>00:17.639</p></td>
-<td><p>1022.4</p></td>
+<td><p>00:18.447</p></td>
+<td><p>1131.3</p></td>
 </tr>
 </tbody>
 </table>
diff --git a/dev/auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.html b/dev/auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.html
index c2b7db67..9ae5d832 100644
--- a/dev/auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.html
+++ b/dev/auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.html
@@ -585,7 +585,7 @@ <h3>Preprocessing<a class="headerlink" href="#preprocessing" title="Link to this
 <div class="highlight-Python notranslate"><div class="highlight"><pre><span></span><a href="../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-function"><span class="n">preprocess</span></a><span class="p">(</span><a href="../../generated/braindecode.datasets.BCICompetitionIVDataset4.html#braindecode.datasets.BCICompetitionIVDataset4" title="braindecode.datasets.BCICompetitionIVDataset4" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">dataset</span></a><span class="p">,</span> <span class="p">[</span><a href="../../generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-class"><span class="n">Preprocessor</span></a><span class="p">(</span><span class="s2">&quot;crop&quot;</span><span class="p">,</span> <span class="n">tmin</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">tmax</span><span class="o">=</span><span class="mi">30</span><span class="p">)])</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.bcicomp.BCICompetitionIVDataset4 object at 0x7fa04530aad0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.bcicomp.BCICompetitionIVDataset4 object at 0x7f1354c2c790&gt;
 </pre></div>
 </div>
 <p>In time series targets setup, targets variables are stored in mne.Raw object as channels
@@ -794,8 +794,8 @@ <h2>Training<a class="headerlink" href="#training" title="Link to this heading">
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_loss    train_pearson_r    train_r2    valid_loss    valid_pearson_r    valid_r2      lr     dur
 -------  ------------  -----------------  ----------  ------------  -----------------  ----------  ------  ------
-      1        1.9859             0.0806     -0.8304        5.0944            -0.0381     -1.3224  0.0006  6.4970
-      2        1.2818             0.3930     -0.0261        4.1415            -0.0461     -0.8881  0.0000  6.3359
+      1        1.9859             0.0806     -0.8304        5.0944            -0.0381     -1.3224  0.0006  6.5104
+      2        1.2818             0.3930     -0.0261        4.1415            -0.0461     -0.8881  0.0000  6.2912
 </pre></div>
 </div>
 <p>Obtaining predictions and targets for the test, train, and validation dataset</p>
@@ -910,8 +910,8 @@ <h2>Plot Results<a class="headerlink" href="#plot-results" title="Link to this h
 <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.tight_layout.html#matplotlib.pyplot.tight_layout" title="matplotlib.pyplot.tight_layout" class="sphx-glr-backref-module-matplotlib-pyplot sphx-glr-backref-type-py-function"><span class="n">plt</span><span class="o">.</span><span class="n">tight_layout</span></a><span class="p">()</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_plot_bcic_iv_4_ecog_trial_002.png" srcset="../../_images/sphx_glr_plot_bcic_iv_4_ecog_trial_002.png" alt="plot bcic iv 4 ecog trial" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 26.059 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  735 MB</p>
+<img src="../../_images/sphx_glr_plot_bcic_iv_4_ecog_trial_002.png" srcset="../../_images/sphx_glr_plot_bcic_iv_4_ecog_trial_002.png" alt="plot bcic iv 4 ecog trial" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 26.037 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  837 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-applied-examples-plot-bcic-iv-4-ecog-trial-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/a7ccc5c1d1d2775e08c053bb25c81a91/plot_bcic_iv_4_ecog_trial.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_bcic_iv_4_ecog_trial.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/applied_examples/plot_sleep_staging_chambon2018.html b/dev/auto_examples/applied_examples/plot_sleep_staging_chambon2018.html
index eb932967..b5e6cac2 100644
--- a/dev/auto_examples/applied_examples/plot_sleep_staging_chambon2018.html
+++ b/dev/auto_examples/applied_examples/plot_sleep_staging_chambon2018.html
@@ -562,7 +562,7 @@ <h3>Preprocessing<a class="headerlink" href="#preprocessing" title="Link to this
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f9f82089570&gt;
+&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f128f761480&gt;
 </pre></div>
 </div>
 </section>
@@ -605,12 +605,12 @@ <h3>Window preprocessing<a class="headerlink" href="#window-preprocessing" title
 <a href="../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-function"><span class="n">preprocess</span></a><span class="p">(</span><a href="../../generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">windows_dataset</span></a><span class="p">,</span> <span class="p">[</span><a href="../../generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-class"><span class="n">Preprocessor</span></a><span class="p">(</span><a href="https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.scale.html#sklearn.preprocessing.scale" title="sklearn.preprocessing.scale" class="sphx-glr-backref-module-sklearn-preprocessing sphx-glr-backref-type-py-function"><span class="n">standard_scale</span></a><span class="p">,</span> <span class="n">channel_wise</span><span class="o">=</span><span class="kc">True</span><span class="p">)])</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa044ef5600&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f128dafb400&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa044ef5600&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f128dafb400&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 
-&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa044ee1bd0&gt;
+&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f129c845e40&gt;
 </pre></div>
 </div>
 </section>
@@ -690,7 +690,7 @@ <h2>Create model<a class="headerlink" href="#create-model" title="Link to this h
 <div class="highlight-Python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">torch</span>
 <span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
 <span class="kn">from</span> <span class="nn">braindecode.util</span> <span class="kn">import</span> <a href="../../generated/braindecode.util.set_random_seeds.html#braindecode.util.set_random_seeds" title="braindecode.util.set_random_seeds" class="sphx-glr-backref-module-braindecode-util sphx-glr-backref-type-py-function"><span class="n">set_random_seeds</span></a>
-<span class="kn">from</span> <span class="nn">braindecode.models</span> <span class="kn">import</span> <a href="../../generated/braindecode.models.SleepStagerChambon2018.html#braindecode.models.SleepStagerChambon2018" title="braindecode.models.SleepStagerChambon2018" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">SleepStagerChambon2018</span></a><span class="p">,</span> <a href="../../generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed" title="braindecode.models.TimeDistributed" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a>
+<span class="kn">from</span> <span class="nn">braindecode.models</span> <span class="kn">import</span> <a href="../../generated/braindecode.models.SleepStagerChambon2018.html#braindecode.models.SleepStagerChambon2018" title="braindecode.models.SleepStagerChambon2018" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">SleepStagerChambon2018</span></a><span class="p">,</span> <a href="https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a>
 
 <a href="https://docs.python.org/3/library/functions.html#bool" title="builtins.bool" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">cuda</span></a> <span class="o">=</span> <a href="https://pytorch.org/docs/stable/generated/torch.cuda.is_available.html#torch.cuda.is_available" title="torch.cuda.is_available" class="sphx-glr-backref-module-torch-cuda sphx-glr-backref-type-py-function"><span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span></a><span class="p">()</span>  <span class="c1"># check if GPU is available</span>
 <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">device</span></a> <span class="o">=</span> <span class="s2">&quot;cuda&quot;</span> <span class="k">if</span> <a href="https://pytorch.org/docs/stable/generated/torch.cuda.is_available.html#torch.cuda.is_available" title="torch.cuda.is_available" class="sphx-glr-backref-module-torch-cuda sphx-glr-backref-type-py-function"><span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span></a><span class="p">()</span> <span class="k">else</span> <span class="s2">&quot;cpu&quot;</span>
@@ -717,7 +717,7 @@ <h2>Create model<a class="headerlink" href="#create-model" title="Link to this h
 <span class="p">)</span>
 
 <a href="https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential" title="torch.nn.Sequential" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">model</span></a> <span class="o">=</span> <a href="https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential" title="torch.nn.Sequential" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span></a><span class="p">(</span>
-    <a href="../../generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed" title="braindecode.models.TimeDistributed" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a><span class="p">(</span><a href="../../generated/braindecode.models.SleepStagerChambon2018.html#braindecode.models.SleepStagerChambon2018" title="braindecode.models.SleepStagerChambon2018" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">feat_extractor</span></a><span class="p">),</span>  <span class="c1"># apply model on each 30-s window</span>
+    <a href="https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a><span class="p">(</span><a href="../../generated/braindecode.models.SleepStagerChambon2018.html#braindecode.models.SleepStagerChambon2018" title="braindecode.models.SleepStagerChambon2018" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">feat_extractor</span></a><span class="p">),</span>  <span class="c1"># apply model on each 30-s window</span>
     <a href="https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential" title="torch.nn.Sequential" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span></a><span class="p">(</span>  <span class="c1"># apply linear layer on concatenated feature vectors</span>
         <a href="https://pytorch.org/docs/stable/generated/torch.nn.Flatten.html#torch.nn.Flatten" title="torch.nn.Flatten" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Flatten</span></a><span class="p">(</span><span class="n">start_dim</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
         <a href="https://pytorch.org/docs/stable/generated/torch.nn.Dropout.html#torch.nn.Dropout" title="torch.nn.Dropout" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Dropout</span></a><span class="p">(</span><span class="mf">0.5</span><span class="p">),</span>
@@ -790,16 +790,16 @@ <h2>Training<a class="headerlink" href="#training" title="Link to this heading">
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_bal_acc    train_loss    valid_acc    valid_bal_acc    valid_loss     dur
 -------  ---------------  ------------  -----------  ---------------  ------------  ------
-      1           0.2136        1.5768       0.0888           0.2000        1.6372  1.4298
-      2           0.2036        1.4788       0.0888           0.2000        1.6676  1.3448
-      3           0.2324        1.4033       0.0966           0.2102        1.6337  1.3427
-      4           0.2888        1.3407       0.1149           0.2465        1.6790  1.3615
-      5           0.3993        1.2126       0.4517           0.4013        1.6235  1.3533
-      6           0.5294        1.0967       0.2768           0.4076        1.6179  1.3581
-      7           0.5755        0.9662       0.5927           0.5671        1.3689  1.3662
-      8           0.6251        0.8904       0.7076           0.5786        1.2952  1.3566
-      9           0.6877        0.8148       0.7154           0.5876        1.3450  1.3446
-     10           0.6860        0.7449       0.5196           0.5269        1.6322  1.3615
+      1           0.2136        1.5768       0.0888           0.2000        1.6372  1.4637
+      2           0.2036        1.4788       0.0888           0.2000        1.6676  1.3394
+      3           0.2324        1.4033       0.0966           0.2102        1.6337  1.3253
+      4           0.2888        1.3407       0.1149           0.2465        1.6790  1.3434
+      5           0.3993        1.2126       0.4517           0.4013        1.6235  1.3363
+      6           0.5294        1.0967       0.2768           0.4076        1.6179  1.3380
+      7           0.5755        0.9662       0.5927           0.5671        1.3689  1.3504
+      8           0.6251        0.8904       0.7076           0.5786        1.2952  1.3362
+      9           0.6877        0.8148       0.7154           0.5876        1.3450  1.3429
+     10           0.6860        0.7449       0.5196           0.5269        1.6322  1.3382
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=Sequential(
@@ -934,7 +934,7 @@ <h2>References<a class="headerlink" href="#references" title="Link to this headi
 Circulation 101(23):e215-e220</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (3 minutes 42.544 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (3 minutes 6.130 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-applied-examples-plot-sleep-staging-chambon2018-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/applied_examples/plot_sleep_staging_eldele2021.html b/dev/auto_examples/applied_examples/plot_sleep_staging_eldele2021.html
index 772935fc..95b90580 100644
--- a/dev/auto_examples/applied_examples/plot_sleep_staging_eldele2021.html
+++ b/dev/auto_examples/applied_examples/plot_sleep_staging_eldele2021.html
@@ -564,7 +564,7 @@ <h3>Preprocessing<a class="headerlink" href="#preprocessing" title="Link to this
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f9f8f33b460&gt;
+&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f1351a5c850&gt;
 </pre></div>
 </div>
 </section>
@@ -614,7 +614,7 @@ <h3>Window preprocessing<a class="headerlink" href="#window-preprocessing" title
 <a href="../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-function"><span class="n">preprocess</span></a><span class="p">(</span><a href="../../generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">windows_dataset</span></a><span class="p">,</span> <span class="p">[</span><a href="../../generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-class"><span class="n">Preprocessor</span></a><span class="p">(</span><a href="https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.scale.html#sklearn.preprocessing.scale" title="sklearn.preprocessing.scale" class="sphx-glr-backref-module-sklearn-preprocessing sphx-glr-backref-type-py-function"><span class="n">standard_scale</span></a><span class="p">,</span> <span class="n">channel_wise</span><span class="o">=</span><span class="kc">True</span><span class="p">)])</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f9f8f339570&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1351a5e9e0&gt;
 </pre></div>
 </div>
 </section>
@@ -696,7 +696,7 @@ <h2>Create model<a class="headerlink" href="#create-model" title="Link to this h
 <div class="highlight-Python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">torch</span>
 <span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
 <span class="kn">from</span> <span class="nn">braindecode.util</span> <span class="kn">import</span> <a href="../../generated/braindecode.util.set_random_seeds.html#braindecode.util.set_random_seeds" title="braindecode.util.set_random_seeds" class="sphx-glr-backref-module-braindecode-util sphx-glr-backref-type-py-function"><span class="n">set_random_seeds</span></a>
-<span class="kn">from</span> <span class="nn">braindecode.models</span> <span class="kn">import</span> <a href="../../generated/braindecode.models.SleepStagerEldele2021.html#braindecode.models.SleepStagerEldele2021" title="braindecode.models.SleepStagerEldele2021" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">SleepStagerEldele2021</span></a><span class="p">,</span> <a href="../../generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed" title="braindecode.models.TimeDistributed" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a>
+<span class="kn">from</span> <span class="nn">braindecode.models</span> <span class="kn">import</span> <a href="../../generated/braindecode.models.SleepStagerEldele2021.html#braindecode.models.SleepStagerEldele2021" title="braindecode.models.SleepStagerEldele2021" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">SleepStagerEldele2021</span></a><span class="p">,</span> <a href="https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a>
 
 <a href="https://docs.python.org/3/library/functions.html#bool" title="builtins.bool" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">cuda</span></a> <span class="o">=</span> <a href="https://pytorch.org/docs/stable/generated/torch.cuda.is_available.html#torch.cuda.is_available" title="torch.cuda.is_available" class="sphx-glr-backref-module-torch-cuda sphx-glr-backref-type-py-function"><span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span></a><span class="p">()</span>  <span class="c1"># check if GPU is available</span>
 <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">device</span></a> <span class="o">=</span> <span class="s2">&quot;cuda&quot;</span> <span class="k">if</span> <a href="https://pytorch.org/docs/stable/generated/torch.cuda.is_available.html#torch.cuda.is_available" title="torch.cuda.is_available" class="sphx-glr-backref-module-torch-cuda sphx-glr-backref-type-py-function"><span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span></a><span class="p">()</span> <span class="k">else</span> <span class="s2">&quot;cpu&quot;</span>
@@ -717,7 +717,7 @@ <h2>Create model<a class="headerlink" href="#create-model" title="Link to this h
 <span class="p">)</span>
 
 <a href="https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential" title="torch.nn.Sequential" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">model</span></a> <span class="o">=</span> <a href="https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential" title="torch.nn.Sequential" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span></a><span class="p">(</span>
-    <a href="../../generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed" title="braindecode.models.TimeDistributed" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a><span class="p">(</span><a href="../../generated/braindecode.models.SleepStagerEldele2021.html#braindecode.models.SleepStagerEldele2021" title="braindecode.models.SleepStagerEldele2021" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">feat_extractor</span></a><span class="p">),</span>  <span class="c1"># apply model on each 30-s window</span>
+    <a href="https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">TimeDistributed</span></a><span class="p">(</span><a href="../../generated/braindecode.models.SleepStagerEldele2021.html#braindecode.models.SleepStagerEldele2021" title="braindecode.models.SleepStagerEldele2021" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">feat_extractor</span></a><span class="p">),</span>  <span class="c1"># apply model on each 30-s window</span>
     <a href="https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential" title="torch.nn.Sequential" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span></a><span class="p">(</span>  <span class="c1"># apply linear layer on concatenated feature vectors</span>
         <a href="https://pytorch.org/docs/stable/generated/torch.nn.Flatten.html#torch.nn.Flatten" title="torch.nn.Flatten" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Flatten</span></a><span class="p">(</span><span class="n">start_dim</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
         <a href="https://pytorch.org/docs/stable/generated/torch.nn.Dropout.html#torch.nn.Dropout" title="torch.nn.Dropout" class="sphx-glr-backref-module-torch-nn sphx-glr-backref-type-py-class"><span class="n">nn</span><span class="o">.</span><span class="n">Dropout</span></a><span class="p">(</span><span class="mf">0.5</span><span class="p">),</span>
@@ -782,9 +782,9 @@ <h2>Training<a class="headerlink" href="#training" title="Link to this heading">
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_bal_acc    train_loss    valid_acc    valid_bal_acc    valid_loss     dur
 -------  ---------------  ------------  -----------  ---------------  ------------  ------
-      1           0.1471        3.1811       0.3459           0.1795        3.4760  2.3002
-      2           0.2781        1.8815       0.1955           0.2186        2.1547  1.9730
-      3           0.4518        1.4929       0.2331           0.2295        4.1885  1.9633
+      1           0.1471        3.1811       0.3459           0.1795        3.4760  2.2511
+      2           0.2781        1.8815       0.1955           0.2186        2.1547  1.9752
+      3           0.4518        1.4929       0.2331           0.2295        4.1885  1.9404
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=Sequential(
@@ -1027,7 +1027,7 @@ <h2>References<a class="headerlink" href="#references" title="Link to this headi
 Circulation 101(23):e215-e220</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 13.159 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 13.021 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  635 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-applied-examples-plot-sleep-staging-eldele2021-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/applied_examples/plot_sleep_staging_usleep.html b/dev/auto_examples/applied_examples/plot_sleep_staging_usleep.html
index ef323fd5..c29a41f8 100644
--- a/dev/auto_examples/applied_examples/plot_sleep_staging_usleep.html
+++ b/dev/auto_examples/applied_examples/plot_sleep_staging_usleep.html
@@ -567,7 +567,7 @@ <h3>Preprocessing<a class="headerlink" href="#preprocessing" title="Link to this
 <a href="../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess" class="sphx-glr-backref-module-braindecode-preprocessing sphx-glr-backref-type-py-function"><span class="n">preprocess</span></a><span class="p">(</span><a href="../../generated/braindecode.datasets.SleepPhysionet.html#braindecode.datasets.SleepPhysionet" title="braindecode.datasets.SleepPhysionet" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">dataset</span></a><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">preprocessors</span></a><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f9f7b4c6fb0&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;braindecode.datasets.sleep_physionet.SleepPhysionet object at 0x7f128f32f9a0&gt;
 </pre></div>
 </div>
 </section>
@@ -763,9 +763,9 @@ <h2>Training<a class="headerlink" href="#training" title="Link to this heading">
   return F.conv1d(input, weight, bias, self.stride,
   epoch    train_bal_acc    train_loss    valid_bal_acc    valid_loss     dur
 -------  ---------------  ------------  ---------------  ------------  ------
-      1           0.2040        1.6129           0.1707        1.5807  2.3315
-      2           0.2224        1.5430           0.1594        1.5866  1.7445
-      3           0.3464        1.4928           0.1853        1.6026  1.7454
+      1           0.2040        1.6129           0.1707        1.5807  2.2410
+      2           0.2224        1.5430           0.1594        1.5866  1.7760
+      3           0.3464        1.4928           0.1853        1.6026  1.7085
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=======================================================================================================================================================
@@ -975,8 +975,8 @@ <h2>References<a class="headerlink" href="#references" title="Link to this headi
 Circulation 101(23):e215-e220</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 11.337 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  667 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 11.396 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  638 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-applied-examples-plot-sleep-staging-usleep-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/8b5ba06718764b959e8dea1dd0bb97df/plot_sleep_staging_usleep.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_sleep_staging_usleep.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/applied_examples/plot_tuh_eeg_corpus.html b/dev/auto_examples/applied_examples/plot_tuh_eeg_corpus.html
index f3a0c3dd..8d753892 100644
--- a/dev/auto_examples/applied_examples/plot_tuh_eeg_corpus.html
+++ b/dev/auto_examples/applied_examples/plot_tuh_eeg_corpus.html
@@ -832,7 +832,7 @@ <h3><a class="toc-backref" href="#id5" role="doc-backlink">Cut Compute Windows</
 <span class="p">)</span>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 7.651 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 7.693 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-applied-examples-plot-tuh-eeg-corpus-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/applied_examples/sg_execution_times.html b/dev/auto_examples/applied_examples/sg_execution_times.html
index a33512ad..f4b4aea7 100644
--- a/dev/auto_examples/applied_examples/sg_execution_times.html
+++ b/dev/auto_examples/applied_examples/sg_execution_times.html
@@ -449,7 +449,7 @@
   
   <section id="computation-times">
 <span id="sphx-glr-auto-examples-applied-examples-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Link to this heading">#</a></h1>
-<p><strong>04:40.750</strong> total execution time for 5 files <strong>from auto_examples/applied_examples</strong>:</p>
+<p><strong>04:04.276</strong> total execution time for 5 files <strong>from auto_examples/applied_examples</strong>:</p>
 <div class="docutils container">
 <style scoped>
 <link href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css" rel="stylesheet" />
@@ -471,23 +471,23 @@
 </thead>
 <tbody>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_sleep_staging_chambon2018.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-chambon2018-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Chambon2018 network</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_sleep_staging_chambon2018.py</span></code>)</p></td>
-<td><p>03:42.544</p></td>
-<td><p>633.0</p></td>
+<td><p>03:06.130</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_bcic_iv_4_ecog_trial.html#sphx-glr-auto-examples-applied-examples-plot-bcic-iv-4-ecog-trial-py"><span class="std std-ref">Fingers flexion decoding on BCIC IV 4 ECoG Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_bcic_iv_4_ecog_trial.py</span></code>)</p></td>
-<td><p>00:26.059</p></td>
-<td><p>735.0</p></td>
+<td><p>00:26.037</p></td>
+<td><p>837.3</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_sleep_staging_eldele2021.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-eldele2021-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Eldele2021</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_sleep_staging_eldele2021.py</span></code>)</p></td>
-<td><p>00:13.159</p></td>
-<td><p>635.1</p></td>
+<td><p>00:13.021</p></td>
+<td><p>635.2</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_sleep_staging_usleep.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-usleep-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using U-Sleep network</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_sleep_staging_usleep.py</span></code>)</p></td>
-<td><p>00:11.337</p></td>
-<td><p>667.0</p></td>
+<td><p>00:11.396</p></td>
+<td><p>638.0</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_tuh_eeg_corpus.html#sphx-glr-auto-examples-applied-examples-plot-tuh-eeg-corpus-py"><span class="std std-ref">Process a big data EEG resource (TUH EEG Corpus)</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_tuh_eeg_corpus.py</span></code>)</p></td>
-<td><p>00:07.651</p></td>
+<td><p>00:07.693</p></td>
 <td><p>633.0</p></td>
 </tr>
 </tbody>
diff --git a/dev/auto_examples/datasets_io/plot_benchmark_preprocessing.html b/dev/auto_examples/datasets_io/plot_benchmark_preprocessing.html
index 26a7ac95..5859d41a 100644
--- a/dev/auto_examples/datasets_io/plot_benchmark_preprocessing.html
+++ b/dev/auto_examples/datasets_io/plot_benchmark_preprocessing.html
@@ -644,833 +644,723 @@
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  0%|                                              | 0.00/51.1M [00:00&lt;?, ?B/s]
-  0%|                                      | 49.2k/51.1M [00:00&lt;01:54, 447kB/s]
-  0%|                                      | 98.3k/51.1M [00:00&lt;02:28, 343kB/s]
-  0%|▏                                      | 206k/51.1M [00:00&lt;01:22, 614kB/s]
-  1%|▏                                      | 274k/51.1M [00:00&lt;01:46, 478kB/s]
-  1%|▎                                      | 377k/51.1M [00:00&lt;01:26, 588kB/s]
-  1%|▎                                      | 442k/51.1M [00:00&lt;01:37, 522kB/s]
-  1%|▍                                      | 508k/51.1M [00:00&lt;01:33, 544kB/s]
-  1%|▍                                      | 566k/51.1M [00:01&lt;01:33, 540kB/s]
-  1%|▍                                      | 624k/51.1M [00:01&lt;01:40, 500kB/s]
-  1%|▌                                      | 688k/51.1M [00:01&lt;01:39, 505kB/s]
-  1%|▌                                      | 754k/51.1M [00:01&lt;01:39, 506kB/s]
-  2%|▋                                      | 819k/51.1M [00:01&lt;01:39, 507kB/s]
-  2%|▋                                      | 885k/51.1M [00:01&lt;01:38, 511kB/s]
-  2%|▋                                      | 950k/51.1M [00:01&lt;01:36, 518kB/s]
-  2%|▊                                     | 1.02M/51.1M [00:01&lt;01:34, 528kB/s]
-  2%|▊                                     | 1.08M/51.1M [00:02&lt;01:33, 534kB/s]
-  2%|▊                                     | 1.15M/51.1M [00:02&lt;01:52, 445kB/s]
-  2%|▉                                     | 1.25M/51.1M [00:02&lt;01:32, 542kB/s]
-  3%|▉                                     | 1.30M/51.1M [00:02&lt;01:33, 530kB/s]
-  3%|█                                     | 1.36M/51.1M [00:02&lt;01:34, 528kB/s]
-  3%|█                                     | 1.41M/51.1M [00:02&lt;01:39, 497kB/s]
-  3%|█                                     | 1.47M/51.1M [00:02&lt;01:41, 487kB/s]
-  3%|█▏                                    | 1.54M/51.1M [00:03&lt;01:38, 504kB/s]
-  3%|█▏                                    | 1.61M/51.1M [00:03&lt;01:37, 508kB/s]
-  3%|█▏                                    | 1.67M/51.1M [00:03&lt;01:36, 514kB/s]
-  3%|█▎                                    | 1.74M/51.1M [00:03&lt;01:34, 525kB/s]
-  4%|█▎                                    | 1.80M/51.1M [00:03&lt;01:32, 531kB/s]
-  4%|█▍                                    | 1.87M/51.1M [00:03&lt;01:31, 539kB/s]
-  4%|█▍                                    | 1.93M/51.1M [00:03&lt;01:32, 533kB/s]
-  4%|█▍                                    | 2.00M/51.1M [00:03&lt;01:30, 543kB/s]
-  4%|█▌                                    | 2.06M/51.1M [00:03&lt;01:28, 553kB/s]
-  4%|█▌                                    | 2.13M/51.1M [00:04&lt;01:27, 559kB/s]
-  4%|█▋                                    | 2.20M/51.1M [00:04&lt;01:24, 576kB/s]
-  4%|█▋                                    | 2.26M/51.1M [00:04&lt;01:22, 589kB/s]
-  5%|█▋                                    | 2.33M/51.1M [00:04&lt;01:23, 581kB/s]
-  5%|█▊                                    | 2.38M/51.1M [00:04&lt;01:34, 516kB/s]
-  5%|█▊                                    | 2.46M/51.1M [00:04&lt;01:26, 560kB/s]
-  5%|█▊                                    | 2.51M/51.1M [00:04&lt;01:28, 550kB/s]
-  5%|█▉                                    | 2.57M/51.1M [00:04&lt;01:36, 504kB/s]
-  5%|█▉                                    | 2.64M/51.1M [00:05&lt;01:34, 512kB/s]
-  5%|██                                    | 2.70M/51.1M [00:05&lt;01:32, 522kB/s]
-  5%|██                                    | 2.77M/51.1M [00:05&lt;01:30, 532kB/s]
-  6%|██                                    | 2.83M/51.1M [00:05&lt;01:29, 537kB/s]
-  6%|██▏                                   | 2.90M/51.1M [00:05&lt;01:29, 542kB/s]
-  6%|██▏                                   | 2.97M/51.1M [00:05&lt;01:28, 547kB/s]
-  6%|██▎                                   | 3.03M/51.1M [00:05&lt;01:25, 560kB/s]
-  6%|██▎                                   | 3.10M/51.1M [00:05&lt;01:26, 556kB/s]
-  6%|██▎                                   | 3.15M/51.1M [00:06&lt;01:40, 477kB/s]
-  6%|██▍                                   | 3.24M/51.1M [00:06&lt;01:27, 546kB/s]
-  6%|██▍                                   | 3.30M/51.1M [00:06&lt;01:28, 540kB/s]
-  7%|██▍                                   | 3.36M/51.1M [00:06&lt;01:28, 538kB/s]
-  7%|██▌                                   | 3.41M/51.1M [00:06&lt;01:36, 494kB/s]
-  7%|██▌                                   | 3.46M/51.1M [00:06&lt;01:35, 497kB/s]
-  7%|██▌                                   | 3.51M/51.1M [00:06&lt;01:35, 500kB/s]
-  7%|██▋                                   | 3.57M/51.1M [00:06&lt;01:36, 490kB/s]
-  7%|██▋                                   | 3.64M/51.1M [00:06&lt;01:35, 498kB/s]
-  7%|██▊                                   | 3.70M/51.1M [00:07&lt;01:32, 515kB/s]
-  7%|██▊                                   | 3.77M/51.1M [00:07&lt;01:31, 519kB/s]
-  8%|██▊                                   | 3.83M/51.1M [00:07&lt;01:30, 524kB/s]
-  8%|██▉                                   | 3.90M/51.1M [00:07&lt;01:27, 537kB/s]
-  8%|██▉                                   | 3.96M/51.1M [00:07&lt;01:26, 546kB/s]
-  8%|██▉                                   | 4.03M/51.1M [00:07&lt;01:26, 545kB/s]
-  8%|███                                   | 4.09M/51.1M [00:07&lt;01:34, 495kB/s]
-  8%|███                                   | 4.16M/51.1M [00:07&lt;01:25, 549kB/s]
-  8%|███▏                                  | 4.22M/51.1M [00:08&lt;01:26, 540kB/s]
-  8%|███▏                                  | 4.27M/51.1M [00:08&lt;01:26, 542kB/s]
-  8%|███▏                                  | 4.33M/51.1M [00:08&lt;01:33, 502kB/s]
-  9%|███▎                                  | 4.39M/51.1M [00:08&lt;01:33, 498kB/s]
-  9%|███▎                                  | 4.46M/51.1M [00:08&lt;01:31, 510kB/s]
-  9%|███▎                                  | 4.52M/51.1M [00:08&lt;01:29, 521kB/s]
-  9%|███▍                                  | 4.59M/51.1M [00:08&lt;01:28, 523kB/s]
-  9%|███▍                                  | 4.65M/51.1M [00:08&lt;01:26, 538kB/s]
-  9%|███▌                                  | 4.72M/51.1M [00:08&lt;01:25, 540kB/s]
-  9%|███▌                                  | 4.78M/51.1M [00:09&lt;01:23, 555kB/s]
-  9%|███▌                                  | 4.85M/51.1M [00:09&lt;01:22, 563kB/s]
- 10%|███▋                                  | 4.92M/51.1M [00:09&lt;01:21, 564kB/s]
- 10%|███▋                                  | 4.98M/51.1M [00:09&lt;01:21, 568kB/s]
- 10%|███▊                                  | 5.05M/51.1M [00:09&lt;01:20, 575kB/s]
- 10%|███▊                                  | 5.11M/51.1M [00:09&lt;01:19, 576kB/s]
- 10%|███▊                                  | 5.17M/51.1M [00:09&lt;01:23, 547kB/s]
- 10%|███▉                                  | 5.23M/51.1M [00:09&lt;01:23, 548kB/s]
- 10%|███▉                                  | 5.29M/51.1M [00:10&lt;01:27, 525kB/s]
- 10%|███▉                                  | 5.35M/51.1M [00:10&lt;01:27, 525kB/s]
- 11%|████                                  | 5.41M/51.1M [00:10&lt;01:28, 517kB/s]
- 11%|████                                  | 5.47M/51.1M [00:10&lt;01:26, 530kB/s]
- 11%|████                                  | 5.54M/51.1M [00:10&lt;01:24, 537kB/s]
- 11%|████▏                                 | 5.60M/51.1M [00:10&lt;01:23, 548kB/s]
- 11%|████▏                                 | 5.67M/51.1M [00:10&lt;01:22, 552kB/s]
- 11%|████▎                                 | 5.73M/51.1M [00:10&lt;01:20, 560kB/s]
- 11%|████▎                                 | 5.80M/51.1M [00:10&lt;01:20, 566kB/s]
- 11%|████▎                                 | 5.87M/51.1M [00:11&lt;01:19, 570kB/s]
- 12%|████▍                                 | 5.93M/51.1M [00:11&lt;01:19, 572kB/s]
- 12%|████▍                                 | 6.00M/51.1M [00:11&lt;01:18, 572kB/s]
- 12%|████▌                                 | 6.06M/51.1M [00:11&lt;01:19, 568kB/s]
- 12%|████▌                                 | 6.12M/51.1M [00:11&lt;01:26, 520kB/s]
- 12%|████▌                                 | 6.19M/51.1M [00:11&lt;01:19, 562kB/s]
- 12%|████▋                                 | 6.25M/51.1M [00:11&lt;01:21, 552kB/s]
- 12%|████▋                                 | 6.31M/51.1M [00:11&lt;01:28, 507kB/s]
- 12%|████▋                                 | 6.37M/51.1M [00:12&lt;01:27, 514kB/s]
- 13%|████▊                                 | 6.44M/51.1M [00:12&lt;01:24, 527kB/s]
- 13%|████▊                                 | 6.50M/51.1M [00:12&lt;01:24, 529kB/s]
- 13%|████▉                                 | 6.57M/51.1M [00:12&lt;01:22, 538kB/s]
- 13%|████▉                                 | 6.64M/51.1M [00:12&lt;01:21, 546kB/s]
- 13%|████▉                                 | 6.70M/51.1M [00:12&lt;01:20, 554kB/s]
- 13%|█████                                 | 6.77M/51.1M [00:12&lt;01:18, 568kB/s]
- 13%|█████                                 | 6.83M/51.1M [00:12&lt;01:17, 572kB/s]
- 13%|█████▏                                | 6.90M/51.1M [00:12&lt;01:17, 572kB/s]
- 14%|█████▏                                | 6.96M/51.1M [00:13&lt;01:17, 572kB/s]
- 14%|█████▏                                | 7.03M/51.1M [00:13&lt;01:17, 569kB/s]
- 14%|█████▎                                | 7.09M/51.1M [00:13&lt;01:25, 517kB/s]
- 14%|█████▎                                | 7.16M/51.1M [00:13&lt;01:19, 555kB/s]
- 14%|█████▎                                | 7.22M/51.1M [00:13&lt;01:19, 551kB/s]
- 14%|█████▍                                | 7.27M/51.1M [00:13&lt;01:19, 553kB/s]
- 14%|█████▍                                | 7.33M/51.1M [00:13&lt;01:24, 518kB/s]
- 14%|█████▍                                | 7.39M/51.1M [00:13&lt;01:25, 510kB/s]
- 15%|█████▌                                | 7.45M/51.1M [00:13&lt;01:22, 528kB/s]
- 15%|█████▌                                | 7.52M/51.1M [00:14&lt;01:20, 539kB/s]
- 15%|█████▋                                | 7.59M/51.1M [00:14&lt;01:18, 552kB/s]
- 15%|█████▋                                | 7.65M/51.1M [00:14&lt;01:18, 556kB/s]
- 15%|█████▋                                | 7.72M/51.1M [00:14&lt;01:18, 555kB/s]
- 15%|█████▊                                | 7.78M/51.1M [00:14&lt;01:17, 561kB/s]
- 15%|█████▊                                | 7.85M/51.1M [00:14&lt;01:16, 565kB/s]
- 15%|█████▉                                | 7.91M/51.1M [00:14&lt;01:14, 579kB/s]
- 16%|█████▉                                | 7.98M/51.1M [00:14&lt;01:14, 581kB/s]
- 16%|█████▉                                | 8.04M/51.1M [00:15&lt;01:24, 509kB/s]
- 16%|██████                                | 8.13M/51.1M [00:15&lt;01:16, 565kB/s]
- 16%|██████                                | 8.18M/51.1M [00:15&lt;01:17, 553kB/s]
- 16%|██████▏                               | 8.24M/51.1M [00:15&lt;01:22, 519kB/s]
- 16%|██████▏                               | 8.31M/51.1M [00:15&lt;01:22, 519kB/s]
- 16%|██████▏                               | 8.37M/51.1M [00:15&lt;01:21, 525kB/s]
- 17%|██████▎                               | 8.44M/51.1M [00:15&lt;01:20, 533kB/s]
- 17%|██████▎                               | 8.49M/51.1M [00:15&lt;01:30, 473kB/s]
- 17%|██████▎                               | 8.57M/51.1M [00:16&lt;01:21, 519kB/s]
- 17%|██████▍                               | 8.62M/51.1M [00:16&lt;01:25, 495kB/s]
- 17%|██████▍                               | 8.67M/51.1M [00:16&lt;01:27, 483kB/s]
- 17%|██████▍                               | 8.72M/51.1M [00:16&lt;01:30, 470kB/s]
- 17%|██████▌                               | 8.77M/51.1M [00:16&lt;01:30, 466kB/s]
- 17%|██████▌                               | 8.82M/51.1M [00:16&lt;01:35, 445kB/s]
- 17%|██████▌                               | 8.86M/51.1M [00:16&lt;01:35, 442kB/s]
- 17%|██████▋                               | 8.91M/51.1M [00:16&lt;01:32, 455kB/s]
- 18%|██████▋                               | 8.96M/51.1M [00:16&lt;01:32, 458kB/s]
- 18%|██████▋                               | 9.03M/51.1M [00:17&lt;01:28, 476kB/s]
- 18%|██████▊                               | 9.09M/51.1M [00:17&lt;01:26, 486kB/s]
- 18%|██████▊                               | 9.16M/51.1M [00:17&lt;01:24, 496kB/s]
- 18%|██████▊                               | 9.22M/51.1M [00:17&lt;01:22, 510kB/s]
- 18%|██████▉                               | 9.29M/51.1M [00:17&lt;01:20, 521kB/s]
- 18%|██████▉                               | 9.36M/51.1M [00:17&lt;01:18, 529kB/s]
- 18%|███████                               | 9.42M/51.1M [00:17&lt;01:17, 535kB/s]
- 19%|███████                               | 9.49M/51.1M [00:17&lt;01:16, 547kB/s]
- 19%|███████                               | 9.55M/51.1M [00:18&lt;01:14, 555kB/s]
- 19%|███████▏                              | 9.61M/51.1M [00:18&lt;01:16, 545kB/s]
- 19%|███████▏                              | 9.67M/51.1M [00:18&lt;01:18, 528kB/s]
- 19%|███████▏                              | 9.72M/51.1M [00:18&lt;01:26, 481kB/s]
- 19%|███████▎                              | 9.77M/51.1M [00:18&lt;01:29, 460kB/s]
- 19%|███████▎                              | 9.82M/51.1M [00:18&lt;01:38, 418kB/s]
- 19%|███████▎                              | 9.86M/51.1M [00:18&lt;01:43, 399kB/s]
- 19%|███████▎                              | 9.91M/51.1M [00:18&lt;01:46, 386kB/s]
- 19%|███████▍                              | 9.96M/51.1M [00:19&lt;01:48, 381kB/s]
- 20%|███████▍                              | 10.0M/51.1M [00:19&lt;01:47, 382kB/s]
- 20%|███████▍                              | 10.1M/51.1M [00:19&lt;01:45, 389kB/s]
- 20%|███████▌                              | 10.1M/51.1M [00:19&lt;01:43, 395kB/s]
- 20%|███████▌                              | 10.2M/51.1M [00:19&lt;01:40, 407kB/s]
- 20%|███████▌                              | 10.2M/51.1M [00:19&lt;01:38, 415kB/s]
- 20%|███████▋                              | 10.3M/51.1M [00:19&lt;01:34, 431kB/s]
- 20%|███████▋                              | 10.3M/51.1M [00:19&lt;01:33, 439kB/s]
- 20%|███████▋                              | 10.4M/51.1M [00:20&lt;01:30, 449kB/s]
- 20%|███████▊                              | 10.4M/51.1M [00:20&lt;01:26, 470kB/s]
- 21%|███████▊                              | 10.5M/51.1M [00:20&lt;01:24, 479kB/s]
- 21%|███████▊                              | 10.6M/51.1M [00:20&lt;01:22, 490kB/s]
- 21%|███████▉                              | 10.6M/51.1M [00:20&lt;01:19, 507kB/s]
- 21%|███████▉                              | 10.7M/51.1M [00:20&lt;01:17, 524kB/s]
- 21%|████████                              | 10.8M/51.1M [00:20&lt;01:15, 535kB/s]
- 21%|████████                              | 10.8M/51.1M [00:20&lt;01:13, 545kB/s]
- 21%|████████                              | 10.9M/51.1M [00:20&lt;01:12, 553kB/s]
- 21%|████████▏                             | 11.0M/51.1M [00:21&lt;01:11, 559kB/s]
- 22%|████████▏                             | 11.0M/51.1M [00:21&lt;01:10, 566kB/s]
- 22%|████████▏                             | 11.1M/51.1M [00:21&lt;01:10, 567kB/s]
- 22%|████████▎                             | 11.1M/51.1M [00:21&lt;01:11, 562kB/s]
- 22%|████████▎                             | 11.2M/51.1M [00:21&lt;01:13, 541kB/s]
- 22%|████████▎                             | 11.3M/51.1M [00:21&lt;01:14, 536kB/s]
- 22%|████████▍                             | 11.3M/51.1M [00:21&lt;01:12, 549kB/s]
- 22%|████████▍                             | 11.4M/51.1M [00:21&lt;01:18, 507kB/s]
- 22%|████████▌                             | 11.4M/51.1M [00:21&lt;01:17, 512kB/s]
- 23%|████████▌                             | 11.5M/51.1M [00:22&lt;01:14, 529kB/s]
- 23%|████████▌                             | 11.6M/51.1M [00:22&lt;01:14, 528kB/s]
- 23%|████████▋                             | 11.6M/51.1M [00:22&lt;01:13, 536kB/s]
- 23%|████████▋                             | 11.7M/51.1M [00:22&lt;01:10, 556kB/s]
- 23%|████████▋                             | 11.8M/51.1M [00:22&lt;01:10, 556kB/s]
- 23%|████████▊                             | 11.8M/51.1M [00:22&lt;01:10, 561kB/s]
- 23%|████████▊                             | 11.9M/51.1M [00:22&lt;01:09, 566kB/s]
- 23%|████████▉                             | 12.0M/51.1M [00:22&lt;01:19, 493kB/s]
- 24%|████████▉                             | 12.0M/51.1M [00:23&lt;01:11, 547kB/s]
- 24%|████████▉                             | 12.1M/51.1M [00:23&lt;01:11, 545kB/s]
- 24%|█████████                             | 12.2M/51.1M [00:23&lt;01:12, 536kB/s]
- 24%|█████████                             | 12.2M/51.1M [00:23&lt;01:18, 495kB/s]
- 24%|█████████                             | 12.3M/51.1M [00:23&lt;01:18, 495kB/s]
- 24%|█████████▏                            | 12.3M/51.1M [00:23&lt;01:17, 498kB/s]
- 24%|█████████▏                            | 12.4M/51.1M [00:23&lt;01:16, 507kB/s]
- 24%|█████████▎                            | 12.5M/51.1M [00:23&lt;01:15, 514kB/s]
- 25%|█████████▎                            | 12.5M/51.1M [00:24&lt;01:13, 523kB/s]
- 25%|█████████▎                            | 12.6M/51.1M [00:24&lt;01:13, 522kB/s]
- 25%|█████████▍                            | 12.7M/51.1M [00:24&lt;01:11, 537kB/s]
- 25%|█████████▍                            | 12.7M/51.1M [00:24&lt;01:11, 539kB/s]
- 25%|█████████▌                            | 12.8M/51.1M [00:24&lt;01:09, 552kB/s]
- 25%|█████████▌                            | 12.9M/51.1M [00:24&lt;01:08, 556kB/s]
- 25%|█████████▌                            | 12.9M/51.1M [00:24&lt;01:07, 567kB/s]
- 25%|█████████▋                            | 13.0M/51.1M [00:24&lt;01:17, 494kB/s]
- 26%|█████████▋                            | 13.1M/51.1M [00:25&lt;01:08, 551kB/s]
- 26%|█████████▊                            | 13.1M/51.1M [00:25&lt;01:10, 542kB/s]
- 26%|█████████▊                            | 13.2M/51.1M [00:25&lt;01:13, 514kB/s]
- 26%|█████████▊                            | 13.3M/51.1M [00:25&lt;01:13, 515kB/s]
- 26%|█████████▉                            | 13.3M/51.1M [00:25&lt;01:11, 526kB/s]
- 26%|█████████▉                            | 13.4M/51.1M [00:25&lt;01:11, 531kB/s]
- 26%|██████████                            | 13.5M/51.1M [00:25&lt;01:10, 538kB/s]
- 26%|██████████                            | 13.5M/51.1M [00:25&lt;01:09, 539kB/s]
- 27%|██████████                            | 13.6M/51.1M [00:26&lt;01:08, 547kB/s]
- 27%|██████████▏                           | 13.6M/51.1M [00:26&lt;01:07, 554kB/s]
- 27%|██████████▏                           | 13.7M/51.1M [00:26&lt;01:19, 470kB/s]
- 27%|██████████▎                           | 13.8M/51.1M [00:26&lt;01:06, 560kB/s]
- 27%|██████████▎                           | 13.9M/51.1M [00:26&lt;01:08, 542kB/s]
- 27%|██████████▎                           | 13.9M/51.1M [00:26&lt;01:15, 489kB/s]
- 27%|██████████▍                           | 14.0M/51.1M [00:26&lt;01:15, 490kB/s]
- 27%|██████████▍                           | 14.0M/51.1M [00:26&lt;01:17, 479kB/s]
- 28%|██████████▍                           | 14.1M/51.1M [00:27&lt;01:17, 480kB/s]
- 28%|██████████▌                           | 14.1M/51.1M [00:27&lt;01:16, 483kB/s]
- 28%|██████████▌                           | 14.2M/51.1M [00:27&lt;01:17, 476kB/s]
- 28%|██████████▌                           | 14.3M/51.1M [00:27&lt;01:15, 486kB/s]
- 28%|██████████▋                           | 14.3M/51.1M [00:27&lt;01:16, 479kB/s]
- 28%|██████████▋                           | 14.4M/51.1M [00:27&lt;01:23, 439kB/s]
- 28%|██████████▋                           | 14.4M/51.1M [00:27&lt;01:26, 426kB/s]
- 28%|██████████▊                           | 14.5M/51.1M [00:27&lt;01:25, 430kB/s]
- 28%|██████████▊                           | 14.5M/51.1M [00:28&lt;01:25, 427kB/s]
- 28%|██████████▊                           | 14.6M/51.1M [00:28&lt;01:23, 435kB/s]
- 29%|██████████▊                           | 14.6M/51.1M [00:28&lt;01:23, 436kB/s]
- 29%|██████████▉                           | 14.7M/51.1M [00:28&lt;01:21, 448kB/s]
- 29%|██████████▉                           | 14.7M/51.1M [00:28&lt;01:19, 460kB/s]
- 29%|██████████▉                           | 14.8M/51.1M [00:28&lt;01:17, 467kB/s]
- 29%|███████████                           | 14.8M/51.1M [00:28&lt;01:16, 472kB/s]
- 29%|███████████                           | 14.9M/51.1M [00:28&lt;01:16, 475kB/s]
- 29%|███████████                           | 15.0M/51.1M [00:28&lt;01:14, 485kB/s]
- 29%|███████████▏                          | 15.0M/51.1M [00:29&lt;01:12, 495kB/s]
- 30%|███████████▏                          | 15.1M/51.1M [00:29&lt;01:11, 504kB/s]
- 30%|███████████▎                          | 15.2M/51.1M [00:29&lt;01:09, 516kB/s]
- 30%|███████████▎                          | 15.2M/51.1M [00:29&lt;01:08, 526kB/s]
- 30%|███████████▎                          | 15.3M/51.1M [00:29&lt;01:06, 538kB/s]
- 30%|███████████▍                          | 15.4M/51.1M [00:29&lt;01:05, 546kB/s]
- 30%|███████████▍                          | 15.4M/51.1M [00:29&lt;01:04, 553kB/s]
- 30%|███████████▌                          | 15.5M/51.1M [00:29&lt;01:04, 553kB/s]
- 30%|███████████▌                          | 15.5M/51.1M [00:30&lt;01:03, 560kB/s]
- 31%|███████████▌                          | 15.6M/51.1M [00:30&lt;01:07, 524kB/s]
- 31%|███████████▋                          | 15.7M/51.1M [00:30&lt;01:05, 545kB/s]
- 31%|███████████▋                          | 15.7M/51.1M [00:30&lt;01:06, 532kB/s]
- 31%|███████████▋                          | 15.8M/51.1M [00:30&lt;01:07, 525kB/s]
- 31%|███████████▊                          | 15.8M/51.1M [00:30&lt;01:10, 498kB/s]
- 31%|███████████▊                          | 15.9M/51.1M [00:30&lt;01:09, 503kB/s]
- 31%|███████████▉                          | 16.0M/51.1M [00:30&lt;01:07, 517kB/s]
- 31%|███████████▉                          | 16.0M/51.1M [00:30&lt;01:07, 521kB/s]
- 32%|███████████▉                          | 16.1M/51.1M [00:31&lt;01:05, 531kB/s]
- 32%|████████████                          | 16.2M/51.1M [00:31&lt;01:05, 535kB/s]
- 32%|████████████                          | 16.2M/51.1M [00:31&lt;01:04, 543kB/s]
- 32%|████████████                          | 16.3M/51.1M [00:31&lt;01:03, 551kB/s]
- 32%|████████████▏                         | 16.4M/51.1M [00:31&lt;01:14, 469kB/s]
- 32%|████████████▏                         | 16.5M/51.1M [00:31&lt;01:02, 553kB/s]
- 32%|████████████▎                         | 16.5M/51.1M [00:31&lt;01:02, 549kB/s]
- 32%|████████████▎                         | 16.6M/51.1M [00:31&lt;01:03, 545kB/s]
- 33%|████████████▎                         | 16.6M/51.1M [00:32&lt;01:08, 501kB/s]
- 33%|████████████▍                         | 16.7M/51.1M [00:32&lt;01:09, 496kB/s]
- 33%|████████████▍                         | 16.7M/51.1M [00:32&lt;01:12, 476kB/s]
- 33%|████████████▍                         | 16.8M/51.1M [00:32&lt;01:11, 480kB/s]
- 33%|████████████▌                         | 16.9M/51.1M [00:32&lt;01:09, 494kB/s]
- 33%|████████████▌                         | 16.9M/51.1M [00:32&lt;01:07, 507kB/s]
- 33%|████████████▋                         | 17.0M/51.1M [00:32&lt;01:05, 518kB/s]
- 33%|████████████▋                         | 17.1M/51.1M [00:32&lt;01:03, 532kB/s]
- 34%|████████████▋                         | 17.1M/51.1M [00:33&lt;01:03, 537kB/s]
- 34%|████████████▊                         | 17.2M/51.1M [00:33&lt;01:01, 554kB/s]
- 34%|████████████▊                         | 17.3M/51.1M [00:33&lt;01:00, 561kB/s]
- 34%|████████████▉                         | 17.3M/51.1M [00:33&lt;01:00, 563kB/s]
- 34%|████████████▉                         | 17.4M/51.1M [00:33&lt;01:08, 496kB/s]
- 34%|████████████▉                         | 17.5M/51.1M [00:33&lt;00:59, 562kB/s]
- 34%|█████████████                         | 17.5M/51.1M [00:33&lt;01:01, 543kB/s]
- 34%|█████████████                         | 17.6M/51.1M [00:33&lt;01:05, 512kB/s]
- 35%|█████████████                         | 17.6M/51.1M [00:34&lt;01:06, 504kB/s]
- 35%|█████████████▏                        | 17.7M/51.1M [00:34&lt;01:06, 503kB/s]
- 35%|█████████████▏                        | 17.8M/51.1M [00:34&lt;01:04, 516kB/s]
- 35%|█████████████▎                        | 17.8M/51.1M [00:34&lt;01:02, 531kB/s]
- 35%|█████████████▎                        | 17.9M/51.1M [00:34&lt;01:01, 538kB/s]
- 35%|█████████████▎                        | 18.0M/51.1M [00:34&lt;01:01, 537kB/s]
- 35%|█████████████▍                        | 18.0M/51.1M [00:34&lt;01:06, 497kB/s]
- 35%|█████████████▍                        | 18.1M/51.1M [00:34&lt;01:04, 514kB/s]
- 36%|█████████████▍                        | 18.2M/51.1M [00:35&lt;01:05, 507kB/s]
- 36%|█████████████▌                        | 18.2M/51.1M [00:35&lt;01:08, 483kB/s]
- 36%|█████████████▌                        | 18.3M/51.1M [00:35&lt;01:07, 483kB/s]
- 36%|█████████████▌                        | 18.3M/51.1M [00:35&lt;01:07, 485kB/s]
- 36%|█████████████▋                        | 18.4M/51.1M [00:35&lt;01:08, 475kB/s]
- 36%|█████████████▋                        | 18.4M/51.1M [00:35&lt;01:09, 474kB/s]
- 36%|█████████████▋                        | 18.5M/51.1M [00:35&lt;01:09, 472kB/s]
- 36%|█████████████▊                        | 18.5M/51.1M [00:35&lt;01:08, 476kB/s]
- 36%|█████████████▊                        | 18.6M/51.1M [00:35&lt;01:05, 496kB/s]
- 36%|█████████████▊                        | 18.6M/51.1M [00:36&lt;01:03, 509kB/s]
- 37%|█████████████▉                        | 18.7M/51.1M [00:36&lt;01:02, 519kB/s]
- 37%|█████████████▉                        | 18.8M/51.1M [00:36&lt;01:01, 525kB/s]
- 37%|██████████████                        | 18.8M/51.1M [00:36&lt;01:00, 533kB/s]
- 37%|██████████████                        | 18.9M/51.1M [00:36&lt;00:59, 540kB/s]
- 37%|██████████████                        | 19.0M/51.1M [00:36&lt;00:58, 554kB/s]
- 37%|██████████████▏                       | 19.0M/51.1M [00:36&lt;01:08, 465kB/s]
- 37%|██████████████▏                       | 19.1M/51.1M [00:36&lt;00:56, 563kB/s]
- 38%|██████████████▎                       | 19.2M/51.1M [00:37&lt;00:56, 561kB/s]
- 38%|██████████████▎                       | 19.3M/51.1M [00:37&lt;01:01, 521kB/s]
- 38%|██████████████▎                       | 19.3M/51.1M [00:37&lt;01:02, 510kB/s]
- 38%|██████████████▍                       | 19.4M/51.1M [00:37&lt;01:01, 513kB/s]
- 38%|██████████████▍                       | 19.4M/51.1M [00:37&lt;01:01, 514kB/s]
- 38%|██████████████▌                       | 19.5M/51.1M [00:37&lt;01:00, 523kB/s]
- 38%|██████████████▌                       | 19.6M/51.1M [00:37&lt;00:58, 537kB/s]
- 38%|██████████████▌                       | 19.6M/51.1M [00:37&lt;00:58, 538kB/s]
- 39%|██████████████▋                       | 19.7M/51.1M [00:38&lt;01:06, 471kB/s]
- 39%|██████████████▋                       | 19.8M/51.1M [00:38&lt;00:58, 538kB/s]
- 39%|██████████████▊                       | 19.8M/51.1M [00:38&lt;00:59, 523kB/s]
- 39%|██████████████▊                       | 19.9M/51.1M [00:38&lt;00:59, 521kB/s]
- 39%|██████████████▊                       | 20.0M/51.1M [00:38&lt;01:07, 464kB/s]
- 39%|██████████████▊                       | 20.0M/51.1M [00:38&lt;01:08, 457kB/s]
- 39%|██████████████▉                       | 20.1M/51.1M [00:38&lt;01:13, 421kB/s]
- 39%|██████████████▉                       | 20.1M/51.1M [00:38&lt;01:20, 386kB/s]
- 39%|██████████████▉                       | 20.1M/51.1M [00:39&lt;01:27, 354kB/s]
- 39%|███████████████                       | 20.2M/51.1M [00:39&lt;01:25, 363kB/s]
- 40%|███████████████                       | 20.2M/51.1M [00:39&lt;01:22, 373kB/s]
- 40%|███████████████                       | 20.3M/51.1M [00:39&lt;01:21, 379kB/s]
- 40%|███████████████                       | 20.3M/51.1M [00:39&lt;01:17, 396kB/s]
- 40%|███████████████▏                      | 20.4M/51.1M [00:39&lt;01:17, 398kB/s]
- 40%|███████████████▏                      | 20.4M/51.1M [00:39&lt;01:13, 418kB/s]
- 40%|███████████████▏                      | 20.5M/51.1M [00:39&lt;01:12, 421kB/s]
- 40%|███████████████▎                      | 20.5M/51.1M [00:40&lt;01:09, 443kB/s]
- 40%|███████████████▎                      | 20.6M/51.1M [00:40&lt;01:07, 454kB/s]
- 40%|███████████████▎                      | 20.7M/51.1M [00:40&lt;01:03, 478kB/s]
- 41%|███████████████▍                      | 20.7M/51.1M [00:40&lt;01:02, 489kB/s]
- 41%|███████████████▍                      | 20.8M/51.1M [00:40&lt;01:00, 500kB/s]
- 41%|███████████████▌                      | 20.9M/51.1M [00:40&lt;00:59, 509kB/s]
- 41%|███████████████▌                      | 20.9M/51.1M [00:40&lt;00:58, 513kB/s]
- 41%|███████████████▌                      | 21.0M/51.1M [00:40&lt;00:56, 531kB/s]
- 41%|███████████████▋                      | 21.1M/51.1M [00:41&lt;00:55, 543kB/s]
- 41%|███████████████▋                      | 21.1M/51.1M [00:41&lt;00:53, 560kB/s]
- 41%|███████████████▊                      | 21.2M/51.1M [00:41&lt;00:52, 571kB/s]
- 42%|███████████████▊                      | 21.3M/51.1M [00:41&lt;00:51, 580kB/s]
- 42%|███████████████▊                      | 21.3M/51.1M [00:41&lt;00:50, 594kB/s]
- 42%|███████████████▉                      | 21.4M/51.1M [00:41&lt;00:49, 595kB/s]
- 42%|███████████████▉                      | 21.4M/51.1M [00:41&lt;00:59, 496kB/s]
- 42%|████████████████                      | 21.5M/51.1M [00:41&lt;00:49, 598kB/s]
- 42%|████████████████                      | 21.6M/51.1M [00:41&lt;00:48, 603kB/s]
- 42%|████████████████                      | 21.7M/51.1M [00:42&lt;00:52, 564kB/s]
- 43%|████████████████▏                     | 21.7M/51.1M [00:42&lt;00:55, 530kB/s]
- 43%|████████████████▏                     | 21.8M/51.1M [00:42&lt;00:55, 524kB/s]
- 43%|████████████████▏                     | 21.9M/51.1M [00:42&lt;00:54, 541kB/s]
- 43%|████████████████▎                     | 21.9M/51.1M [00:42&lt;00:52, 552kB/s]
- 43%|████████████████▎                     | 22.0M/51.1M [00:42&lt;00:52, 555kB/s]
- 43%|████████████████▍                     | 22.1M/51.1M [00:42&lt;00:53, 545kB/s]
- 43%|████████████████▍                     | 22.1M/51.1M [00:42&lt;00:54, 528kB/s]
- 43%|████████████████▍                     | 22.2M/51.1M [00:43&lt;00:57, 506kB/s]
- 43%|████████████████▌                     | 22.2M/51.1M [00:43&lt;00:58, 494kB/s]
- 44%|████████████████▌                     | 22.3M/51.1M [00:43&lt;00:59, 486kB/s]
- 44%|████████████████▌                     | 22.3M/51.1M [00:43&lt;00:59, 487kB/s]
- 44%|████████████████▋                     | 22.4M/51.1M [00:43&lt;01:00, 473kB/s]
- 44%|████████████████▋                     | 22.4M/51.1M [00:43&lt;01:01, 470kB/s]
- 44%|████████████████▋                     | 22.5M/51.1M [00:43&lt;01:03, 449kB/s]
- 44%|████████████████▋                     | 22.5M/51.1M [00:43&lt;01:00, 472kB/s]
- 44%|████████████████▊                     | 22.6M/51.1M [00:43&lt;00:58, 490kB/s]
- 44%|████████████████▊                     | 22.7M/51.1M [00:44&lt;00:56, 502kB/s]
- 44%|████████████████▉                     | 22.7M/51.1M [00:44&lt;00:55, 516kB/s]
- 45%|████████████████▉                     | 22.8M/51.1M [00:44&lt;00:53, 529kB/s]
- 45%|████████████████▉                     | 22.9M/51.1M [00:44&lt;00:52, 534kB/s]
- 45%|█████████████████                     | 22.9M/51.1M [00:44&lt;00:50, 554kB/s]
- 45%|█████████████████                     | 23.0M/51.1M [00:44&lt;00:50, 552kB/s]
- 45%|█████████████████▏                    | 23.0M/51.1M [00:44&lt;00:53, 523kB/s]
- 45%|█████████████████▏                    | 23.1M/51.1M [00:44&lt;00:53, 525kB/s]
- 45%|█████████████████▏                    | 23.2M/51.1M [00:45&lt;00:54, 510kB/s]
- 45%|█████████████████▎                    | 23.2M/51.1M [00:45&lt;01:02, 447kB/s]
- 46%|█████████████████▎                    | 23.3M/51.1M [00:45&lt;00:56, 490kB/s]
- 46%|█████████████████▎                    | 23.4M/51.1M [00:45&lt;01:00, 460kB/s]
- 46%|█████████████████▍                    | 23.4M/51.1M [00:45&lt;01:03, 439kB/s]
- 46%|█████████████████▍                    | 23.5M/51.1M [00:45&lt;01:05, 424kB/s]
- 46%|█████████████████▍                    | 23.5M/51.1M [00:45&lt;01:05, 419kB/s]
- 46%|█████████████████▌                    | 23.6M/51.1M [00:45&lt;01:06, 415kB/s]
- 46%|█████████████████▌                    | 23.6M/51.1M [00:46&lt;01:04, 427kB/s]
- 46%|█████████████████▌                    | 23.7M/51.1M [00:46&lt;01:04, 423kB/s]
- 46%|█████████████████▋                    | 23.7M/51.1M [00:46&lt;01:02, 438kB/s]
- 47%|█████████████████▋                    | 23.8M/51.1M [00:46&lt;00:59, 459kB/s]
- 47%|█████████████████▋                    | 23.8M/51.1M [00:46&lt;00:58, 465kB/s]
- 47%|█████████████████▊                    | 23.9M/51.1M [00:46&lt;00:57, 470kB/s]
- 47%|█████████████████▊                    | 24.0M/51.1M [00:46&lt;00:55, 485kB/s]
- 47%|█████████████████▊                    | 24.0M/51.1M [00:46&lt;00:54, 498kB/s]
- 47%|█████████████████▉                    | 24.1M/51.1M [00:47&lt;00:54, 494kB/s]
- 47%|█████████████████▉                    | 24.2M/51.1M [00:47&lt;00:53, 507kB/s]
- 47%|██████████████████                    | 24.2M/51.1M [00:47&lt;00:50, 529kB/s]
- 48%|██████████████████                    | 24.3M/51.1M [00:47&lt;00:49, 542kB/s]
- 48%|██████████████████                    | 24.3M/51.1M [00:47&lt;00:49, 546kB/s]
- 48%|██████████████████▏                   | 24.4M/51.1M [00:47&lt;00:54, 486kB/s]
- 48%|██████████████████▏                   | 24.5M/51.1M [00:47&lt;00:49, 538kB/s]
- 48%|██████████████████▏                   | 24.5M/51.1M [00:47&lt;00:50, 525kB/s]
- 48%|██████████████████▎                   | 24.6M/51.1M [00:48&lt;00:51, 516kB/s]
- 48%|██████████████████▎                   | 24.6M/51.1M [00:48&lt;00:51, 517kB/s]
- 48%|██████████████████▎                   | 24.7M/51.1M [00:48&lt;00:55, 479kB/s]
- 48%|██████████████████▍                   | 24.8M/51.1M [00:48&lt;00:52, 501kB/s]
- 49%|██████████████████▍                   | 24.8M/51.1M [00:48&lt;00:50, 516kB/s]
- 49%|██████████████████▌                   | 24.9M/51.1M [00:48&lt;00:50, 520kB/s]
- 49%|██████████████████▌                   | 25.0M/51.1M [00:48&lt;00:48, 536kB/s]
- 49%|██████████████████▌                   | 25.0M/51.1M [00:48&lt;00:47, 547kB/s]
- 49%|██████████████████▋                   | 25.1M/51.1M [00:48&lt;00:46, 560kB/s]
- 49%|██████████████████▋                   | 25.1M/51.1M [00:49&lt;00:46, 558kB/s]
- 49%|██████████████████▋                   | 25.2M/51.1M [00:49&lt;00:45, 565kB/s]
- 49%|██████████████████▊                   | 25.3M/51.1M [00:49&lt;00:54, 470kB/s]
- 50%|██████████████████▊                   | 25.4M/51.1M [00:49&lt;00:46, 548kB/s]
- 50%|██████████████████▉                   | 25.4M/51.1M [00:49&lt;00:47, 538kB/s]
- 50%|██████████████████▉                   | 25.5M/51.1M [00:49&lt;00:48, 531kB/s]
- 50%|██████████████████▉                   | 25.5M/51.1M [00:49&lt;00:52, 488kB/s]
- 50%|███████████████████                   | 25.6M/51.1M [00:49&lt;00:54, 470kB/s]
- 50%|███████████████████                   | 25.6M/51.1M [00:50&lt;00:54, 471kB/s]
- 50%|███████████████████                   | 25.7M/51.1M [00:50&lt;00:53, 473kB/s]
- 50%|███████████████████▏                  | 25.7M/51.1M [00:50&lt;00:54, 461kB/s]
- 50%|███████████████████▏                  | 25.8M/51.1M [00:50&lt;00:54, 462kB/s]
- 51%|███████████████████▏                  | 25.8M/51.1M [00:50&lt;00:53, 469kB/s]
- 51%|███████████████████▎                  | 25.9M/51.1M [00:50&lt;00:51, 488kB/s]
- 51%|███████████████████▎                  | 26.0M/51.1M [00:50&lt;00:49, 506kB/s]
- 51%|███████████████████▎                  | 26.0M/51.1M [00:50&lt;00:48, 519kB/s]
- 51%|███████████████████▍                  | 26.1M/51.1M [00:50&lt;00:46, 535kB/s]
- 51%|███████████████████▍                  | 26.2M/51.1M [00:51&lt;00:44, 557kB/s]
- 51%|███████████████████▌                  | 26.2M/51.1M [00:51&lt;00:44, 556kB/s]
- 51%|███████████████████▌                  | 26.3M/51.1M [00:51&lt;00:49, 504kB/s]
- 52%|███████████████████▌                  | 26.4M/51.1M [00:51&lt;00:46, 527kB/s]
- 52%|███████████████████▋                  | 26.4M/51.1M [00:51&lt;00:46, 527kB/s]
- 52%|███████████████████▋                  | 26.5M/51.1M [00:51&lt;00:46, 524kB/s]
- 52%|███████████████████▋                  | 26.5M/51.1M [00:51&lt;00:47, 518kB/s]
- 52%|███████████████████▊                  | 26.6M/51.1M [00:51&lt;00:49, 493kB/s]
- 52%|███████████████████▊                  | 26.6M/51.1M [00:52&lt;00:48, 503kB/s]
- 52%|███████████████████▊                  | 26.7M/51.1M [00:52&lt;00:47, 515kB/s]
- 52%|███████████████████▉                  | 26.8M/51.1M [00:52&lt;00:46, 528kB/s]
- 53%|███████████████████▉                  | 26.8M/51.1M [00:52&lt;00:44, 543kB/s]
- 53%|████████████████████                  | 26.9M/51.1M [00:52&lt;00:44, 542kB/s]
- 53%|████████████████████                  | 27.0M/51.1M [00:52&lt;00:43, 555kB/s]
- 53%|████████████████████                  | 27.0M/51.1M [00:52&lt;00:52, 456kB/s]
- 53%|████████████████████▏                 | 27.1M/51.1M [00:52&lt;00:43, 547kB/s]
- 53%|████████████████████▏                 | 27.2M/51.1M [00:53&lt;00:45, 528kB/s]
- 53%|████████████████████▎                 | 27.2M/51.1M [00:53&lt;00:45, 530kB/s]
- 53%|████████████████████▎                 | 27.3M/51.1M [00:53&lt;00:49, 478kB/s]
- 54%|████████████████████▎                 | 27.4M/51.1M [00:53&lt;00:50, 467kB/s]
- 54%|████████████████████▍                 | 27.4M/51.1M [00:53&lt;00:51, 463kB/s]
- 54%|████████████████████▍                 | 27.5M/51.1M [00:53&lt;00:50, 466kB/s]
- 54%|████████████████████▍                 | 27.5M/51.1M [00:53&lt;00:49, 474kB/s]
- 54%|████████████████████▌                 | 27.6M/51.1M [00:53&lt;00:49, 478kB/s]
- 54%|████████████████████▌                 | 27.6M/51.1M [00:54&lt;00:47, 491kB/s]
- 54%|████████████████████▌                 | 27.7M/51.1M [00:54&lt;00:46, 503kB/s]
- 54%|████████████████████▋                 | 27.8M/51.1M [00:54&lt;00:45, 514kB/s]
- 54%|████████████████████▋                 | 27.8M/51.1M [00:54&lt;00:44, 521kB/s]
- 55%|████████████████████▋                 | 27.9M/51.1M [00:54&lt;00:43, 529kB/s]
- 55%|████████████████████▊                 | 28.0M/51.1M [00:54&lt;00:42, 544kB/s]
- 55%|████████████████████▊                 | 28.0M/51.1M [00:54&lt;00:41, 558kB/s]
- 55%|████████████████████▉                 | 28.1M/51.1M [00:54&lt;00:40, 569kB/s]
- 55%|████████████████████▉                 | 28.2M/51.1M [00:54&lt;00:40, 572kB/s]
- 55%|████████████████████▉                 | 28.2M/51.1M [00:55&lt;00:39, 575kB/s]
- 55%|█████████████████████                 | 28.3M/51.1M [00:55&lt;00:46, 487kB/s]
- 56%|█████████████████████                 | 28.4M/51.1M [00:55&lt;00:39, 576kB/s]
- 56%|█████████████████████▏                | 28.5M/51.1M [00:55&lt;00:39, 570kB/s]
- 56%|█████████████████████▏                | 28.5M/51.1M [00:55&lt;00:42, 527kB/s]
- 56%|█████████████████████▏                | 28.6M/51.1M [00:55&lt;00:43, 518kB/s]
- 56%|█████████████████████▎                | 28.6M/51.1M [00:55&lt;00:42, 526kB/s]
- 56%|█████████████████████▎                | 28.7M/51.1M [00:55&lt;00:41, 534kB/s]
- 56%|█████████████████████▍                | 28.8M/51.1M [00:56&lt;00:40, 545kB/s]
- 56%|█████████████████████▍                | 28.8M/51.1M [00:56&lt;00:40, 545kB/s]
- 57%|█████████████████████▍                | 28.9M/51.1M [00:56&lt;00:40, 552kB/s]
- 57%|█████████████████████▌                | 29.0M/51.1M [00:56&lt;00:46, 480kB/s]
- 57%|█████████████████████▌                | 29.0M/51.1M [00:56&lt;00:41, 534kB/s]
- 57%|█████████████████████▋                | 29.1M/51.1M [00:56&lt;00:42, 519kB/s]
- 57%|█████████████████████▋                | 29.1M/51.1M [00:56&lt;00:42, 518kB/s]
- 57%|█████████████████████▋                | 29.2M/51.1M [00:56&lt;00:42, 522kB/s]
- 57%|█████████████████████▋                | 29.2M/51.1M [00:57&lt;00:46, 470kB/s]
- 57%|█████████████████████▊                | 29.3M/51.1M [00:57&lt;00:46, 472kB/s]
- 57%|█████████████████████▊                | 29.3M/51.1M [00:57&lt;00:46, 471kB/s]
- 58%|█████████████████████▊                | 29.4M/51.1M [00:57&lt;00:44, 485kB/s]
- 58%|█████████████████████▉                | 29.5M/51.1M [00:57&lt;00:44, 483kB/s]
- 58%|█████████████████████▉                | 29.5M/51.1M [00:57&lt;00:43, 502kB/s]
- 58%|█████████████████████▉                | 29.6M/51.1M [00:57&lt;00:42, 511kB/s]
- 58%|██████████████████████                | 29.7M/51.1M [00:57&lt;00:40, 524kB/s]
- 58%|██████████████████████                | 29.7M/51.1M [00:57&lt;00:39, 538kB/s]
- 58%|██████████████████████▏               | 29.8M/51.1M [00:58&lt;00:39, 547kB/s]
- 58%|██████████████████████▏               | 29.9M/51.1M [00:58&lt;00:38, 553kB/s]
- 59%|██████████████████████▏               | 29.9M/51.1M [00:58&lt;00:37, 564kB/s]
- 59%|██████████████████████▎               | 30.0M/51.1M [00:58&lt;00:36, 572kB/s]
- 59%|██████████████████████▎               | 30.0M/51.1M [00:58&lt;00:42, 493kB/s]
- 59%|██████████████████████▍               | 30.1M/51.1M [00:58&lt;00:37, 558kB/s]
- 59%|██████████████████████▍               | 30.2M/51.1M [00:58&lt;00:37, 556kB/s]
- 59%|██████████████████████▍               | 30.3M/51.1M [00:58&lt;00:39, 522kB/s]
- 59%|██████████████████████▌               | 30.3M/51.1M [00:59&lt;00:39, 522kB/s]
- 59%|██████████████████████▌               | 30.4M/51.1M [00:59&lt;00:39, 524kB/s]
- 60%|██████████████████████▋               | 30.5M/51.1M [00:59&lt;00:38, 535kB/s]
- 60%|██████████████████████▋               | 30.5M/51.1M [00:59&lt;00:37, 549kB/s]
- 60%|██████████████████████▋               | 30.6M/51.1M [00:59&lt;00:36, 555kB/s]
- 60%|██████████████████████▊               | 30.7M/51.1M [00:59&lt;00:36, 555kB/s]
- 60%|██████████████████████▊               | 30.7M/51.1M [00:59&lt;00:35, 570kB/s]
- 60%|██████████████████████▉               | 30.8M/51.1M [00:59&lt;00:36, 562kB/s]
- 60%|██████████████████████▉               | 30.9M/51.1M [01:00&lt;00:35, 564kB/s]
- 60%|██████████████████████▉               | 30.9M/51.1M [01:00&lt;00:34, 579kB/s]
- 61%|███████████████████████               | 31.0M/51.1M [01:00&lt;00:34, 579kB/s]
- 61%|███████████████████████               | 31.0M/51.1M [01:00&lt;00:33, 595kB/s]
- 61%|███████████████████████▏              | 31.1M/51.1M [01:00&lt;00:34, 588kB/s]
- 61%|███████████████████████▏              | 31.2M/51.1M [01:00&lt;00:35, 569kB/s]
- 61%|███████████████████████▏              | 31.2M/51.1M [01:00&lt;00:35, 566kB/s]
- 61%|███████████████████████▎              | 31.3M/51.1M [01:00&lt;00:36, 544kB/s]
- 61%|███████████████████████▎              | 31.3M/51.1M [01:00&lt;00:39, 497kB/s]
- 61%|███████████████████████▎              | 31.4M/51.1M [01:01&lt;00:39, 499kB/s]
- 62%|███████████████████████▍              | 31.5M/51.1M [01:01&lt;00:38, 510kB/s]
- 62%|███████████████████████▍              | 31.5M/51.1M [01:01&lt;00:37, 520kB/s]
- 62%|███████████████████████▍              | 31.6M/51.1M [01:01&lt;00:36, 535kB/s]
- 62%|███████████████████████▌              | 31.7M/51.1M [01:01&lt;00:36, 539kB/s]
- 62%|███████████████████████▌              | 31.7M/51.1M [01:01&lt;00:35, 552kB/s]
- 62%|███████████████████████▋              | 31.8M/51.1M [01:01&lt;00:34, 561kB/s]
- 62%|███████████████████████▋              | 31.9M/51.1M [01:01&lt;00:34, 564kB/s]
- 62%|███████████████████████▋              | 31.9M/51.1M [01:01&lt;00:33, 571kB/s]
- 63%|███████████████████████▊              | 32.0M/51.1M [01:02&lt;00:33, 573kB/s]
- 63%|███████████████████████▊              | 32.1M/51.1M [01:02&lt;00:32, 580kB/s]
- 63%|███████████████████████▉              | 32.1M/51.1M [01:02&lt;00:35, 539kB/s]
- 63%|███████████████████████▉              | 32.2M/51.1M [01:02&lt;00:33, 557kB/s]
- 63%|███████████████████████▉              | 32.3M/51.1M [01:02&lt;00:34, 551kB/s]
- 63%|████████████████████████              | 32.3M/51.1M [01:02&lt;00:36, 512kB/s]
- 63%|████████████████████████              | 32.4M/51.1M [01:02&lt;00:36, 512kB/s]
- 63%|████████████████████████              | 32.4M/51.1M [01:02&lt;00:36, 512kB/s]
- 64%|████████████████████████▏             | 32.5M/51.1M [01:03&lt;00:35, 520kB/s]
- 64%|████████████████████████▏             | 32.6M/51.1M [01:03&lt;00:34, 534kB/s]
- 64%|████████████████████████▎             | 32.6M/51.1M [01:03&lt;00:34, 536kB/s]
- 64%|████████████████████████▎             | 32.7M/51.1M [01:03&lt;00:33, 546kB/s]
- 64%|████████████████████████▎             | 32.8M/51.1M [01:03&lt;00:33, 555kB/s]
- 64%|████████████████████████▍             | 32.8M/51.1M [01:03&lt;00:39, 462kB/s]
- 64%|████████████████████████▍             | 32.9M/51.1M [01:03&lt;00:33, 549kB/s]
- 64%|████████████████████████▌             | 33.0M/51.1M [01:03&lt;00:34, 529kB/s]
- 65%|████████████████████████▌             | 33.0M/51.1M [01:04&lt;00:34, 531kB/s]
- 65%|████████████████████████▌             | 33.1M/51.1M [01:04&lt;00:37, 479kB/s]
- 65%|████████████████████████▌             | 33.1M/51.1M [01:04&lt;00:37, 478kB/s]
- 65%|████████████████████████▋             | 33.2M/51.1M [01:04&lt;00:37, 473kB/s]
- 65%|████████████████████████▋             | 33.2M/51.1M [01:04&lt;00:39, 457kB/s]
- 65%|████████████████████████▊             | 33.3M/51.1M [01:04&lt;00:37, 472kB/s]
- 65%|████████████████████████▊             | 33.3M/51.1M [01:04&lt;00:37, 476kB/s]
- 65%|████████████████████████▊             | 33.4M/51.1M [01:04&lt;00:36, 488kB/s]
- 65%|████████████████████████▉             | 33.5M/51.1M [01:05&lt;00:34, 509kB/s]
- 66%|████████████████████████▉             | 33.5M/51.1M [01:05&lt;00:33, 521kB/s]
- 66%|████████████████████████▉             | 33.6M/51.1M [01:05&lt;00:33, 528kB/s]
- 66%|█████████████████████████             | 33.7M/51.1M [01:05&lt;00:32, 535kB/s]
- 66%|█████████████████████████             | 33.7M/51.1M [01:05&lt;00:32, 538kB/s]
- 66%|█████████████████████████             | 33.8M/51.1M [01:05&lt;00:32, 535kB/s]
- 66%|█████████████████████████▏            | 33.8M/51.1M [01:05&lt;00:33, 514kB/s]
- 66%|█████████████████████████▏            | 33.9M/51.1M [01:05&lt;00:34, 497kB/s]
- 66%|█████████████████████████▏            | 34.0M/51.1M [01:05&lt;00:34, 491kB/s]
- 67%|█████████████████████████▎            | 34.0M/51.1M [01:06&lt;00:35, 479kB/s]
- 67%|█████████████████████████▎            | 34.1M/51.1M [01:06&lt;00:35, 480kB/s]
- 67%|█████████████████████████▎            | 34.1M/51.1M [01:06&lt;00:34, 492kB/s]
- 67%|█████████████████████████▍            | 34.2M/51.1M [01:06&lt;00:33, 507kB/s]
- 67%|█████████████████████████▍            | 34.3M/51.1M [01:06&lt;00:32, 514kB/s]
- 67%|█████████████████████████▌            | 34.3M/51.1M [01:06&lt;00:31, 526kB/s]
- 67%|█████████████████████████▌            | 34.4M/51.1M [01:06&lt;00:31, 533kB/s]
- 67%|█████████████████████████▌            | 34.4M/51.1M [01:06&lt;00:36, 453kB/s]
- 68%|█████████████████████████▋            | 34.5M/51.1M [01:07&lt;00:31, 526kB/s]
- 68%|█████████████████████████▋            | 34.6M/51.1M [01:07&lt;00:32, 516kB/s]
- 68%|█████████████████████████▊            | 34.6M/51.1M [01:07&lt;00:32, 510kB/s]
- 68%|█████████████████████████▊            | 34.7M/51.1M [01:07&lt;00:32, 503kB/s]
- 68%|█████████████████████████▊            | 34.7M/51.1M [01:07&lt;00:33, 492kB/s]
- 68%|█████████████████████████▊            | 34.8M/51.1M [01:07&lt;00:35, 453kB/s]
- 68%|█████████████████████████▉            | 34.9M/51.1M [01:07&lt;00:35, 464kB/s]
- 68%|█████████████████████████▉            | 34.9M/51.1M [01:07&lt;00:34, 475kB/s]
- 68%|██████████████████████████            | 35.0M/51.1M [01:08&lt;00:33, 475kB/s]
- 69%|██████████████████████████            | 35.1M/51.1M [01:08&lt;00:32, 494kB/s]
- 69%|██████████████████████████            | 35.1M/51.1M [01:08&lt;00:30, 516kB/s]
- 69%|██████████████████████████▏           | 35.2M/51.1M [01:08&lt;00:30, 521kB/s]
- 69%|██████████████████████████▏           | 35.3M/51.1M [01:08&lt;00:29, 529kB/s]
- 69%|██████████████████████████▎           | 35.3M/51.1M [01:08&lt;00:29, 537kB/s]
- 69%|██████████████████████████▎           | 35.4M/51.1M [01:08&lt;00:28, 546kB/s]
- 69%|██████████████████████████▎           | 35.5M/51.1M [01:08&lt;00:27, 564kB/s]
- 69%|██████████████████████████▍           | 35.5M/51.1M [01:08&lt;00:27, 572kB/s]
- 70%|██████████████████████████▍           | 35.6M/51.1M [01:09&lt;00:27, 572kB/s]
- 70%|██████████████████████████▌           | 35.7M/51.1M [01:09&lt;00:27, 571kB/s]
- 70%|██████████████████████████▌           | 35.7M/51.1M [01:09&lt;00:30, 501kB/s]
- 70%|██████████████████████████▌           | 35.8M/51.1M [01:09&lt;00:27, 560kB/s]
- 70%|██████████████████████████▋           | 35.9M/51.1M [01:09&lt;00:27, 549kB/s]
- 70%|██████████████████████████▋           | 35.9M/51.1M [01:09&lt;00:29, 519kB/s]
- 70%|██████████████████████████▊           | 36.0M/51.1M [01:09&lt;00:28, 523kB/s]
- 71%|██████████████████████████▊           | 36.0M/51.1M [01:09&lt;00:28, 530kB/s]
- 71%|██████████████████████████▊           | 36.1M/51.1M [01:10&lt;00:27, 545kB/s]
- 71%|██████████████████████████▉           | 36.2M/51.1M [01:10&lt;00:27, 549kB/s]
- 71%|██████████████████████████▉           | 36.2M/51.1M [01:10&lt;00:26, 559kB/s]
- 71%|██████████████████████████▉           | 36.3M/51.1M [01:10&lt;00:26, 567kB/s]
- 71%|███████████████████████████           | 36.4M/51.1M [01:10&lt;00:25, 574kB/s]
- 71%|███████████████████████████           | 36.4M/51.1M [01:10&lt;00:24, 591kB/s]
- 71%|███████████████████████████▏          | 36.5M/51.1M [01:10&lt;00:24, 591kB/s]
- 72%|███████████████████████████▏          | 36.6M/51.1M [01:10&lt;00:24, 585kB/s]
- 72%|███████████████████████████▏          | 36.6M/51.1M [01:10&lt;00:25, 579kB/s]
- 72%|███████████████████████████▎          | 36.7M/51.1M [01:11&lt;00:26, 553kB/s]
- 72%|███████████████████████████▎          | 36.7M/51.1M [01:11&lt;00:26, 541kB/s]
- 72%|███████████████████████████▎          | 36.8M/51.1M [01:11&lt;00:28, 494kB/s]
- 72%|███████████████████████████▍          | 36.9M/51.1M [01:11&lt;00:28, 503kB/s]
- 72%|███████████████████████████▍          | 36.9M/51.1M [01:11&lt;00:28, 505kB/s]
- 72%|███████████████████████████▍          | 37.0M/51.1M [01:11&lt;00:28, 500kB/s]
- 72%|███████████████████████████▌          | 37.0M/51.1M [01:11&lt;00:27, 503kB/s]
- 73%|███████████████████████████▌          | 37.1M/51.1M [01:11&lt;00:27, 516kB/s]
- 73%|███████████████████████████▋          | 37.2M/51.1M [01:12&lt;00:26, 528kB/s]
- 73%|███████████████████████████▋          | 37.2M/51.1M [01:12&lt;00:26, 531kB/s]
- 73%|███████████████████████████▋          | 37.3M/51.1M [01:12&lt;00:25, 548kB/s]
- 73%|███████████████████████████▊          | 37.4M/51.1M [01:12&lt;00:24, 554kB/s]
- 73%|███████████████████████████▊          | 37.4M/51.1M [01:12&lt;00:24, 567kB/s]
- 73%|███████████████████████████▉          | 37.5M/51.1M [01:12&lt;00:23, 575kB/s]
- 74%|███████████████████████████▉          | 37.6M/51.1M [01:12&lt;00:23, 572kB/s]
- 74%|███████████████████████████▉          | 37.6M/51.1M [01:12&lt;00:22, 587kB/s]
- 74%|████████████████████████████          | 37.7M/51.1M [01:12&lt;00:22, 587kB/s]
- 74%|████████████████████████████          | 37.8M/51.1M [01:13&lt;00:22, 584kB/s]
- 74%|████████████████████████████          | 37.8M/51.1M [01:13&lt;00:23, 575kB/s]
- 74%|████████████████████████████▏         | 37.9M/51.1M [01:13&lt;00:23, 570kB/s]
- 74%|████████████████████████████▏         | 37.9M/51.1M [01:13&lt;00:25, 525kB/s]
- 74%|████████████████████████████▏         | 38.0M/51.1M [01:13&lt;00:25, 514kB/s]
- 74%|████████████████████████████▎         | 38.1M/51.1M [01:13&lt;00:30, 432kB/s]
- 75%|████████████████████████████▎         | 38.2M/51.1M [01:13&lt;00:25, 508kB/s]
- 75%|████████████████████████████▍         | 38.2M/51.1M [01:13&lt;00:26, 494kB/s]
- 75%|████████████████████████████▍         | 38.3M/51.1M [01:14&lt;00:27, 475kB/s]
- 75%|████████████████████████████▍         | 38.3M/51.1M [01:14&lt;00:27, 458kB/s]
- 75%|████████████████████████████▌         | 38.4M/51.1M [01:14&lt;00:28, 441kB/s]
- 75%|████████████████████████████▌         | 38.4M/51.1M [01:14&lt;00:28, 441kB/s]
- 75%|████████████████████████████▌         | 38.5M/51.1M [01:14&lt;00:28, 439kB/s]
- 75%|████████████████████████████▋         | 38.5M/51.1M [01:14&lt;00:27, 451kB/s]
- 75%|████████████████████████████▋         | 38.6M/51.1M [01:14&lt;00:27, 462kB/s]
- 76%|████████████████████████████▋         | 38.6M/51.1M [01:14&lt;00:27, 452kB/s]
- 76%|████████████████████████████▋         | 38.7M/51.1M [01:15&lt;00:26, 472kB/s]
- 76%|████████████████████████████▊         | 38.7M/51.1M [01:15&lt;00:25, 479kB/s]
- 76%|████████████████████████████▊         | 38.8M/51.1M [01:15&lt;00:24, 502kB/s]
- 76%|████████████████████████████▉         | 38.9M/51.1M [01:15&lt;00:23, 514kB/s]
- 76%|████████████████████████████▉         | 38.9M/51.1M [01:15&lt;00:23, 527kB/s]
- 76%|████████████████████████████▉         | 39.0M/51.1M [01:15&lt;00:22, 540kB/s]
- 76%|█████████████████████████████         | 39.1M/51.1M [01:15&lt;00:21, 549kB/s]
- 77%|█████████████████████████████         | 39.1M/51.1M [01:15&lt;00:21, 561kB/s]
- 77%|█████████████████████████████▏        | 39.2M/51.1M [01:15&lt;00:21, 559kB/s]
- 77%|█████████████████████████████▏        | 39.3M/51.1M [01:16&lt;00:24, 480kB/s]
- 77%|█████████████████████████████▎        | 39.4M/51.1M [01:16&lt;00:21, 549kB/s]
- 77%|█████████████████████████████▎        | 39.4M/51.1M [01:16&lt;00:21, 545kB/s]
- 77%|█████████████████████████████▎        | 39.5M/51.1M [01:16&lt;00:21, 539kB/s]
- 77%|█████████████████████████████▍        | 39.5M/51.1M [01:16&lt;00:22, 504kB/s]
- 77%|█████████████████████████████▍        | 39.6M/51.1M [01:16&lt;00:22, 501kB/s]
- 78%|█████████████████████████████▍        | 39.6M/51.1M [01:16&lt;00:22, 511kB/s]
- 78%|█████████████████████████████▌        | 39.7M/51.1M [01:16&lt;00:21, 520kB/s]
- 78%|█████████████████████████████▌        | 39.8M/51.1M [01:17&lt;00:21, 523kB/s]
- 78%|█████████████████████████████▌        | 39.8M/51.1M [01:17&lt;00:20, 541kB/s]
- 78%|█████████████████████████████▋        | 39.9M/51.1M [01:17&lt;00:20, 556kB/s]
- 78%|█████████████████████████████▋        | 40.0M/51.1M [01:17&lt;00:19, 561kB/s]
- 78%|█████████████████████████████▊        | 40.0M/51.1M [01:17&lt;00:19, 562kB/s]
- 78%|█████████████████████████████▊        | 40.1M/51.1M [01:17&lt;00:19, 567kB/s]
- 79%|█████████████████████████████▊        | 40.2M/51.1M [01:17&lt;00:19, 567kB/s]
- 79%|█████████████████████████████▉        | 40.2M/51.1M [01:17&lt;00:19, 564kB/s]
- 79%|█████████████████████████████▉        | 40.3M/51.1M [01:18&lt;00:19, 547kB/s]
- 79%|██████████████████████████████        | 40.4M/51.1M [01:18&lt;00:20, 533kB/s]
- 79%|██████████████████████████████        | 40.4M/51.1M [01:18&lt;00:21, 510kB/s]
- 79%|██████████████████████████████        | 40.5M/51.1M [01:18&lt;00:21, 486kB/s]
- 79%|██████████████████████████████▏       | 40.5M/51.1M [01:18&lt;00:21, 488kB/s]
- 79%|██████████████████████████████▏       | 40.6M/51.1M [01:18&lt;00:20, 501kB/s]
- 80%|██████████████████████████████▏       | 40.7M/51.1M [01:18&lt;00:20, 504kB/s]
- 80%|██████████████████████████████▎       | 40.7M/51.1M [01:18&lt;00:20, 506kB/s]
- 80%|██████████████████████████████▎       | 40.8M/51.1M [01:18&lt;00:19, 518kB/s]
- 80%|██████████████████████████████▎       | 40.8M/51.1M [01:19&lt;00:19, 526kB/s]
- 80%|██████████████████████████████▍       | 40.9M/51.1M [01:19&lt;00:18, 537kB/s]
- 80%|██████████████████████████████▍       | 41.0M/51.1M [01:19&lt;00:18, 546kB/s]
- 80%|██████████████████████████████▌       | 41.0M/51.1M [01:19&lt;00:18, 551kB/s]
- 80%|██████████████████████████████▌       | 41.1M/51.1M [01:19&lt;00:17, 564kB/s]
- 81%|██████████████████████████████▌       | 41.2M/51.1M [01:19&lt;00:17, 564kB/s]
- 81%|██████████████████████████████▋       | 41.2M/51.1M [01:19&lt;00:18, 523kB/s]
- 81%|██████████████████████████████▋       | 41.3M/51.1M [01:19&lt;00:17, 546kB/s]
- 81%|██████████████████████████████▊       | 41.4M/51.1M [01:20&lt;00:18, 528kB/s]
- 81%|██████████████████████████████▊       | 41.4M/51.1M [01:20&lt;00:19, 502kB/s]
- 81%|██████████████████████████████▊       | 41.5M/51.1M [01:20&lt;00:19, 495kB/s]
- 81%|██████████████████████████████▉       | 41.5M/51.1M [01:20&lt;00:19, 501kB/s]
- 81%|██████████████████████████████▉       | 41.6M/51.1M [01:20&lt;00:18, 512kB/s]
- 82%|██████████████████████████████▉       | 41.7M/51.1M [01:20&lt;00:17, 528kB/s]
- 82%|███████████████████████████████       | 41.7M/51.1M [01:20&lt;00:17, 535kB/s]
- 82%|███████████████████████████████       | 41.8M/51.1M [01:20&lt;00:17, 543kB/s]
- 82%|███████████████████████████████▏      | 41.9M/51.1M [01:21&lt;00:16, 553kB/s]
- 82%|███████████████████████████████▏      | 41.9M/51.1M [01:21&lt;00:16, 562kB/s]
- 82%|███████████████████████████████▏      | 42.0M/51.1M [01:21&lt;00:15, 572kB/s]
- 82%|███████████████████████████████▎      | 42.1M/51.1M [01:21&lt;00:15, 579kB/s]
- 82%|███████████████████████████████▎      | 42.1M/51.1M [01:21&lt;00:15, 583kB/s]
- 83%|███████████████████████████████▍      | 42.2M/51.1M [01:21&lt;00:15, 576kB/s]
- 83%|███████████████████████████████▍      | 42.3M/51.1M [01:21&lt;00:16, 550kB/s]
- 83%|███████████████████████████████▍      | 42.3M/51.1M [01:21&lt;00:15, 551kB/s]
- 83%|███████████████████████████████▌      | 42.4M/51.1M [01:21&lt;00:15, 549kB/s]
- 83%|███████████████████████████████▌      | 42.4M/51.1M [01:22&lt;00:15, 543kB/s]
- 83%|███████████████████████████████▌      | 42.5M/51.1M [01:22&lt;00:17, 487kB/s]
- 83%|███████████████████████████████▋      | 42.5M/51.1M [01:22&lt;00:17, 496kB/s]
- 83%|███████████████████████████████▋      | 42.6M/51.1M [01:22&lt;00:16, 509kB/s]
- 84%|███████████████████████████████▋      | 42.7M/51.1M [01:22&lt;00:16, 511kB/s]
- 84%|███████████████████████████████▊      | 42.7M/51.1M [01:22&lt;00:17, 477kB/s]
- 84%|███████████████████████████████▊      | 42.8M/51.1M [01:22&lt;00:18, 456kB/s]
- 84%|███████████████████████████████▊      | 42.8M/51.1M [01:22&lt;00:18, 438kB/s]
- 84%|███████████████████████████████▉      | 42.9M/51.1M [01:23&lt;00:19, 431kB/s]
- 84%|███████████████████████████████▉      | 42.9M/51.1M [01:23&lt;00:18, 435kB/s]
- 84%|███████████████████████████████▉      | 43.0M/51.1M [01:23&lt;00:18, 436kB/s]
- 84%|███████████████████████████████▉      | 43.0M/51.1M [01:23&lt;00:18, 445kB/s]
- 84%|████████████████████████████████      | 43.1M/51.1M [01:23&lt;00:18, 441kB/s]
- 84%|████████████████████████████████      | 43.1M/51.1M [01:23&lt;00:17, 460kB/s]
- 84%|████████████████████████████████      | 43.2M/51.1M [01:23&lt;00:17, 465kB/s]
- 85%|████████████████████████████████▏     | 43.2M/51.1M [01:23&lt;00:16, 471kB/s]
- 85%|████████████████████████████████▏     | 43.3M/51.1M [01:23&lt;00:16, 487kB/s]
- 85%|████████████████████████████████▏     | 43.4M/51.1M [01:24&lt;00:15, 496kB/s]
- 85%|████████████████████████████████▎     | 43.4M/51.1M [01:24&lt;00:15, 510kB/s]
- 85%|████████████████████████████████▎     | 43.5M/51.1M [01:24&lt;00:14, 523kB/s]
- 85%|████████████████████████████████▍     | 43.6M/51.1M [01:24&lt;00:14, 536kB/s]
- 85%|████████████████████████████████▍     | 43.6M/51.1M [01:24&lt;00:13, 549kB/s]
- 85%|████████████████████████████████▍     | 43.7M/51.1M [01:24&lt;00:13, 553kB/s]
- 86%|████████████████████████████████▌     | 43.8M/51.1M [01:24&lt;00:13, 560kB/s]
- 86%|████████████████████████████████▌     | 43.8M/51.1M [01:24&lt;00:12, 566kB/s]
- 86%|████████████████████████████████▋     | 43.9M/51.1M [01:25&lt;00:14, 492kB/s]
- 86%|████████████████████████████████▋     | 44.0M/51.1M [01:25&lt;00:12, 566kB/s]
- 86%|████████████████████████████████▋     | 44.0M/51.1M [01:25&lt;00:12, 560kB/s]
- 86%|████████████████████████████████▊     | 44.1M/51.1M [01:25&lt;00:13, 516kB/s]
- 86%|████████████████████████████████▊     | 44.2M/51.1M [01:25&lt;00:13, 521kB/s]
- 87%|████████████████████████████████▉     | 44.2M/51.1M [01:25&lt;00:13, 524kB/s]
- 87%|████████████████████████████████▉     | 44.3M/51.1M [01:25&lt;00:12, 531kB/s]
- 87%|████████████████████████████████▉     | 44.4M/51.1M [01:25&lt;00:12, 542kB/s]
- 87%|█████████████████████████████████     | 44.4M/51.1M [01:25&lt;00:12, 551kB/s]
- 87%|█████████████████████████████████     | 44.5M/51.1M [01:26&lt;00:11, 557kB/s]
- 87%|█████████████████████████████████     | 44.5M/51.1M [01:26&lt;00:11, 567kB/s]
- 87%|█████████████████████████████████▏    | 44.6M/51.1M [01:26&lt;00:11, 570kB/s]
- 87%|█████████████████████████████████▏    | 44.7M/51.1M [01:26&lt;00:11, 568kB/s]
- 88%|█████████████████████████████████▎    | 44.7M/51.1M [01:26&lt;00:12, 500kB/s]
- 88%|█████████████████████████████████▎    | 44.8M/51.1M [01:26&lt;00:10, 575kB/s]
- 88%|█████████████████████████████████▎    | 44.9M/51.1M [01:26&lt;00:10, 566kB/s]
- 88%|█████████████████████████████████▍    | 44.9M/51.1M [01:26&lt;00:12, 513kB/s]
- 88%|█████████████████████████████████▍    | 45.0M/51.1M [01:27&lt;00:11, 514kB/s]
- 88%|█████████████████████████████████▍    | 45.1M/51.1M [01:27&lt;00:12, 487kB/s]
- 88%|█████████████████████████████████▌    | 45.1M/51.1M [01:27&lt;00:12, 487kB/s]
- 88%|█████████████████████████████████▌    | 45.2M/51.1M [01:27&lt;00:12, 492kB/s]
- 89%|█████████████████████████████████▋    | 45.3M/51.1M [01:27&lt;00:11, 497kB/s]
- 89%|█████████████████████████████████▋    | 45.3M/51.1M [01:27&lt;00:11, 509kB/s]
- 89%|█████████████████████████████████▋    | 45.4M/51.1M [01:27&lt;00:10, 524kB/s]
- 89%|█████████████████████████████████▊    | 45.4M/51.1M [01:27&lt;00:10, 538kB/s]
- 89%|█████████████████████████████████▊    | 45.5M/51.1M [01:28&lt;00:10, 547kB/s]
- 89%|█████████████████████████████████▉    | 45.6M/51.1M [01:28&lt;00:09, 561kB/s]
- 89%|█████████████████████████████████▉    | 45.6M/51.1M [01:28&lt;00:09, 565kB/s]
- 89%|█████████████████████████████████▉    | 45.7M/51.1M [01:28&lt;00:09, 575kB/s]
- 90%|██████████████████████████████████    | 45.8M/51.1M [01:28&lt;00:09, 580kB/s]
- 90%|██████████████████████████████████    | 45.8M/51.1M [01:28&lt;00:09, 571kB/s]
- 90%|██████████████████████████████████▏   | 45.9M/51.1M [01:28&lt;00:09, 569kB/s]
- 90%|██████████████████████████████████▏   | 46.0M/51.1M [01:28&lt;00:09, 544kB/s]
- 90%|██████████████████████████████████▏   | 46.0M/51.1M [01:28&lt;00:09, 537kB/s]
- 90%|██████████████████████████████████▎   | 46.1M/51.1M [01:29&lt;00:09, 537kB/s]
- 90%|██████████████████████████████████▎   | 46.2M/51.1M [01:29&lt;00:09, 522kB/s]
- 90%|██████████████████████████████████▎   | 46.2M/51.1M [01:29&lt;00:09, 520kB/s]
- 91%|██████████████████████████████████▍   | 46.3M/51.1M [01:29&lt;00:09, 526kB/s]
- 91%|██████████████████████████████████▍   | 46.4M/51.1M [01:29&lt;00:08, 542kB/s]
- 91%|██████████████████████████████████▌   | 46.4M/51.1M [01:29&lt;00:08, 543kB/s]
- 91%|██████████████████████████████████▌   | 46.5M/51.1M [01:29&lt;00:08, 556kB/s]
- 91%|██████████████████████████████████▌   | 46.5M/51.1M [01:29&lt;00:08, 556kB/s]
- 91%|██████████████████████████████████▋   | 46.6M/51.1M [01:30&lt;00:07, 568kB/s]
- 91%|██████████████████████████████████▋   | 46.7M/51.1M [01:30&lt;00:07, 569kB/s]
- 91%|██████████████████████████████████▋   | 46.7M/51.1M [01:30&lt;00:08, 510kB/s]
- 92%|██████████████████████████████████▊   | 46.8M/51.1M [01:30&lt;00:07, 560kB/s]
- 92%|██████████████████████████████████▊   | 46.9M/51.1M [01:30&lt;00:07, 559kB/s]
- 92%|██████████████████████████████████▉   | 46.9M/51.1M [01:30&lt;00:07, 543kB/s]
- 92%|██████████████████████████████████▉   | 47.0M/51.1M [01:30&lt;00:08, 508kB/s]
- 92%|██████████████████████████████████▉   | 47.1M/51.1M [01:30&lt;00:08, 492kB/s]
- 92%|███████████████████████████████████   | 47.1M/51.1M [01:31&lt;00:08, 496kB/s]
- 92%|███████████████████████████████████   | 47.2M/51.1M [01:31&lt;00:07, 502kB/s]
- 92%|███████████████████████████████████▏  | 47.3M/51.1M [01:31&lt;00:07, 511kB/s]
- 93%|███████████████████████████████████▏  | 47.3M/51.1M [01:31&lt;00:07, 522kB/s]
- 93%|███████████████████████████████████▏  | 47.4M/51.1M [01:31&lt;00:07, 531kB/s]
- 93%|███████████████████████████████████▎  | 47.4M/51.1M [01:31&lt;00:06, 540kB/s]
- 93%|███████████████████████████████████▎  | 47.5M/51.1M [01:31&lt;00:06, 549kB/s]
- 93%|███████████████████████████████████▎  | 47.6M/51.1M [01:31&lt;00:06, 554kB/s]
- 93%|███████████████████████████████████▍  | 47.6M/51.1M [01:31&lt;00:06, 561kB/s]
- 93%|███████████████████████████████████▍  | 47.7M/51.1M [01:32&lt;00:06, 560kB/s]
- 93%|███████████████████████████████████▌  | 47.8M/51.1M [01:32&lt;00:06, 525kB/s]
- 94%|███████████████████████████████████▌  | 47.8M/51.1M [01:32&lt;00:05, 557kB/s]
- 94%|███████████████████████████████████▌  | 47.9M/51.1M [01:32&lt;00:05, 549kB/s]
- 94%|███████████████████████████████████▋  | 48.0M/51.1M [01:32&lt;00:06, 516kB/s]
- 94%|███████████████████████████████████▋  | 48.0M/51.1M [01:32&lt;00:05, 517kB/s]
- 94%|███████████████████████████████████▊  | 48.1M/51.1M [01:32&lt;00:05, 523kB/s]
- 94%|███████████████████████████████████▊  | 48.2M/51.1M [01:32&lt;00:05, 534kB/s]
- 94%|███████████████████████████████████▊  | 48.2M/51.1M [01:33&lt;00:05, 544kB/s]
- 94%|███████████████████████████████████▉  | 48.3M/51.1M [01:33&lt;00:05, 544kB/s]
- 95%|███████████████████████████████████▉  | 48.3M/51.1M [01:33&lt;00:05, 490kB/s]
- 95%|███████████████████████████████████▉  | 48.4M/51.1M [01:33&lt;00:05, 526kB/s]
- 95%|████████████████████████████████████  | 48.5M/51.1M [01:33&lt;00:05, 499kB/s]
- 95%|████████████████████████████████████  | 48.5M/51.1M [01:33&lt;00:05, 499kB/s]
- 95%|████████████████████████████████████  | 48.6M/51.1M [01:33&lt;00:05, 485kB/s]
- 95%|████████████████████████████████████▏ | 48.6M/51.1M [01:33&lt;00:05, 484kB/s]
- 95%|████████████████████████████████████▏ | 48.7M/51.1M [01:34&lt;00:05, 484kB/s]
- 95%|████████████████████████████████████▏ | 48.7M/51.1M [01:34&lt;00:04, 483kB/s]
- 95%|████████████████████████████████████▎ | 48.8M/51.1M [01:34&lt;00:04, 481kB/s]
- 96%|████████████████████████████████████▎ | 48.8M/51.1M [01:34&lt;00:05, 455kB/s]
- 96%|████████████████████████████████████▎ | 48.9M/51.1M [01:34&lt;00:04, 480kB/s]
- 96%|████████████████████████████████████▍ | 49.0M/51.1M [01:34&lt;00:04, 499kB/s]
- 96%|████████████████████████████████████▍ | 49.0M/51.1M [01:34&lt;00:04, 509kB/s]
- 96%|████████████████████████████████████▍ | 49.1M/51.1M [01:34&lt;00:03, 522kB/s]
- 96%|████████████████████████████████████▌ | 49.2M/51.1M [01:34&lt;00:03, 534kB/s]
- 96%|████████████████████████████████████▌ | 49.2M/51.1M [01:35&lt;00:03, 541kB/s]
- 96%|████████████████████████████████████▋ | 49.3M/51.1M [01:35&lt;00:03, 550kB/s]
- 97%|████████████████████████████████████▋ | 49.3M/51.1M [01:35&lt;00:03, 560kB/s]
- 97%|████████████████████████████████████▋ | 49.4M/51.1M [01:35&lt;00:02, 575kB/s]
- 97%|████████████████████████████████████▊ | 49.5M/51.1M [01:35&lt;00:02, 585kB/s]
- 97%|████████████████████████████████████▊ | 49.5M/51.1M [01:35&lt;00:03, 500kB/s]
- 97%|████████████████████████████████████▉ | 49.6M/51.1M [01:35&lt;00:02, 578kB/s]
- 97%|████████████████████████████████████▉ | 49.7M/51.1M [01:35&lt;00:02, 567kB/s]
- 97%|████████████████████████████████████▉ | 49.7M/51.1M [01:36&lt;00:02, 531kB/s]
- 97%|█████████████████████████████████████ | 49.8M/51.1M [01:36&lt;00:02, 522kB/s]
- 98%|█████████████████████████████████████ | 49.9M/51.1M [01:36&lt;00:02, 527kB/s]
- 98%|█████████████████████████████████████▏| 49.9M/51.1M [01:36&lt;00:02, 536kB/s]
- 98%|█████████████████████████████████████▏| 50.0M/51.1M [01:36&lt;00:02, 539kB/s]
- 98%|█████████████████████████████████████▏| 50.1M/51.1M [01:36&lt;00:01, 549kB/s]
- 98%|█████████████████████████████████████▎| 50.1M/51.1M [01:36&lt;00:01, 554kB/s]
- 98%|█████████████████████████████████████▎| 50.2M/51.1M [01:36&lt;00:01, 467kB/s]
- 98%|█████████████████████████████████████▍| 50.3M/51.1M [01:37&lt;00:01, 559kB/s]
- 98%|█████████████████████████████████████▍| 50.3M/51.1M [01:37&lt;00:01, 551kB/s]
- 99%|█████████████████████████████████████▍| 50.4M/51.1M [01:37&lt;00:01, 498kB/s]
- 99%|█████████████████████████████████████▌| 50.5M/51.1M [01:37&lt;00:01, 503kB/s]
- 99%|█████████████████████████████████████▌| 50.5M/51.1M [01:37&lt;00:01, 500kB/s]
- 99%|█████████████████████████████████████▌| 50.6M/51.1M [01:37&lt;00:01, 500kB/s]
- 99%|█████████████████████████████████████▌| 50.6M/51.1M [01:37&lt;00:01, 503kB/s]
- 99%|█████████████████████████████████████▋| 50.7M/51.1M [01:37&lt;00:00, 475kB/s]
- 99%|█████████████████████████████████████▋| 50.7M/51.1M [01:37&lt;00:00, 485kB/s]
- 99%|█████████████████████████████████████▊| 50.8M/51.1M [01:38&lt;00:00, 498kB/s]
-100%|█████████████████████████████████████▊| 50.9M/51.1M [01:38&lt;00:00, 516kB/s]
-100%|█████████████████████████████████████▊| 50.9M/51.1M [01:38&lt;00:00, 527kB/s]
-100%|█████████████████████████████████████▉| 51.0M/51.1M [01:38&lt;00:00, 535kB/s]
-100%|█████████████████████████████████████▉| 51.1M/51.1M [01:38&lt;00:00, 547kB/s]
+  0%|                                      | 49.2k/51.1M [00:00&lt;01:48, 469kB/s]
+  0%|                                      | 98.3k/51.1M [00:00&lt;02:29, 342kB/s]
+  0%|▏                                      | 229k/51.1M [00:00&lt;01:16, 663kB/s]
+  1%|▏                                      | 302k/51.1M [00:00&lt;01:14, 681kB/s]
+  1%|▎                                      | 375k/51.1M [00:00&lt;01:28, 571kB/s]
+  1%|▎                                      | 475k/51.1M [00:00&lt;01:15, 671kB/s]
+  1%|▍                                      | 547k/51.1M [00:00&lt;01:27, 575kB/s]
+  1%|▍                                      | 639k/51.1M [00:01&lt;01:20, 626kB/s]
+  1%|▌                                      | 706k/51.1M [00:01&lt;01:24, 599kB/s]
+  2%|▌                                      | 770k/51.1M [00:01&lt;01:25, 589kB/s]
+  2%|▋                                      | 836k/51.1M [00:01&lt;01:26, 584kB/s]
+  2%|▋                                      | 901k/51.1M [00:01&lt;01:25, 590kB/s]
+  2%|▋                                      | 967k/51.1M [00:01&lt;01:25, 587kB/s]
+  2%|▊                                     | 1.03M/51.1M [00:01&lt;01:25, 589kB/s]
+  2%|▊                                     | 1.10M/51.1M [00:01&lt;01:23, 597kB/s]
+  2%|▊                                     | 1.16M/51.1M [00:01&lt;01:22, 602kB/s]
+  2%|▉                                     | 1.23M/51.1M [00:02&lt;01:22, 606kB/s]
+  3%|▉                                     | 1.29M/51.1M [00:02&lt;01:20, 615kB/s]
+  3%|█                                     | 1.38M/51.1M [00:02&lt;01:19, 629kB/s]
+  3%|█                                     | 1.44M/51.1M [00:02&lt;01:18, 633kB/s]
+  3%|█▏                                    | 1.52M/51.1M [00:02&lt;01:15, 653kB/s]
+  3%|█▏                                    | 1.59M/51.1M [00:02&lt;01:16, 643kB/s]
+  3%|█▏                                    | 1.65M/51.1M [00:02&lt;01:28, 561kB/s]
+  3%|█▎                                    | 1.75M/51.1M [00:02&lt;01:18, 629kB/s]
+  4%|█▎                                    | 1.82M/51.1M [00:03&lt;01:21, 603kB/s]
+  4%|█▍                                    | 1.88M/51.1M [00:03&lt;01:23, 593kB/s]
+  4%|█▍                                    | 1.95M/51.1M [00:03&lt;01:22, 594kB/s]
+  4%|█▍                                    | 2.02M/51.1M [00:03&lt;01:22, 597kB/s]
+  4%|█▌                                    | 2.08M/51.1M [00:03&lt;01:20, 607kB/s]
+  4%|█▌                                    | 2.15M/51.1M [00:03&lt;01:19, 620kB/s]
+  4%|█▋                                    | 2.21M/51.1M [00:03&lt;01:18, 625kB/s]
+  4%|█▋                                    | 2.29M/51.1M [00:03&lt;01:16, 637kB/s]
+  5%|█▊                                    | 2.38M/51.1M [00:03&lt;01:15, 649kB/s]
+  5%|█▊                                    | 2.46M/51.1M [00:04&lt;01:13, 664kB/s]
+  5%|█▉                                    | 2.52M/51.1M [00:04&lt;01:13, 663kB/s]
+  5%|█▉                                    | 2.61M/51.1M [00:04&lt;01:12, 666kB/s]
+  5%|█▉                                    | 2.69M/51.1M [00:04&lt;01:12, 665kB/s]
+  5%|██                                    | 2.75M/51.1M [00:04&lt;01:13, 660kB/s]
+  6%|██                                    | 2.82M/51.1M [00:04&lt;01:21, 589kB/s]
+  6%|██▏                                   | 2.92M/51.1M [00:04&lt;01:16, 633kB/s]
+  6%|██▏                                   | 2.98M/51.1M [00:04&lt;01:19, 604kB/s]
+  6%|██▎                                   | 3.05M/51.1M [00:04&lt;01:20, 596kB/s]
+  6%|██▎                                   | 3.11M/51.1M [00:05&lt;01:20, 597kB/s]
+  6%|██▎                                   | 3.18M/51.1M [00:05&lt;01:19, 600kB/s]
+  6%|██▍                                   | 3.24M/51.1M [00:05&lt;01:19, 606kB/s]
+  6%|██▍                                   | 3.31M/51.1M [00:05&lt;01:18, 612kB/s]
+  7%|██▌                                   | 3.38M/51.1M [00:05&lt;01:17, 616kB/s]
+  7%|██▌                                   | 3.44M/51.1M [00:05&lt;01:16, 626kB/s]
+  7%|██▌                                   | 3.51M/51.1M [00:05&lt;01:15, 627kB/s]
+  7%|██▋                                   | 3.59M/51.1M [00:05&lt;01:13, 644kB/s]
+  7%|██▋                                   | 3.65M/51.1M [00:05&lt;01:13, 644kB/s]
+  7%|██▊                                   | 3.74M/51.1M [00:06&lt;01:11, 659kB/s]
+  7%|██▊                                   | 3.80M/51.1M [00:06&lt;01:11, 660kB/s]
+  8%|██▉                                   | 3.87M/51.1M [00:06&lt;01:11, 659kB/s]
+  8%|██▉                                   | 3.94M/51.1M [00:06&lt;01:11, 656kB/s]
+  8%|██▉                                   | 4.00M/51.1M [00:06&lt;01:14, 635kB/s]
+  8%|███                                   | 4.07M/51.1M [00:06&lt;01:17, 606kB/s]
+  8%|███                                   | 4.13M/51.1M [00:06&lt;01:21, 574kB/s]
+  8%|███                                   | 4.19M/51.1M [00:06&lt;01:21, 574kB/s]
+  8%|███▏                                  | 4.26M/51.1M [00:06&lt;01:21, 578kB/s]
+  8%|███▏                                  | 4.33M/51.1M [00:07&lt;01:20, 582kB/s]
+  9%|███▎                                  | 4.39M/51.1M [00:07&lt;01:18, 594kB/s]
+  9%|███▎                                  | 4.46M/51.1M [00:07&lt;01:17, 600kB/s]
+  9%|███▎                                  | 4.52M/51.1M [00:07&lt;01:16, 606kB/s]
+  9%|███▍                                  | 4.59M/51.1M [00:07&lt;01:15, 614kB/s]
+  9%|███▍                                  | 4.65M/51.1M [00:07&lt;01:14, 620kB/s]
+  9%|███▌                                  | 4.73M/51.1M [00:07&lt;01:11, 647kB/s]
+  9%|███▌                                  | 4.82M/51.1M [00:07&lt;01:10, 659kB/s]
+ 10%|███▋                                  | 4.90M/51.1M [00:07&lt;01:08, 670kB/s]
+ 10%|███▋                                  | 4.98M/51.1M [00:08&lt;01:07, 683kB/s]
+ 10%|███▊                                  | 5.05M/51.1M [00:08&lt;01:07, 683kB/s]
+ 10%|███▊                                  | 5.12M/51.1M [00:08&lt;01:08, 675kB/s]
+ 10%|███▊                                  | 5.19M/51.1M [00:08&lt;01:22, 558kB/s]
+ 10%|███▉                                  | 5.29M/51.1M [00:08&lt;01:12, 632kB/s]
+ 10%|███▉                                  | 5.36M/51.1M [00:08&lt;01:16, 600kB/s]
+ 11%|████                                  | 5.42M/51.1M [00:08&lt;01:16, 598kB/s]
+ 11%|████                                  | 5.49M/51.1M [00:08&lt;01:16, 600kB/s]
+ 11%|████▏                                 | 5.55M/51.1M [00:09&lt;01:16, 599kB/s]
+ 11%|████▏                                 | 5.62M/51.1M [00:09&lt;01:14, 608kB/s]
+ 11%|████▏                                 | 5.69M/51.1M [00:09&lt;01:13, 615kB/s]
+ 11%|████▎                                 | 5.75M/51.1M [00:09&lt;01:12, 622kB/s]
+ 11%|████▎                                 | 5.82M/51.1M [00:09&lt;01:11, 629kB/s]
+ 12%|████▎                                 | 5.88M/51.1M [00:09&lt;01:11, 634kB/s]
+ 12%|████▍                                 | 5.95M/51.1M [00:09&lt;01:10, 640kB/s]
+ 12%|████▍                                 | 6.03M/51.1M [00:09&lt;01:09, 647kB/s]
+ 12%|████▌                                 | 6.09M/51.1M [00:09&lt;01:09, 645kB/s]
+ 12%|████▌                                 | 6.18M/51.1M [00:09&lt;01:07, 665kB/s]
+ 12%|████▋                                 | 6.26M/51.1M [00:10&lt;01:06, 678kB/s]
+ 12%|████▋                                 | 6.34M/51.1M [00:10&lt;01:06, 673kB/s]
+ 13%|████▊                                 | 6.42M/51.1M [00:10&lt;01:06, 673kB/s]
+ 13%|████▊                                 | 6.50M/51.1M [00:10&lt;01:06, 666kB/s]
+ 13%|████▉                                 | 6.59M/51.1M [00:10&lt;01:06, 667kB/s]
+ 13%|████▉                                 | 6.67M/51.1M [00:10&lt;01:06, 665kB/s]
+ 13%|█████                                 | 6.75M/51.1M [00:10&lt;01:06, 668kB/s]
+ 13%|█████                                 | 6.82M/51.1M [00:10&lt;01:06, 665kB/s]
+ 13%|█████                                 | 6.88M/51.1M [00:11&lt;01:09, 640kB/s]
+ 14%|█████▏                                | 6.96M/51.1M [00:11&lt;01:08, 640kB/s]
+ 14%|█████▏                                | 7.03M/51.1M [00:11&lt;01:13, 600kB/s]
+ 14%|█████▎                                | 7.09M/51.1M [00:11&lt;01:13, 601kB/s]
+ 14%|█████▎                                | 7.16M/51.1M [00:11&lt;01:12, 608kB/s]
+ 14%|█████▎                                | 7.23M/51.1M [00:11&lt;01:12, 607kB/s]
+ 14%|█████▍                                | 7.29M/51.1M [00:11&lt;01:10, 623kB/s]
+ 14%|█████▍                                | 7.37M/51.1M [00:11&lt;01:09, 630kB/s]
+ 15%|█████▌                                | 7.45M/51.1M [00:11&lt;01:07, 651kB/s]
+ 15%|█████▌                                | 7.54M/51.1M [00:12&lt;01:06, 655kB/s]
+ 15%|█████▋                                | 7.60M/51.1M [00:12&lt;01:06, 652kB/s]
+ 15%|█████▋                                | 7.68M/51.1M [00:12&lt;01:06, 658kB/s]
+ 15%|█████▊                                | 7.77M/51.1M [00:12&lt;01:04, 674kB/s]
+ 15%|█████▊                                | 7.85M/51.1M [00:12&lt;01:04, 671kB/s]
+ 15%|█████▉                                | 7.92M/51.1M [00:12&lt;01:06, 652kB/s]
+ 16%|█████▉                                | 7.98M/51.1M [00:12&lt;01:07, 644kB/s]
+ 16%|█████▉                                | 8.05M/51.1M [00:12&lt;01:11, 598kB/s]
+ 16%|██████                                | 8.11M/51.1M [00:12&lt;01:12, 595kB/s]
+ 16%|██████                                | 8.18M/51.1M [00:13&lt;01:13, 586kB/s]
+ 16%|██████▏                               | 8.24M/51.1M [00:13&lt;01:12, 594kB/s]
+ 16%|██████▏                               | 8.31M/51.1M [00:13&lt;01:12, 594kB/s]
+ 16%|██████▏                               | 8.37M/51.1M [00:13&lt;01:11, 594kB/s]
+ 17%|██████▎                               | 8.44M/51.1M [00:13&lt;01:10, 603kB/s]
+ 17%|██████▎                               | 8.50M/51.1M [00:13&lt;01:10, 609kB/s]
+ 17%|██████▎                               | 8.57M/51.1M [00:13&lt;01:09, 608kB/s]
+ 17%|██████▍                               | 8.63M/51.1M [00:13&lt;01:08, 617kB/s]
+ 17%|██████▍                               | 8.70M/51.1M [00:13&lt;01:07, 625kB/s]
+ 17%|██████▌                               | 8.78M/51.1M [00:14&lt;01:07, 632kB/s]
+ 17%|██████▌                               | 8.85M/51.1M [00:14&lt;01:07, 631kB/s]
+ 17%|██████▋                               | 8.93M/51.1M [00:14&lt;01:04, 652kB/s]
+ 18%|██████▋                               | 9.01M/51.1M [00:14&lt;01:03, 664kB/s]
+ 18%|██████▋                               | 9.08M/51.1M [00:14&lt;01:03, 658kB/s]
+ 18%|██████▊                               | 9.16M/51.1M [00:14&lt;01:04, 647kB/s]
+ 18%|██████▊                               | 9.22M/51.1M [00:14&lt;01:10, 598kB/s]
+ 18%|██████▉                               | 9.29M/51.1M [00:14&lt;01:11, 584kB/s]
+ 18%|██████▉                               | 9.36M/51.1M [00:15&lt;01:11, 585kB/s]
+ 18%|███████                               | 9.42M/51.1M [00:15&lt;01:11, 584kB/s]
+ 19%|███████                               | 9.49M/51.1M [00:15&lt;01:10, 594kB/s]
+ 19%|███████                               | 9.55M/51.1M [00:15&lt;01:08, 610kB/s]
+ 19%|███████▏                              | 9.62M/51.1M [00:15&lt;01:07, 619kB/s]
+ 19%|███████▏                              | 9.68M/51.1M [00:15&lt;01:07, 616kB/s]
+ 19%|███████▏                              | 9.75M/51.1M [00:15&lt;01:06, 625kB/s]
+ 19%|███████▎                              | 9.81M/51.1M [00:15&lt;01:05, 626kB/s]
+ 19%|███████▎                              | 9.90M/51.1M [00:15&lt;01:03, 647kB/s]
+ 20%|███████▍                              | 9.98M/51.1M [00:15&lt;01:01, 665kB/s]
+ 20%|███████▍                              | 10.1M/51.1M [00:16&lt;01:00, 678kB/s]
+ 20%|███████▌                              | 10.1M/51.1M [00:16&lt;01:00, 679kB/s]
+ 20%|███████▌                              | 10.2M/51.1M [00:16&lt;00:59, 686kB/s]
+ 20%|███████▋                              | 10.3M/51.1M [00:16&lt;00:59, 685kB/s]
+ 20%|███████▋                              | 10.4M/51.1M [00:16&lt;01:00, 669kB/s]
+ 20%|███████▊                              | 10.4M/51.1M [00:16&lt;01:12, 557kB/s]
+ 21%|███████▊                              | 10.6M/51.1M [00:16&lt;01:01, 655kB/s]
+ 21%|███████▉                              | 10.6M/51.1M [00:16&lt;01:04, 629kB/s]
+ 21%|███████▉                              | 10.7M/51.1M [00:17&lt;01:06, 611kB/s]
+ 21%|███████▉                              | 10.7M/51.1M [00:17&lt;01:06, 603kB/s]
+ 21%|████████                              | 10.8M/51.1M [00:17&lt;01:07, 601kB/s]
+ 21%|████████                              | 10.9M/51.1M [00:17&lt;01:05, 610kB/s]
+ 21%|████████▏                             | 10.9M/51.1M [00:17&lt;01:04, 618kB/s]
+ 22%|████████▏                             | 11.0M/51.1M [00:17&lt;01:03, 634kB/s]
+ 22%|████████▏                             | 11.1M/51.1M [00:17&lt;01:02, 636kB/s]
+ 22%|████████▎                             | 11.2M/51.1M [00:17&lt;01:01, 645kB/s]
+ 22%|████████▎                             | 11.3M/51.1M [00:18&lt;01:00, 661kB/s]
+ 22%|████████▍                             | 11.3M/51.1M [00:18&lt;01:00, 662kB/s]
+ 22%|████████▍                             | 11.4M/51.1M [00:18&lt;00:58, 673kB/s]
+ 22%|████████▌                             | 11.5M/51.1M [00:18&lt;00:59, 670kB/s]
+ 23%|████████▌                             | 11.6M/51.1M [00:18&lt;01:06, 599kB/s]
+ 23%|████████▋                             | 11.6M/51.1M [00:18&lt;01:01, 638kB/s]
+ 23%|████████▋                             | 11.7M/51.1M [00:18&lt;01:06, 596kB/s]
+ 23%|████████▋                             | 11.8M/51.1M [00:18&lt;01:06, 589kB/s]
+ 23%|████████▊                             | 11.8M/51.1M [00:18&lt;01:09, 565kB/s]
+ 23%|████████▊                             | 11.9M/51.1M [00:19&lt;01:08, 573kB/s]
+ 23%|████████▉                             | 12.0M/51.1M [00:19&lt;01:08, 574kB/s]
+ 24%|████████▉                             | 12.0M/51.1M [00:19&lt;01:07, 578kB/s]
+ 24%|████████▉                             | 12.1M/51.1M [00:19&lt;01:07, 579kB/s]
+ 24%|█████████                             | 12.2M/51.1M [00:19&lt;01:06, 585kB/s]
+ 24%|█████████                             | 12.2M/51.1M [00:19&lt;01:06, 581kB/s]
+ 24%|█████████▏                            | 12.3M/51.1M [00:19&lt;01:10, 550kB/s]
+ 24%|█████████▏                            | 12.3M/51.1M [00:19&lt;01:11, 543kB/s]
+ 24%|█████████▏                            | 12.4M/51.1M [00:20&lt;01:18, 491kB/s]
+ 24%|█████████▎                            | 12.5M/51.1M [00:20&lt;01:20, 481kB/s]
+ 24%|█████████▎                            | 12.5M/51.1M [00:20&lt;01:18, 490kB/s]
+ 25%|█████████▎                            | 12.6M/51.1M [00:20&lt;01:16, 503kB/s]
+ 25%|█████████▍                            | 12.6M/51.1M [00:20&lt;01:14, 513kB/s]
+ 25%|█████████▍                            | 12.7M/51.1M [00:20&lt;01:11, 534kB/s]
+ 25%|█████████▌                            | 12.8M/51.1M [00:20&lt;01:10, 541kB/s]
+ 25%|█████████▌                            | 12.8M/51.1M [00:20&lt;01:10, 546kB/s]
+ 25%|█████████▌                            | 12.9M/51.1M [00:20&lt;01:08, 559kB/s]
+ 25%|█████████▋                            | 13.0M/51.1M [00:21&lt;01:06, 572kB/s]
+ 26%|█████████▋                            | 13.0M/51.1M [00:21&lt;01:06, 573kB/s]
+ 26%|█████████▋                            | 13.1M/51.1M [00:21&lt;01:04, 588kB/s]
+ 26%|█████████▊                            | 13.2M/51.1M [00:21&lt;01:02, 604kB/s]
+ 26%|█████████▊                            | 13.2M/51.1M [00:21&lt;01:03, 597kB/s]
+ 26%|█████████▉                            | 13.3M/51.1M [00:21&lt;01:01, 612kB/s]
+ 26%|█████████▉                            | 13.4M/51.1M [00:21&lt;01:00, 620kB/s]
+ 26%|██████████                            | 13.5M/51.1M [00:21&lt;00:59, 632kB/s]
+ 26%|██████████                            | 13.5M/51.1M [00:21&lt;00:58, 646kB/s]
+ 27%|██████████                            | 13.6M/51.1M [00:22&lt;00:56, 658kB/s]
+ 27%|██████████▏                           | 13.7M/51.1M [00:22&lt;00:56, 664kB/s]
+ 27%|██████████▏                           | 13.8M/51.1M [00:22&lt;00:55, 673kB/s]
+ 27%|██████████▎                           | 13.9M/51.1M [00:22&lt;00:55, 676kB/s]
+ 27%|██████████▎                           | 13.9M/51.1M [00:22&lt;00:54, 677kB/s]
+ 27%|██████████▍                           | 14.0M/51.1M [00:22&lt;00:54, 676kB/s]
+ 28%|██████████▍                           | 14.1M/51.1M [00:22&lt;00:53, 691kB/s]
+ 28%|██████████▌                           | 14.2M/51.1M [00:22&lt;00:54, 680kB/s]
+ 28%|██████████▌                           | 14.3M/51.1M [00:23&lt;00:53, 690kB/s]
+ 28%|██████████▋                           | 14.3M/51.1M [00:23&lt;00:53, 689kB/s]
+ 28%|██████████▋                           | 14.4M/51.1M [00:23&lt;00:54, 673kB/s]
+ 28%|██████████▊                           | 14.5M/51.1M [00:23&lt;00:52, 692kB/s]
+ 29%|██████████▊                           | 14.6M/51.1M [00:23&lt;00:51, 707kB/s]
+ 29%|██████████▉                           | 14.7M/51.1M [00:23&lt;00:52, 699kB/s]
+ 29%|██████████▉                           | 14.7M/51.1M [00:23&lt;00:52, 697kB/s]
+ 29%|███████████                           | 14.8M/51.1M [00:23&lt;00:51, 698kB/s]
+ 29%|███████████                           | 14.9M/51.1M [00:23&lt;00:52, 695kB/s]
+ 29%|███████████▏                          | 15.0M/51.1M [00:24&lt;00:51, 700kB/s]
+ 29%|███████████▏                          | 15.1M/51.1M [00:24&lt;00:51, 703kB/s]
+ 30%|███████████▎                          | 15.1M/51.1M [00:24&lt;00:51, 697kB/s]
+ 30%|███████████▎                          | 15.2M/51.1M [00:24&lt;00:51, 701kB/s]
+ 30%|███████████▍                          | 15.3M/51.1M [00:24&lt;00:50, 704kB/s]
+ 30%|███████████▍                          | 15.4M/51.1M [00:24&lt;00:50, 704kB/s]
+ 30%|███████████▍                          | 15.5M/51.1M [00:24&lt;00:51, 690kB/s]
+ 30%|███████████▌                          | 15.5M/51.1M [00:24&lt;00:51, 696kB/s]
+ 31%|███████████▌                          | 15.6M/51.1M [00:24&lt;00:50, 700kB/s]
+ 31%|███████████▋                          | 15.7M/51.1M [00:25&lt;00:50, 701kB/s]
+ 31%|███████████▋                          | 15.8M/51.1M [00:25&lt;00:50, 699kB/s]
+ 31%|███████████▊                          | 15.9M/51.1M [00:25&lt;00:50, 701kB/s]
+ 31%|███████████▊                          | 15.9M/51.1M [00:25&lt;00:52, 676kB/s]
+ 31%|███████████▉                          | 16.0M/51.1M [00:25&lt;00:51, 675kB/s]
+ 31%|███████████▉                          | 16.1M/51.1M [00:25&lt;00:51, 676kB/s]
+ 32%|████████████                          | 16.2M/51.1M [00:25&lt;00:51, 678kB/s]
+ 32%|████████████                          | 16.3M/51.1M [00:25&lt;00:50, 684kB/s]
+ 32%|████████████▏                         | 16.3M/51.1M [00:26&lt;00:49, 697kB/s]
+ 32%|████████████▏                         | 16.4M/51.1M [00:26&lt;00:50, 691kB/s]
+ 32%|████████████▎                         | 16.5M/51.1M [00:26&lt;00:50, 685kB/s]
+ 32%|████████████▎                         | 16.6M/51.1M [00:26&lt;00:50, 680kB/s]
+ 33%|████████████▍                         | 16.7M/51.1M [00:26&lt;00:50, 679kB/s]
+ 33%|████████████▍                         | 16.7M/51.1M [00:26&lt;00:50, 679kB/s]
+ 33%|████████████▍                         | 16.8M/51.1M [00:26&lt;00:50, 674kB/s]
+ 33%|████████████▌                         | 16.9M/51.1M [00:26&lt;00:49, 696kB/s]
+ 33%|████████████▋                         | 17.0M/51.1M [00:26&lt;00:46, 733kB/s]
+ 33%|████████████▋                         | 17.1M/51.1M [00:27&lt;00:46, 737kB/s]
+ 34%|████████████▊                         | 17.2M/51.1M [00:27&lt;00:47, 718kB/s]
+ 34%|████████████▊                         | 17.2M/51.1M [00:27&lt;00:47, 712kB/s]
+ 34%|████████████▉                         | 17.3M/51.1M [00:27&lt;00:48, 696kB/s]
+ 34%|████████████▉                         | 17.4M/51.1M [00:27&lt;00:48, 700kB/s]
+ 34%|████████████▉                         | 17.5M/51.1M [00:27&lt;00:48, 699kB/s]
+ 34%|█████████████                         | 17.6M/51.1M [00:27&lt;00:48, 696kB/s]
+ 35%|█████████████                         | 17.6M/51.1M [00:27&lt;00:48, 684kB/s]
+ 35%|█████████████▏                        | 17.7M/51.1M [00:28&lt;00:48, 693kB/s]
+ 35%|█████████████▏                        | 17.8M/51.1M [00:28&lt;00:47, 704kB/s]
+ 35%|█████████████▎                        | 17.9M/51.1M [00:28&lt;00:47, 697kB/s]
+ 35%|█████████████▎                        | 18.0M/51.1M [00:28&lt;00:47, 698kB/s]
+ 35%|█████████████▍                        | 18.1M/51.1M [00:28&lt;00:48, 685kB/s]
+ 35%|█████████████▍                        | 18.1M/51.1M [00:28&lt;00:48, 682kB/s]
+ 36%|█████████████▌                        | 18.2M/51.1M [00:28&lt;00:48, 681kB/s]
+ 36%|█████████████▌                        | 18.3M/51.1M [00:28&lt;00:47, 686kB/s]
+ 36%|█████████████▋                        | 18.4M/51.1M [00:28&lt;00:45, 713kB/s]
+ 36%|█████████████▋                        | 18.4M/51.1M [00:29&lt;00:45, 712kB/s]
+ 36%|█████████████▊                        | 18.5M/51.1M [00:29&lt;00:47, 681kB/s]
+ 36%|█████████████▊                        | 18.6M/51.1M [00:29&lt;00:47, 689kB/s]
+ 37%|█████████████▉                        | 18.7M/51.1M [00:29&lt;00:47, 685kB/s]
+ 37%|█████████████▉                        | 18.8M/51.1M [00:29&lt;00:46, 691kB/s]
+ 37%|██████████████                        | 18.8M/51.1M [00:29&lt;00:44, 720kB/s]
+ 37%|██████████████                        | 18.9M/51.1M [00:29&lt;00:46, 696kB/s]
+ 37%|██████████████                        | 19.0M/51.1M [00:29&lt;00:46, 697kB/s]
+ 37%|██████████████▏                       | 19.1M/51.1M [00:29&lt;00:46, 695kB/s]
+ 37%|██████████████▏                       | 19.2M/51.1M [00:30&lt;00:45, 698kB/s]
+ 38%|██████████████▎                       | 19.2M/51.1M [00:30&lt;00:46, 692kB/s]
+ 38%|██████████████▎                       | 19.3M/51.1M [00:30&lt;00:46, 690kB/s]
+ 38%|██████████████▍                       | 19.4M/51.1M [00:30&lt;00:46, 690kB/s]
+ 38%|██████████████▍                       | 19.4M/51.1M [00:30&lt;00:46, 676kB/s]
+ 38%|██████████████▌                       | 19.5M/51.1M [00:30&lt;00:46, 676kB/s]
+ 38%|██████████████▌                       | 19.6M/51.1M [00:30&lt;00:47, 661kB/s]
+ 38%|██████████████▌                       | 19.7M/51.1M [00:30&lt;00:47, 656kB/s]
+ 39%|██████████████▋                       | 19.7M/51.1M [00:30&lt;00:46, 681kB/s]
+ 39%|██████████████▋                       | 19.8M/51.1M [00:31&lt;00:46, 672kB/s]
+ 39%|██████████████▊                       | 19.9M/51.1M [00:31&lt;00:46, 673kB/s]
+ 39%|██████████████▊                       | 20.0M/51.1M [00:31&lt;00:46, 663kB/s]
+ 39%|██████████████▉                       | 20.0M/51.1M [00:31&lt;00:50, 621kB/s]
+ 39%|██████████████▉                       | 20.1M/51.1M [00:31&lt;00:50, 610kB/s]
+ 39%|██████████████▉                       | 20.2M/51.1M [00:31&lt;00:51, 598kB/s]
+ 40%|███████████████                       | 20.2M/51.1M [00:31&lt;00:51, 601kB/s]
+ 40%|███████████████                       | 20.3M/51.1M [00:31&lt;00:50, 611kB/s]
+ 40%|███████████████▏                      | 20.3M/51.1M [00:31&lt;00:49, 621kB/s]
+ 40%|███████████████▏                      | 20.4M/51.1M [00:32&lt;00:49, 619kB/s]
+ 40%|███████████████▏                      | 20.5M/51.1M [00:32&lt;00:48, 626kB/s]
+ 40%|███████████████▎                      | 20.6M/51.1M [00:32&lt;00:48, 631kB/s]
+ 40%|███████████████▎                      | 20.6M/51.1M [00:32&lt;00:47, 636kB/s]
+ 41%|███████████████▍                      | 20.7M/51.1M [00:32&lt;00:47, 644kB/s]
+ 41%|███████████████▍                      | 20.8M/51.1M [00:32&lt;00:46, 647kB/s]
+ 41%|███████████████▌                      | 20.9M/51.1M [00:32&lt;00:45, 667kB/s]
+ 41%|███████████████▌                      | 20.9M/51.1M [00:32&lt;00:44, 675kB/s]
+ 41%|███████████████▋                      | 21.0M/51.1M [00:32&lt;00:44, 677kB/s]
+ 41%|███████████████▋                      | 21.1M/51.1M [00:33&lt;00:44, 675kB/s]
+ 41%|███████████████▋                      | 21.2M/51.1M [00:33&lt;00:54, 549kB/s]
+ 42%|███████████████▊                      | 21.3M/51.1M [00:33&lt;00:45, 658kB/s]
+ 42%|███████████████▊                      | 21.3M/51.1M [00:33&lt;00:46, 637kB/s]
+ 42%|███████████████▉                      | 21.4M/51.1M [00:33&lt;00:47, 627kB/s]
+ 42%|███████████████▉                      | 21.5M/51.1M [00:33&lt;00:48, 610kB/s]
+ 42%|████████████████                      | 21.5M/51.1M [00:33&lt;00:48, 611kB/s]
+ 42%|████████████████                      | 21.6M/51.1M [00:33&lt;00:47, 618kB/s]
+ 42%|████████████████▏                     | 21.7M/51.1M [00:34&lt;00:46, 633kB/s]
+ 43%|████████████████▏                     | 21.8M/51.1M [00:34&lt;00:45, 642kB/s]
+ 43%|████████████████▏                     | 21.9M/51.1M [00:34&lt;00:44, 658kB/s]
+ 43%|████████████████▎                     | 21.9M/51.1M [00:34&lt;00:43, 672kB/s]
+ 43%|████████████████▎                     | 22.0M/51.1M [00:34&lt;00:43, 671kB/s]
+ 43%|████████████████▍                     | 22.1M/51.1M [00:34&lt;00:43, 674kB/s]
+ 43%|████████████████▍                     | 22.2M/51.1M [00:34&lt;00:42, 673kB/s]
+ 44%|████████████████▌                     | 22.3M/51.1M [00:34&lt;00:42, 677kB/s]
+ 44%|████████████████▌                     | 22.3M/51.1M [00:34&lt;00:42, 681kB/s]
+ 44%|████████████████▋                     | 22.4M/51.1M [00:35&lt;00:41, 685kB/s]
+ 44%|████████████████▋                     | 22.5M/51.1M [00:35&lt;00:42, 681kB/s]
+ 44%|████████████████▊                     | 22.6M/51.1M [00:35&lt;00:41, 680kB/s]
+ 44%|████████████████▊                     | 22.7M/51.1M [00:35&lt;00:41, 679kB/s]
+ 45%|████████████████▉                     | 22.8M/51.1M [00:35&lt;00:40, 698kB/s]
+ 45%|████████████████▉                     | 22.8M/51.1M [00:35&lt;00:39, 710kB/s]
+ 45%|█████████████████                     | 22.9M/51.1M [00:35&lt;00:39, 706kB/s]
+ 45%|█████████████████                     | 23.0M/51.1M [00:35&lt;00:40, 696kB/s]
+ 45%|█████████████████▏                    | 23.1M/51.1M [00:36&lt;00:41, 682kB/s]
+ 45%|█████████████████▏                    | 23.2M/51.1M [00:36&lt;00:41, 679kB/s]
+ 45%|█████████████████▎                    | 23.2M/51.1M [00:36&lt;00:47, 584kB/s]
+ 46%|█████████████████▎                    | 23.3M/51.1M [00:36&lt;00:41, 664kB/s]
+ 46%|█████████████████▍                    | 23.4M/51.1M [00:36&lt;00:42, 654kB/s]
+ 46%|█████████████████▍                    | 23.5M/51.1M [00:36&lt;00:42, 648kB/s]
+ 46%|█████████████████▍                    | 23.5M/51.1M [00:36&lt;00:42, 650kB/s]
+ 46%|█████████████████▌                    | 23.6M/51.1M [00:36&lt;00:42, 653kB/s]
+ 46%|█████████████████▌                    | 23.7M/51.1M [00:36&lt;00:42, 653kB/s]
+ 46%|█████████████████▋                    | 23.7M/51.1M [00:37&lt;00:42, 638kB/s]
+ 47%|█████████████████▋                    | 23.8M/51.1M [00:37&lt;00:41, 657kB/s]
+ 47%|█████████████████▊                    | 23.9M/51.1M [00:37&lt;00:41, 659kB/s]
+ 47%|█████████████████▊                    | 24.0M/51.1M [00:37&lt;00:39, 682kB/s]
+ 47%|█████████████████▉                    | 24.1M/51.1M [00:37&lt;00:40, 676kB/s]
+ 47%|█████████████████▉                    | 24.1M/51.1M [00:37&lt;00:39, 683kB/s]
+ 47%|█████████████████▉                    | 24.2M/51.1M [00:37&lt;00:42, 636kB/s]
+ 48%|██████████████████                    | 24.3M/51.1M [00:37&lt;00:41, 650kB/s]
+ 48%|██████████████████                    | 24.3M/51.1M [00:38&lt;00:43, 622kB/s]
+ 48%|██████████████████▏                   | 24.4M/51.1M [00:38&lt;00:43, 613kB/s]
+ 48%|██████████████████▏                   | 24.5M/51.1M [00:38&lt;00:44, 595kB/s]
+ 48%|██████████████████▏                   | 24.5M/51.1M [00:38&lt;00:43, 606kB/s]
+ 48%|██████████████████▎                   | 24.6M/51.1M [00:38&lt;00:43, 610kB/s]
+ 48%|██████████████████▎                   | 24.7M/51.1M [00:38&lt;00:43, 603kB/s]
+ 48%|██████████████████▍                   | 24.7M/51.1M [00:38&lt;00:43, 613kB/s]
+ 49%|██████████████████▍                   | 24.8M/51.1M [00:38&lt;00:42, 622kB/s]
+ 49%|██████████████████▍                   | 24.9M/51.1M [00:38&lt;00:41, 631kB/s]
+ 49%|██████████████████▌                   | 24.9M/51.1M [00:38&lt;00:41, 631kB/s]
+ 49%|██████████████████▌                   | 25.0M/51.1M [00:39&lt;00:41, 633kB/s]
+ 49%|██████████████████▋                   | 25.1M/51.1M [00:39&lt;00:40, 645kB/s]
+ 49%|██████████████████▋                   | 25.1M/51.1M [00:39&lt;00:40, 646kB/s]
+ 49%|██████████████████▋                   | 25.2M/51.1M [00:39&lt;00:45, 573kB/s]
+ 49%|██████████████████▊                   | 25.3M/51.1M [00:39&lt;00:41, 623kB/s]
+ 50%|██████████████████▊                   | 25.4M/51.1M [00:39&lt;00:42, 600kB/s]
+ 50%|██████████████████▉                   | 25.4M/51.1M [00:39&lt;00:43, 586kB/s]
+ 50%|██████████████████▉                   | 25.5M/51.1M [00:39&lt;00:43, 594kB/s]
+ 50%|███████████████████                   | 25.6M/51.1M [00:40&lt;00:43, 594kB/s]
+ 50%|███████████████████                   | 25.6M/51.1M [00:40&lt;00:42, 596kB/s]
+ 50%|███████████████████                   | 25.7M/51.1M [00:40&lt;00:42, 602kB/s]
+ 50%|███████████████████▏                  | 25.8M/51.1M [00:40&lt;00:41, 614kB/s]
+ 51%|███████████████████▏                  | 25.8M/51.1M [00:40&lt;00:40, 621kB/s]
+ 51%|███████████████████▎                  | 25.9M/51.1M [00:40&lt;00:40, 628kB/s]
+ 51%|███████████████████▎                  | 26.0M/51.1M [00:40&lt;00:39, 643kB/s]
+ 51%|███████████████████▎                  | 26.1M/51.1M [00:40&lt;00:39, 641kB/s]
+ 51%|███████████████████▍                  | 26.1M/51.1M [00:40&lt;00:43, 579kB/s]
+ 51%|███████████████████▍                  | 26.2M/51.1M [00:41&lt;00:39, 626kB/s]
+ 51%|███████████████████▌                  | 26.3M/51.1M [00:41&lt;00:39, 623kB/s]
+ 52%|███████████████████▌                  | 26.3M/51.1M [00:41&lt;00:42, 590kB/s]
+ 52%|███████████████████▌                  | 26.4M/51.1M [00:41&lt;00:44, 560kB/s]
+ 52%|███████████████████▋                  | 26.4M/51.1M [00:41&lt;00:45, 541kB/s]
+ 52%|███████████████████▋                  | 26.5M/51.1M [00:41&lt;00:45, 547kB/s]
+ 52%|███████████████████▊                  | 26.6M/51.1M [00:41&lt;00:44, 554kB/s]
+ 52%|███████████████████▊                  | 26.6M/51.1M [00:41&lt;00:43, 562kB/s]
+ 52%|███████████████████▊                  | 26.7M/51.1M [00:41&lt;00:42, 570kB/s]
+ 52%|███████████████████▉                  | 26.8M/51.1M [00:42&lt;00:42, 574kB/s]
+ 53%|███████████████████▉                  | 26.8M/51.1M [00:42&lt;00:41, 589kB/s]
+ 53%|████████████████████                  | 26.9M/51.1M [00:42&lt;00:40, 600kB/s]
+ 53%|████████████████████                  | 27.0M/51.1M [00:42&lt;00:39, 612kB/s]
+ 53%|████████████████████                  | 27.0M/51.1M [00:42&lt;00:38, 628kB/s]
+ 53%|████████████████████▏                 | 27.1M/51.1M [00:42&lt;00:37, 634kB/s]
+ 53%|████████████████████▏                 | 27.2M/51.1M [00:42&lt;00:36, 649kB/s]
+ 53%|████████████████████▎                 | 27.3M/51.1M [00:42&lt;00:36, 650kB/s]
+ 54%|████████████████████▎                 | 27.3M/51.1M [00:42&lt;00:37, 642kB/s]
+ 54%|████████████████████▍                 | 27.4M/51.1M [00:43&lt;00:36, 651kB/s]
+ 54%|████████████████████▍                 | 27.5M/51.1M [00:43&lt;00:35, 667kB/s]
+ 54%|████████████████████▌                 | 27.6M/51.1M [00:43&lt;00:41, 561kB/s]
+ 54%|████████████████████▌                 | 27.7M/51.1M [00:43&lt;00:35, 656kB/s]
+ 54%|████████████████████▋                 | 27.8M/51.1M [00:43&lt;00:36, 632kB/s]
+ 54%|████████████████████▋                 | 27.8M/51.1M [00:43&lt;00:38, 608kB/s]
+ 55%|████████████████████▋                 | 27.9M/51.1M [00:43&lt;00:38, 597kB/s]
+ 55%|████████████████████▊                 | 28.0M/51.1M [00:43&lt;00:37, 612kB/s]
+ 55%|████████████████████▊                 | 28.0M/51.1M [00:44&lt;00:37, 622kB/s]
+ 55%|████████████████████▉                 | 28.1M/51.1M [00:44&lt;00:36, 627kB/s]
+ 55%|████████████████████▉                 | 28.1M/51.1M [00:44&lt;00:42, 538kB/s]
+ 55%|█████████████████████                 | 28.2M/51.1M [00:44&lt;00:36, 621kB/s]
+ 55%|█████████████████████                 | 28.3M/51.1M [00:44&lt;00:36, 620kB/s]
+ 56%|█████████████████████                 | 28.4M/51.1M [00:44&lt;00:38, 589kB/s]
+ 56%|█████████████████████▏                | 28.4M/51.1M [00:44&lt;00:41, 552kB/s]
+ 56%|█████████████████████▏                | 28.5M/51.1M [00:44&lt;00:43, 518kB/s]
+ 56%|█████████████████████▏                | 28.6M/51.1M [00:45&lt;00:42, 533kB/s]
+ 56%|█████████████████████▎                | 28.6M/51.1M [00:45&lt;00:42, 531kB/s]
+ 56%|█████████████████████▎                | 28.7M/51.1M [00:45&lt;00:41, 544kB/s]
+ 56%|█████████████████████▍                | 28.8M/51.1M [00:45&lt;00:40, 553kB/s]
+ 56%|█████████████████████▍                | 28.8M/51.1M [00:45&lt;00:39, 562kB/s]
+ 57%|█████████████████████▍                | 28.9M/51.1M [00:45&lt;00:38, 576kB/s]
+ 57%|█████████████████████▌                | 29.0M/51.1M [00:45&lt;00:38, 579kB/s]
+ 57%|█████████████████████▌                | 29.0M/51.1M [00:45&lt;00:37, 595kB/s]
+ 57%|█████████████████████▌                | 29.1M/51.1M [00:45&lt;00:36, 608kB/s]
+ 57%|█████████████████████▋                | 29.1M/51.1M [00:46&lt;00:35, 619kB/s]
+ 57%|█████████████████████▋                | 29.2M/51.1M [00:46&lt;00:35, 617kB/s]
+ 57%|█████████████████████▊                | 29.3M/51.1M [00:46&lt;00:34, 626kB/s]
+ 57%|█████████████████████▊                | 29.3M/51.1M [00:46&lt;00:34, 633kB/s]
+ 58%|█████████████████████▉                | 29.4M/51.1M [00:46&lt;00:33, 646kB/s]
+ 58%|█████████████████████▉                | 29.5M/51.1M [00:46&lt;00:32, 660kB/s]
+ 58%|█████████████████████▉                | 29.6M/51.1M [00:46&lt;00:32, 655kB/s]
+ 58%|██████████████████████                | 29.6M/51.1M [00:46&lt;00:36, 593kB/s]
+ 58%|██████████████████████                | 29.7M/51.1M [00:46&lt;00:33, 635kB/s]
+ 58%|██████████████████████▏               | 29.8M/51.1M [00:47&lt;00:35, 597kB/s]
+ 58%|██████████████████████▏               | 29.9M/51.1M [00:47&lt;00:36, 583kB/s]
+ 59%|██████████████████████▏               | 29.9M/51.1M [00:47&lt;00:36, 578kB/s]
+ 59%|██████████████████████▎               | 30.0M/51.1M [00:47&lt;00:36, 579kB/s]
+ 59%|██████████████████████▎               | 30.0M/51.1M [00:47&lt;00:35, 593kB/s]
+ 59%|██████████████████████▍               | 30.1M/51.1M [00:47&lt;00:35, 597kB/s]
+ 59%|██████████████████████▍               | 30.2M/51.1M [00:47&lt;00:34, 603kB/s]
+ 59%|██████████████████████▍               | 30.2M/51.1M [00:47&lt;00:33, 616kB/s]
+ 59%|██████████████████████▌               | 30.3M/51.1M [00:47&lt;00:33, 623kB/s]
+ 59%|██████████████████████▌               | 30.4M/51.1M [00:48&lt;00:32, 641kB/s]
+ 60%|██████████████████████▋               | 30.5M/51.1M [00:48&lt;00:31, 651kB/s]
+ 60%|██████████████████████▋               | 30.5M/51.1M [00:48&lt;00:31, 650kB/s]
+ 60%|██████████████████████▊               | 30.6M/51.1M [00:48&lt;00:31, 661kB/s]
+ 60%|██████████████████████▊               | 30.7M/51.1M [00:48&lt;00:30, 665kB/s]
+ 60%|██████████████████████▉               | 30.8M/51.1M [00:48&lt;00:30, 674kB/s]
+ 60%|██████████████████████▉               | 30.9M/51.1M [00:48&lt;00:29, 680kB/s]
+ 61%|███████████████████████               | 30.9M/51.1M [00:48&lt;00:29, 679kB/s]
+ 61%|███████████████████████               | 31.0M/51.1M [00:48&lt;00:29, 683kB/s]
+ 61%|███████████████████████               | 31.1M/51.1M [00:49&lt;00:29, 681kB/s]
+ 61%|███████████████████████▏              | 31.2M/51.1M [00:49&lt;00:35, 564kB/s]
+ 61%|███████████████████████▎              | 31.3M/51.1M [00:49&lt;00:29, 674kB/s]
+ 61%|███████████████████████▎              | 31.3M/51.1M [00:49&lt;00:30, 640kB/s]
+ 61%|███████████████████████▎              | 31.4M/51.1M [00:49&lt;00:31, 633kB/s]
+ 62%|███████████████████████▍              | 31.5M/51.1M [00:49&lt;00:32, 609kB/s]
+ 62%|███████████████████████▍              | 31.5M/51.1M [00:49&lt;00:32, 602kB/s]
+ 62%|███████████████████████▍              | 31.6M/51.1M [00:49&lt;00:32, 606kB/s]
+ 62%|███████████████████████▌              | 31.7M/51.1M [00:50&lt;00:31, 619kB/s]
+ 62%|███████████████████████▌              | 31.8M/51.1M [00:50&lt;00:30, 628kB/s]
+ 62%|███████████████████████▋              | 31.8M/51.1M [00:50&lt;00:30, 631kB/s]
+ 62%|███████████████████████▋              | 31.9M/51.1M [00:50&lt;00:29, 647kB/s]
+ 63%|███████████████████████▊              | 32.0M/51.1M [00:50&lt;00:29, 652kB/s]
+ 63%|███████████████████████▊              | 32.1M/51.1M [00:50&lt;00:28, 666kB/s]
+ 63%|███████████████████████▉              | 32.1M/51.1M [00:50&lt;00:28, 672kB/s]
+ 63%|███████████████████████▉              | 32.2M/51.1M [00:50&lt;00:27, 677kB/s]
+ 63%|████████████████████████              | 32.3M/51.1M [00:50&lt;00:27, 676kB/s]
+ 63%|████████████████████████              | 32.4M/51.1M [00:51&lt;00:27, 674kB/s]
+ 64%|████████████████████████▏             | 32.5M/51.1M [00:51&lt;00:27, 675kB/s]
+ 64%|████████████████████████▏             | 32.6M/51.1M [00:51&lt;00:27, 669kB/s]
+ 64%|████████████████████████▎             | 32.6M/51.1M [00:51&lt;00:27, 677kB/s]
+ 64%|████████████████████████▎             | 32.7M/51.1M [00:51&lt;00:26, 685kB/s]
+ 64%|████████████████████████▍             | 32.8M/51.1M [00:51&lt;00:26, 687kB/s]
+ 64%|████████████████████████▍             | 32.9M/51.1M [00:51&lt;00:27, 675kB/s]
+ 64%|████████████████████████▍             | 33.0M/51.1M [00:51&lt;00:28, 638kB/s]
+ 65%|████████████████████████▌             | 33.0M/51.1M [00:52&lt;00:28, 630kB/s]
+ 65%|████████████████████████▌             | 33.1M/51.1M [00:52&lt;00:29, 618kB/s]
+ 65%|████████████████████████▋             | 33.1M/51.1M [00:52&lt;00:28, 621kB/s]
+ 65%|████████████████████████▋             | 33.2M/51.1M [00:52&lt;00:28, 630kB/s]
+ 65%|████████████████████████▋             | 33.3M/51.1M [00:52&lt;00:28, 632kB/s]
+ 65%|████████████████████████▊             | 33.4M/51.1M [00:52&lt;00:27, 649kB/s]
+ 65%|████████████████████████▊             | 33.4M/51.1M [00:52&lt;00:26, 659kB/s]
+ 66%|████████████████████████▉             | 33.5M/51.1M [00:52&lt;00:26, 668kB/s]
+ 66%|████████████████████████▉             | 33.6M/51.1M [00:52&lt;00:25, 679kB/s]
+ 66%|█████████████████████████             | 33.7M/51.1M [00:53&lt;00:25, 676kB/s]
+ 66%|█████████████████████████             | 33.8M/51.1M [00:53&lt;00:25, 672kB/s]
+ 66%|█████████████████████████▏            | 33.8M/51.1M [00:53&lt;00:25, 675kB/s]
+ 66%|█████████████████████████▏            | 33.9M/51.1M [00:53&lt;00:25, 682kB/s]
+ 67%|█████████████████████████▎            | 34.0M/51.1M [00:53&lt;00:24, 688kB/s]
+ 67%|█████████████████████████▎            | 34.1M/51.1M [00:53&lt;00:25, 677kB/s]
+ 67%|█████████████████████████▍            | 34.2M/51.1M [00:53&lt;00:25, 677kB/s]
+ 67%|█████████████████████████▍            | 34.2M/51.1M [00:53&lt;00:24, 675kB/s]
+ 67%|█████████████████████████▌            | 34.3M/51.1M [00:54&lt;00:30, 553kB/s]
+ 67%|█████████████████████████▌            | 34.4M/51.1M [00:54&lt;00:25, 665kB/s]
+ 67%|█████████████████████████▋            | 34.5M/51.1M [00:54&lt;00:25, 650kB/s]
+ 68%|█████████████████████████▋            | 34.6M/51.1M [00:54&lt;00:25, 639kB/s]
+ 68%|█████████████████████████▋            | 34.6M/51.1M [00:54&lt;00:27, 604kB/s]
+ 68%|█████████████████████████▊            | 34.7M/51.1M [00:54&lt;00:28, 575kB/s]
+ 68%|█████████████████████████▊            | 34.7M/51.1M [00:54&lt;00:29, 562kB/s]
+ 68%|█████████████████████████▉            | 34.8M/51.1M [00:54&lt;00:32, 505kB/s]
+ 68%|█████████████████████████▉            | 34.9M/51.1M [00:55&lt;00:34, 477kB/s]
+ 68%|█████████████████████████▉            | 34.9M/51.1M [00:55&lt;00:32, 494kB/s]
+ 68%|██████████████████████████            | 35.0M/51.1M [00:55&lt;00:32, 498kB/s]
+ 69%|██████████████████████████            | 35.0M/51.1M [00:55&lt;00:31, 509kB/s]
+ 69%|██████████████████████████            | 35.1M/51.1M [00:55&lt;00:31, 503kB/s]
+ 69%|██████████████████████████▏           | 35.2M/51.1M [00:55&lt;00:30, 516kB/s]
+ 69%|██████████████████████████▏           | 35.2M/51.1M [00:55&lt;00:31, 511kB/s]
+ 69%|██████████████████████████▏           | 35.3M/51.1M [00:55&lt;00:29, 532kB/s]
+ 69%|██████████████████████████▎           | 35.4M/51.1M [00:55&lt;00:29, 537kB/s]
+ 69%|██████████████████████████▎           | 35.4M/51.1M [00:56&lt;00:28, 559kB/s]
+ 69%|██████████████████████████▍           | 35.5M/51.1M [00:56&lt;00:27, 574kB/s]
+ 70%|██████████████████████████▍           | 35.6M/51.1M [00:56&lt;00:26, 589kB/s]
+ 70%|██████████████████████████▍           | 35.6M/51.1M [00:56&lt;00:25, 601kB/s]
+ 70%|██████████████████████████▌           | 35.7M/51.1M [00:56&lt;00:25, 610kB/s]
+ 70%|██████████████████████████▌           | 35.8M/51.1M [00:56&lt;00:24, 631kB/s]
+ 70%|██████████████████████████▋           | 35.8M/51.1M [00:56&lt;00:23, 646kB/s]
+ 70%|██████████████████████████▋           | 35.9M/51.1M [00:56&lt;00:23, 653kB/s]
+ 70%|██████████████████████████▊           | 36.0M/51.1M [00:56&lt;00:22, 659kB/s]
+ 71%|██████████████████████████▊           | 36.1M/51.1M [00:57&lt;00:22, 665kB/s]
+ 71%|██████████████████████████▉           | 36.2M/51.1M [00:57&lt;00:22, 666kB/s]
+ 71%|██████████████████████████▉           | 36.3M/51.1M [00:57&lt;00:22, 674kB/s]
+ 71%|███████████████████████████           | 36.3M/51.1M [00:57&lt;00:21, 674kB/s]
+ 71%|███████████████████████████           | 36.4M/51.1M [00:57&lt;00:21, 673kB/s]
+ 71%|███████████████████████████▏          | 36.5M/51.1M [00:57&lt;00:21, 682kB/s]
+ 72%|███████████████████████████▏          | 36.6M/51.1M [00:57&lt;00:20, 699kB/s]
+ 72%|███████████████████████████▏          | 36.7M/51.1M [00:57&lt;00:21, 687kB/s]
+ 72%|███████████████████████████▎          | 36.7M/51.1M [00:58&lt;00:20, 698kB/s]
+ 72%|███████████████████████████▎          | 36.8M/51.1M [00:58&lt;00:20, 697kB/s]
+ 72%|███████████████████████████▍          | 36.9M/51.1M [00:58&lt;00:21, 657kB/s]
+ 72%|███████████████████████████▍          | 36.9M/51.1M [00:58&lt;00:21, 657kB/s]
+ 72%|███████████████████████████▌          | 37.0M/51.1M [00:58&lt;00:25, 558kB/s]
+ 73%|███████████████████████████▌          | 37.1M/51.1M [00:58&lt;00:20, 672kB/s]
+ 73%|███████████████████████████▋          | 37.2M/51.1M [00:58&lt;00:21, 653kB/s]
+ 73%|███████████████████████████▋          | 37.3M/51.1M [00:58&lt;00:21, 645kB/s]
+ 73%|███████████████████████████▊          | 37.3M/51.1M [00:58&lt;00:21, 640kB/s]
+ 73%|███████████████████████████▊          | 37.4M/51.1M [00:59&lt;00:21, 639kB/s]
+ 73%|███████████████████████████▊          | 37.5M/51.1M [00:59&lt;00:21, 635kB/s]
+ 73%|███████████████████████████▉          | 37.5M/51.1M [00:59&lt;00:21, 629kB/s]
+ 74%|███████████████████████████▉          | 37.6M/51.1M [00:59&lt;00:20, 650kB/s]
+ 74%|████████████████████████████          | 37.7M/51.1M [00:59&lt;00:22, 592kB/s]
+ 74%|████████████████████████████          | 37.7M/51.1M [00:59&lt;00:21, 618kB/s]
+ 74%|████████████████████████████          | 37.8M/51.1M [00:59&lt;00:22, 580kB/s]
+ 74%|████████████████████████████▏         | 37.9M/51.1M [00:59&lt;00:23, 568kB/s]
+ 74%|████████████████████████████▏         | 37.9M/51.1M [01:00&lt;00:23, 568kB/s]
+ 74%|████████████████████████████▎         | 38.0M/51.1M [01:00&lt;00:23, 558kB/s]
+ 74%|████████████████████████████▎         | 38.1M/51.1M [01:00&lt;00:22, 573kB/s]
+ 75%|████████████████████████████▎         | 38.1M/51.1M [01:00&lt;00:22, 570kB/s]
+ 75%|████████████████████████████▍         | 38.2M/51.1M [01:00&lt;00:22, 583kB/s]
+ 75%|████████████████████████████▍         | 38.3M/51.1M [01:00&lt;00:22, 583kB/s]
+ 75%|████████████████████████████▌         | 38.3M/51.1M [01:00&lt;00:21, 591kB/s]
+ 75%|████████████████████████████▌         | 38.4M/51.1M [01:00&lt;00:21, 602kB/s]
+ 75%|████████████████████████████▌         | 38.5M/51.1M [01:00&lt;00:20, 612kB/s]
+ 75%|████████████████████████████▋         | 38.5M/51.1M [01:01&lt;00:20, 619kB/s]
+ 76%|████████████████████████████▋         | 38.6M/51.1M [01:01&lt;00:19, 629kB/s]
+ 76%|████████████████████████████▊         | 38.7M/51.1M [01:01&lt;00:19, 649kB/s]
+ 76%|████████████████████████████▊         | 38.8M/51.1M [01:01&lt;00:18, 656kB/s]
+ 76%|████████████████████████████▉         | 38.8M/51.1M [01:01&lt;00:18, 678kB/s]
+ 76%|████████████████████████████▉         | 38.9M/51.1M [01:01&lt;00:17, 680kB/s]
+ 76%|█████████████████████████████         | 39.0M/51.1M [01:01&lt;00:17, 702kB/s]
+ 76%|█████████████████████████████         | 39.1M/51.1M [01:01&lt;00:17, 704kB/s]
+ 77%|█████████████████████████████▏        | 39.2M/51.1M [01:01&lt;00:17, 692kB/s]
+ 77%|█████████████████████████████▏        | 39.3M/51.1M [01:02&lt;00:16, 702kB/s]
+ 77%|█████████████████████████████▏        | 39.3M/51.1M [01:02&lt;00:16, 704kB/s]
+ 77%|█████████████████████████████▎        | 39.4M/51.1M [01:02&lt;00:16, 705kB/s]
+ 77%|█████████████████████████████▎        | 39.5M/51.1M [01:02&lt;00:17, 674kB/s]
+ 77%|█████████████████████████████▍        | 39.6M/51.1M [01:02&lt;00:17, 655kB/s]
+ 78%|█████████████████████████████▍        | 39.6M/51.1M [01:02&lt;00:17, 644kB/s]
+ 78%|█████████████████████████████▌        | 39.7M/51.1M [01:02&lt;00:18, 631kB/s]
+ 78%|█████████████████████████████▌        | 39.8M/51.1M [01:02&lt;00:17, 632kB/s]
+ 78%|█████████████████████████████▌        | 39.8M/51.1M [01:02&lt;00:17, 662kB/s]
+ 78%|█████████████████████████████▋        | 39.9M/51.1M [01:03&lt;00:17, 648kB/s]
+ 78%|█████████████████████████████▋        | 40.0M/51.1M [01:03&lt;00:16, 662kB/s]
+ 78%|█████████████████████████████▊        | 40.1M/51.1M [01:03&lt;00:16, 681kB/s]
+ 79%|█████████████████████████████▊        | 40.1M/51.1M [01:03&lt;00:16, 681kB/s]
+ 79%|█████████████████████████████▉        | 40.2M/51.1M [01:03&lt;00:16, 645kB/s]
+ 79%|█████████████████████████████▉        | 40.3M/51.1M [01:03&lt;00:18, 595kB/s]
+ 79%|█████████████████████████████▉        | 40.3M/51.1M [01:03&lt;00:18, 572kB/s]
+ 79%|██████████████████████████████        | 40.4M/51.1M [01:03&lt;00:19, 560kB/s]
+ 79%|██████████████████████████████        | 40.5M/51.1M [01:03&lt;00:18, 572kB/s]
+ 79%|██████████████████████████████▏       | 40.5M/51.1M [01:04&lt;00:18, 565kB/s]
+ 79%|██████████████████████████████▏       | 40.6M/51.1M [01:04&lt;00:18, 580kB/s]
+ 80%|██████████████████████████████▏       | 40.7M/51.1M [01:04&lt;00:17, 582kB/s]
+ 80%|██████████████████████████████▎       | 40.7M/51.1M [01:04&lt;00:17, 592kB/s]
+ 80%|██████████████████████████████▎       | 40.8M/51.1M [01:04&lt;00:17, 601kB/s]
+ 80%|██████████████████████████████▍       | 40.9M/51.1M [01:04&lt;00:16, 610kB/s]
+ 80%|██████████████████████████████▍       | 40.9M/51.1M [01:04&lt;00:16, 618kB/s]
+ 80%|██████████████████████████████▍       | 41.0M/51.1M [01:04&lt;00:16, 627kB/s]
+ 80%|██████████████████████████████▌       | 41.1M/51.1M [01:04&lt;00:15, 634kB/s]
+ 80%|██████████████████████████████▌       | 41.1M/51.1M [01:05&lt;00:15, 645kB/s]
+ 81%|██████████████████████████████▋       | 41.2M/51.1M [01:05&lt;00:15, 653kB/s]
+ 81%|██████████████████████████████▋       | 41.3M/51.1M [01:05&lt;00:14, 660kB/s]
+ 81%|██████████████████████████████▊       | 41.4M/51.1M [01:05&lt;00:14, 660kB/s]
+ 81%|██████████████████████████████▊       | 41.5M/51.1M [01:05&lt;00:14, 663kB/s]
+ 81%|██████████████████████████████▉       | 41.5M/51.1M [01:05&lt;00:14, 661kB/s]
+ 81%|██████████████████████████████▉       | 41.6M/51.1M [01:05&lt;00:14, 675kB/s]
+ 82%|███████████████████████████████       | 41.7M/51.1M [01:05&lt;00:13, 684kB/s]
+ 82%|███████████████████████████████       | 41.8M/51.1M [01:06&lt;00:13, 680kB/s]
+ 82%|███████████████████████████████       | 41.9M/51.1M [01:06&lt;00:13, 675kB/s]
+ 82%|███████████████████████████████▏      | 41.9M/51.1M [01:06&lt;00:13, 675kB/s]
+ 82%|███████████████████████████████▏      | 42.0M/51.1M [01:06&lt;00:13, 653kB/s]
+ 82%|███████████████████████████████▎      | 42.1M/51.1M [01:06&lt;00:13, 649kB/s]
+ 82%|███████████████████████████████▎      | 42.1M/51.1M [01:06&lt;00:14, 620kB/s]
+ 83%|███████████████████████████████▎      | 42.2M/51.1M [01:06&lt;00:14, 599kB/s]
+ 83%|███████████████████████████████▍      | 42.3M/51.1M [01:06&lt;00:14, 606kB/s]
+ 83%|███████████████████████████████▍      | 42.3M/51.1M [01:06&lt;00:14, 619kB/s]
+ 83%|███████████████████████████████▌      | 42.4M/51.1M [01:07&lt;00:13, 638kB/s]
+ 83%|███████████████████████████████▌      | 42.5M/51.1M [01:07&lt;00:13, 642kB/s]
+ 83%|███████████████████████████████▋      | 42.5M/51.1M [01:07&lt;00:13, 645kB/s]
+ 83%|███████████████████████████████▋      | 42.6M/51.1M [01:07&lt;00:12, 655kB/s]
+ 84%|███████████████████████████████▋      | 42.7M/51.1M [01:07&lt;00:12, 654kB/s]
+ 84%|███████████████████████████████▊      | 42.8M/51.1M [01:07&lt;00:14, 566kB/s]
+ 84%|███████████████████████████████▉      | 42.9M/51.1M [01:07&lt;00:12, 662kB/s]
+ 84%|███████████████████████████████▉      | 43.0M/51.1M [01:07&lt;00:12, 631kB/s]
+ 84%|███████████████████████████████▉      | 43.0M/51.1M [01:08&lt;00:13, 601kB/s]
+ 84%|████████████████████████████████      | 43.1M/51.1M [01:08&lt;00:13, 595kB/s]
+ 84%|████████████████████████████████      | 43.2M/51.1M [01:08&lt;00:13, 591kB/s]
+ 85%|████████████████████████████████▏     | 43.2M/51.1M [01:08&lt;00:13, 581kB/s]
+ 85%|████████████████████████████████▏     | 43.3M/51.1M [01:08&lt;00:13, 587kB/s]
+ 85%|████████████████████████████████▏     | 43.4M/51.1M [01:08&lt;00:13, 587kB/s]
+ 85%|████████████████████████████████▎     | 43.4M/51.1M [01:08&lt;00:12, 595kB/s]
+ 85%|████████████████████████████████▎     | 43.5M/51.1M [01:08&lt;00:12, 605kB/s]
+ 85%|████████████████████████████████▍     | 43.5M/51.1M [01:08&lt;00:12, 612kB/s]
+ 85%|████████████████████████████████▍     | 43.6M/51.1M [01:09&lt;00:12, 617kB/s]
+ 85%|████████████████████████████████▍     | 43.7M/51.1M [01:09&lt;00:11, 638kB/s]
+ 86%|████████████████████████████████▌     | 43.8M/51.1M [01:09&lt;00:11, 645kB/s]
+ 86%|████████████████████████████████▌     | 43.9M/51.1M [01:09&lt;00:11, 653kB/s]
+ 86%|████████████████████████████████▋     | 43.9M/51.1M [01:09&lt;00:10, 660kB/s]
+ 86%|████████████████████████████████▋     | 44.0M/51.1M [01:09&lt;00:10, 660kB/s]
+ 86%|████████████████████████████████▊     | 44.1M/51.1M [01:09&lt;00:12, 574kB/s]
+ 86%|████████████████████████████████▊     | 44.2M/51.1M [01:09&lt;00:10, 644kB/s]
+ 87%|████████████████████████████████▉     | 44.2M/51.1M [01:09&lt;00:11, 611kB/s]
+ 87%|████████████████████████████████▉     | 44.3M/51.1M [01:10&lt;00:11, 602kB/s]
+ 87%|████████████████████████████████▉     | 44.4M/51.1M [01:10&lt;00:11, 593kB/s]
+ 87%|█████████████████████████████████     | 44.4M/51.1M [01:10&lt;00:11, 597kB/s]
+ 87%|█████████████████████████████████     | 44.5M/51.1M [01:10&lt;00:10, 602kB/s]
+ 87%|█████████████████████████████████▏    | 44.6M/51.1M [01:10&lt;00:10, 614kB/s]
+ 87%|█████████████████████████████████▏    | 44.6M/51.1M [01:10&lt;00:10, 622kB/s]
+ 87%|█████████████████████████████████▏    | 44.7M/51.1M [01:10&lt;00:10, 635kB/s]
+ 88%|█████████████████████████████████▎    | 44.8M/51.1M [01:10&lt;00:09, 639kB/s]
+ 88%|█████████████████████████████████▎    | 44.8M/51.1M [01:11&lt;00:11, 562kB/s]
+ 88%|█████████████████████████████████▍    | 44.9M/51.1M [01:11&lt;00:09, 620kB/s]
+ 88%|█████████████████████████████████▍    | 45.0M/51.1M [01:11&lt;00:09, 622kB/s]
+ 88%|█████████████████████████████████▍    | 45.1M/51.1M [01:11&lt;00:10, 590kB/s]
+ 88%|█████████████████████████████████▌    | 45.1M/51.1M [01:11&lt;00:10, 557kB/s]
+ 88%|█████████████████████████████████▌    | 45.2M/51.1M [01:11&lt;00:11, 538kB/s]
+ 89%|█████████████████████████████████▋    | 45.2M/51.1M [01:11&lt;00:10, 538kB/s]
+ 89%|█████████████████████████████████▋    | 45.3M/51.1M [01:11&lt;00:10, 549kB/s]
+ 89%|█████████████████████████████████▋    | 45.4M/51.1M [01:11&lt;00:10, 556kB/s]
+ 89%|█████████████████████████████████▊    | 45.4M/51.1M [01:12&lt;00:09, 569kB/s]
+ 89%|█████████████████████████████████▊    | 45.5M/51.1M [01:12&lt;00:09, 577kB/s]
+ 89%|█████████████████████████████████▉    | 45.6M/51.1M [01:12&lt;00:09, 580kB/s]
+ 89%|█████████████████████████████████▉    | 45.6M/51.1M [01:12&lt;00:09, 597kB/s]
+ 89%|█████████████████████████████████▉    | 45.7M/51.1M [01:12&lt;00:08, 608kB/s]
+ 90%|██████████████████████████████████    | 45.8M/51.1M [01:12&lt;00:08, 606kB/s]
+ 90%|██████████████████████████████████    | 45.8M/51.1M [01:12&lt;00:08, 626kB/s]
+ 90%|██████████████████████████████████▏   | 45.9M/51.1M [01:12&lt;00:08, 621kB/s]
+ 90%|██████████████████████████████████▏   | 46.0M/51.1M [01:12&lt;00:08, 638kB/s]
+ 90%|██████████████████████████████████▎   | 46.1M/51.1M [01:13&lt;00:07, 651kB/s]
+ 90%|██████████████████████████████████▎   | 46.2M/51.1M [01:13&lt;00:07, 653kB/s]
+ 90%|██████████████████████████████████▍   | 46.2M/51.1M [01:13&lt;00:07, 679kB/s]
+ 91%|██████████████████████████████████▍   | 46.3M/51.1M [01:13&lt;00:06, 690kB/s]
+ 91%|██████████████████████████████████▍   | 46.4M/51.1M [01:13&lt;00:06, 698kB/s]
+ 91%|██████████████████████████████████▌   | 46.5M/51.1M [01:13&lt;00:06, 697kB/s]
+ 91%|██████████████████████████████████▌   | 46.6M/51.1M [01:13&lt;00:06, 693kB/s]
+ 91%|██████████████████████████████████▋   | 46.6M/51.1M [01:13&lt;00:06, 686kB/s]
+ 91%|██████████████████████████████████▋   | 46.7M/51.1M [01:13&lt;00:06, 685kB/s]
+ 92%|██████████████████████████████████▊   | 46.8M/51.1M [01:14&lt;00:06, 681kB/s]
+ 92%|██████████████████████████████████▊   | 46.9M/51.1M [01:14&lt;00:06, 633kB/s]
+ 92%|██████████████████████████████████▉   | 46.9M/51.1M [01:14&lt;00:06, 633kB/s]
+ 92%|██████████████████████████████████▉   | 47.0M/51.1M [01:14&lt;00:06, 623kB/s]
+ 92%|██████████████████████████████████▉   | 47.1M/51.1M [01:14&lt;00:06, 618kB/s]
+ 92%|███████████████████████████████████   | 47.1M/51.1M [01:14&lt;00:06, 617kB/s]
+ 92%|███████████████████████████████████   | 47.2M/51.1M [01:14&lt;00:06, 623kB/s]
+ 93%|███████████████████████████████████▏  | 47.3M/51.1M [01:14&lt;00:07, 538kB/s]
+ 93%|███████████████████████████████████▏  | 47.4M/51.1M [01:15&lt;00:05, 629kB/s]
+ 93%|███████████████████████████████████▎  | 47.4M/51.1M [01:15&lt;00:06, 593kB/s]
+ 93%|███████████████████████████████████▎  | 47.5M/51.1M [01:15&lt;00:06, 556kB/s]
+ 93%|███████████████████████████████████▎  | 47.6M/51.1M [01:15&lt;00:06, 518kB/s]
+ 93%|███████████████████████████████████▍  | 47.6M/51.1M [01:15&lt;00:07, 490kB/s]
+ 93%|███████████████████████████████████▍  | 47.7M/51.1M [01:15&lt;00:07, 463kB/s]
+ 93%|███████████████████████████████████▍  | 47.7M/51.1M [01:15&lt;00:07, 453kB/s]
+ 93%|███████████████████████████████████▌  | 47.8M/51.1M [01:15&lt;00:07, 424kB/s]
+ 94%|███████████████████████████████████▌  | 47.8M/51.1M [01:16&lt;00:07, 416kB/s]
+ 94%|███████████████████████████████████▌  | 47.9M/51.1M [01:16&lt;00:08, 406kB/s]
+ 94%|███████████████████████████████████▌  | 47.9M/51.1M [01:16&lt;00:07, 422kB/s]
+ 94%|███████████████████████████████████▋  | 48.0M/51.1M [01:16&lt;00:07, 423kB/s]
+ 94%|███████████████████████████████████▋  | 48.0M/51.1M [01:16&lt;00:06, 464kB/s]
+ 94%|███████████████████████████████████▋  | 48.1M/51.1M [01:16&lt;00:07, 392kB/s]
+ 94%|███████████████████████████████████▊  | 48.2M/51.1M [01:16&lt;00:06, 449kB/s]
+ 94%|███████████████████████████████████▊  | 48.2M/51.1M [01:16&lt;00:06, 425kB/s]
+ 94%|███████████████████████████████████▊  | 48.3M/51.1M [01:17&lt;00:06, 412kB/s]
+ 95%|███████████████████████████████████▉  | 48.3M/51.1M [01:17&lt;00:06, 423kB/s]
+ 95%|███████████████████████████████████▉  | 48.3M/51.1M [01:17&lt;00:06, 411kB/s]
+ 95%|███████████████████████████████████▉  | 48.4M/51.1M [01:17&lt;00:06, 428kB/s]
+ 95%|████████████████████████████████████  | 48.4M/51.1M [01:17&lt;00:06, 429kB/s]
+ 95%|████████████████████████████████████  | 48.5M/51.1M [01:17&lt;00:05, 440kB/s]
+ 95%|████████████████████████████████████  | 48.6M/51.1M [01:17&lt;00:05, 446kB/s]
+ 95%|████████████████████████████████████▏ | 48.6M/51.1M [01:17&lt;00:05, 456kB/s]
+ 95%|████████████████████████████████████▏ | 48.7M/51.1M [01:18&lt;00:05, 477kB/s]
+ 95%|████████████████████████████████████▏ | 48.7M/51.1M [01:18&lt;00:04, 475kB/s]
+ 95%|████████████████████████████████████▎ | 48.8M/51.1M [01:18&lt;00:04, 492kB/s]
+ 96%|████████████████████████████████████▎ | 48.9M/51.1M [01:18&lt;00:04, 500kB/s]
+ 96%|████████████████████████████████████▍ | 48.9M/51.1M [01:18&lt;00:04, 507kB/s]
+ 96%|████████████████████████████████████▍ | 49.0M/51.1M [01:18&lt;00:03, 529kB/s]
+ 96%|████████████████████████████████████▍ | 49.1M/51.1M [01:18&lt;00:03, 536kB/s]
+ 96%|████████████████████████████████████▌ | 49.1M/51.1M [01:18&lt;00:03, 550kB/s]
+ 96%|████████████████████████████████████▌ | 49.2M/51.1M [01:19&lt;00:03, 561kB/s]
+ 96%|████████████████████████████████████▋ | 49.3M/51.1M [01:19&lt;00:03, 573kB/s]
+ 97%|████████████████████████████████████▋ | 49.3M/51.1M [01:19&lt;00:03, 581kB/s]
+ 97%|████████████████████████████████████▋ | 49.4M/51.1M [01:19&lt;00:02, 599kB/s]
+ 97%|████████████████████████████████████▊ | 49.5M/51.1M [01:19&lt;00:02, 602kB/s]
+ 97%|████████████████████████████████████▊ | 49.5M/51.1M [01:19&lt;00:02, 624kB/s]
+ 97%|████████████████████████████████████▉ | 49.6M/51.1M [01:19&lt;00:02, 625kB/s]
+ 97%|████████████████████████████████████▉ | 49.7M/51.1M [01:19&lt;00:02, 641kB/s]
+ 97%|█████████████████████████████████████ | 49.8M/51.1M [01:19&lt;00:02, 642kB/s]
+ 98%|█████████████████████████████████████ | 49.8M/51.1M [01:20&lt;00:01, 638kB/s]
+ 98%|█████████████████████████████████████ | 49.9M/51.1M [01:20&lt;00:01, 646kB/s]
+ 98%|█████████████████████████████████████▏| 50.0M/51.1M [01:20&lt;00:01, 639kB/s]
+ 98%|█████████████████████████████████████▏| 50.1M/51.1M [01:20&lt;00:01, 634kB/s]
+ 98%|█████████████████████████████████████▎| 50.1M/51.1M [01:20&lt;00:01, 638kB/s]
+ 98%|█████████████████████████████████████▎| 50.2M/51.1M [01:20&lt;00:01, 635kB/s]
+ 98%|█████████████████████████████████████▎| 50.2M/51.1M [01:20&lt;00:01, 640kB/s]
+ 98%|█████████████████████████████████████▍| 50.3M/51.1M [01:20&lt;00:01, 650kB/s]
+ 99%|█████████████████████████████████████▍| 50.4M/51.1M [01:20&lt;00:01, 625kB/s]
+ 99%|█████████████████████████████████████▌| 50.5M/51.1M [01:21&lt;00:01, 622kB/s]
+ 99%|█████████████████████████████████████▌| 50.5M/51.1M [01:21&lt;00:00, 607kB/s]
+ 99%|█████████████████████████████████████▋| 50.6M/51.1M [01:21&lt;00:00, 606kB/s]
+ 99%|█████████████████████████████████████▋| 50.7M/51.1M [01:21&lt;00:00, 604kB/s]
+ 99%|█████████████████████████████████████▋| 50.7M/51.1M [01:21&lt;00:00, 520kB/s]
+ 99%|█████████████████████████████████████▊| 50.8M/51.1M [01:21&lt;00:00, 591kB/s]
+100%|█████████████████████████████████████▊| 50.9M/51.1M [01:21&lt;00:00, 581kB/s]
+100%|█████████████████████████████████████▉| 50.9M/51.1M [01:21&lt;00:00, 547kB/s]
+100%|█████████████████████████████████████▉| 51.0M/51.1M [01:21&lt;00:00, 544kB/s]
+100%|█████████████████████████████████████▉| 51.1M/51.1M [01:22&lt;00:00, 518kB/s]
   0%|                                              | 0.00/51.1M [00:00&lt;?, ?B/s]
-100%|██████████████████████████████████████| 51.1M/51.1M [00:00&lt;00:00, 224GB/s]
+100%|██████████████████████████████████████| 51.1M/51.1M [00:00&lt;00:00, 146GB/s]
 
   0%|                                              | 0.00/3.90k [00:00&lt;?, ?B/s]
   0%|                                              | 0.00/3.90k [00:00&lt;?, ?B/s]
-100%|█████████████████████████████████████| 3.90k/3.90k [00:00&lt;00:00, 19.6MB/s]
-Download complete in 01m39s (48.7 MB)
+100%|█████████████████████████████████████| 3.90k/3.90k [00:00&lt;00:00, 26.1MB/s]
+Download complete in 01m23s (48.7 MB)
 Extracting EDF parameters from /home/runner/mne_data/physionet-sleep-data/SC4001E0-PSG.edf...
 EDF file detected
 Setting channel info structure...
@@ -1492,8 +1382,8 @@
 - Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
 - Filter length: 45 samples (0.450 s)
 
-Writing /tmp/tmp4f42zyus/0/0-raw.fif
-Closing /tmp/tmp4f42zyus/0/0-raw.fif
+Writing /tmp/tmpvjq3k0_t/0/0-raw.fif
+Closing /tmp/tmpvjq3k0_t/0/0-raw.fif
 [done]
 Reading 0 ... 3260000  =      0.000 ... 32600.000 secs...
 Filtering raw data in 1 contiguous segment
@@ -1508,42 +1398,42 @@
 - Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
 - Filter length: 45 samples (0.450 s)
 
-Writing /tmp/tmp4f42zyus/1/1-raw.fif
-Closing /tmp/tmp4f42zyus/1/1-raw.fif
+Writing /tmp/tmpvjq3k0_t/1/1-raw.fif
+Closing /tmp/tmpvjq3k0_t/1/1-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmp4f42zyus contains other subdirectories or files [&#39;0&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmpvjq3k0_t contains other subdirectories or files [&#39;0&#39;].
   warnings.warn(
-Opening raw data file /tmp/tmp4f42zyus/0/0-raw.fif...
+Opening raw data file /tmp/tmpvjq3k0_t/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmp4f42zyus/1/1-raw.fif...
+Opening raw data file /tmp/tmpvjq3k0_t/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f9f81aff220&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f128f3e8220&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 Reading 0 ... 2507000  =      0.000 ... 25070.000 secs...
-Writing /tmp/tmp4f42zyus/0/0-raw.fif
-Closing /tmp/tmp4f42zyus/0/0-raw.fif
+Writing /tmp/tmpvjq3k0_t/0/0-raw.fif
+Closing /tmp/tmpvjq3k0_t/0/0-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:773: UserWarning: The number of saved datasets (1) does not match the number of existing subdirectories (2). You may now encounter a mix of differently preprocessed datasets!
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:777: UserWarning: The number of saved datasets (1) does not match the number of existing subdirectories (2). You may now encounter a mix of differently preprocessed datasets!
   warnings.warn(
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmp4f42zyus contains other subdirectories or files [&#39;1&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmpvjq3k0_t contains other subdirectories or files [&#39;1&#39;].
   warnings.warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f9f81aff220&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f128f3e8220&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 Reading 0 ... 3260000  =      0.000 ... 32600.000 secs...
-Writing /tmp/tmp4f42zyus/1/1-raw.fif
-Closing /tmp/tmp4f42zyus/1/1-raw.fif
+Writing /tmp/tmpvjq3k0_t/1/1-raw.fif
+Closing /tmp/tmpvjq3k0_t/1/1-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmp4f42zyus contains other subdirectories or files [&#39;0&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmpvjq3k0_t contains other subdirectories or files [&#39;0&#39;].
   warnings.warn(
-Opening raw data file /tmp/tmp4f42zyus/0/0-raw.fif...
+Opening raw data file /tmp/tmpvjq3k0_t/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmp4f42zyus/1/1-raw.fif...
+Opening raw data file /tmp/tmpvjq3k0_t/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
@@ -1555,19 +1445,19 @@
 EDF file detected
 Setting channel info structure...
 Creating raw.info structure...
-Opening raw data file /tmp/tmpgwi690jo/0/0-raw.fif...
+Opening raw data file /tmp/tmphz8hdcoi/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmpgwi690jo/1/1-raw.fif...
+Opening raw data file /tmp/tmphz8hdcoi/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
-Opening raw data file /tmp/tmpgwi690jo/0/0-raw.fif...
+Opening raw data file /tmp/tmphz8hdcoi/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmpgwi690jo/1/1-raw.fif...
+Opening raw data file /tmp/tmphz8hdcoi/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
@@ -1605,9 +1495,9 @@
 - Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
 - Filter length: 45 samples (0.450 s)
 
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f9f820894e0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f128dada380&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f9f820894e0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f128dada380&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 Extracting EDF parameters from /home/runner/mne_data/physionet-sleep-data/SC4001E0-PSG.edf...
 EDF file detected
@@ -1638,8 +1528,8 @@
 - Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
 - Filter length: 45 samples (0.450 s)
 
-Writing /tmp/tmpvtj60y_x/0/0-raw.fif
-Closing /tmp/tmpvtj60y_x/0/0-raw.fif
+Writing /tmp/tmpuoeu3_w1/0/0-raw.fif
+Closing /tmp/tmpuoeu3_w1/0/0-raw.fif
 [done]
 Reading 0 ... 3260000  =      0.000 ... 32600.000 secs...
 Filtering raw data in 1 contiguous segment
@@ -1654,42 +1544,42 @@
 - Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
 - Filter length: 45 samples (0.450 s)
 
-Writing /tmp/tmpvtj60y_x/1/1-raw.fif
-Closing /tmp/tmpvtj60y_x/1/1-raw.fif
+Writing /tmp/tmpuoeu3_w1/1/1-raw.fif
+Closing /tmp/tmpuoeu3_w1/1/1-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmpvtj60y_x contains other subdirectories or files [&#39;0&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmpuoeu3_w1 contains other subdirectories or files [&#39;0&#39;].
   warnings.warn(
-Opening raw data file /tmp/tmpvtj60y_x/0/0-raw.fif...
+Opening raw data file /tmp/tmpuoeu3_w1/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmpvtj60y_x/1/1-raw.fif...
+Opening raw data file /tmp/tmpuoeu3_w1/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f9f81ec4280&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f13541623b0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 Reading 0 ... 2507000  =      0.000 ... 25070.000 secs...
-Writing /tmp/tmpvtj60y_x/0/0-raw.fif
-Closing /tmp/tmpvtj60y_x/0/0-raw.fif
+Writing /tmp/tmpuoeu3_w1/0/0-raw.fif
+Closing /tmp/tmpuoeu3_w1/0/0-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:773: UserWarning: The number of saved datasets (1) does not match the number of existing subdirectories (2). You may now encounter a mix of differently preprocessed datasets!
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:777: UserWarning: The number of saved datasets (1) does not match the number of existing subdirectories (2). You may now encounter a mix of differently preprocessed datasets!
   warnings.warn(
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmpvtj60y_x contains other subdirectories or files [&#39;1&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmpuoeu3_w1 contains other subdirectories or files [&#39;1&#39;].
   warnings.warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f9f81ec4280&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f13541623b0&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 Reading 0 ... 3260000  =      0.000 ... 32600.000 secs...
-Writing /tmp/tmpvtj60y_x/1/1-raw.fif
-Closing /tmp/tmpvtj60y_x/1/1-raw.fif
+Writing /tmp/tmpuoeu3_w1/1/1-raw.fif
+Closing /tmp/tmpuoeu3_w1/1/1-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmpvtj60y_x contains other subdirectories or files [&#39;0&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmpuoeu3_w1 contains other subdirectories or files [&#39;0&#39;].
   warnings.warn(
-Opening raw data file /tmp/tmpvtj60y_x/0/0-raw.fif...
+Opening raw data file /tmp/tmpuoeu3_w1/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmpvtj60y_x/1/1-raw.fif...
+Opening raw data file /tmp/tmpuoeu3_w1/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
@@ -1701,19 +1591,19 @@
 EDF file detected
 Setting channel info structure...
 Creating raw.info structure...
-Opening raw data file /tmp/tmpufi4ur1h/0/0-raw.fif...
+Opening raw data file /tmp/tmp3mmu2kqx/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmpufi4ur1h/1/1-raw.fif...
+Opening raw data file /tmp/tmp3mmu2kqx/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
-Opening raw data file /tmp/tmpufi4ur1h/0/0-raw.fif...
+Opening raw data file /tmp/tmp3mmu2kqx/0/0-raw.fif...
 Isotrak not found
     Range : 2884000 ... 5391000 =  28840.000 ... 53910.000 secs
 Ready.
-Opening raw data file /tmp/tmpufi4ur1h/1/1-raw.fif...
+Opening raw data file /tmp/tmp3mmu2kqx/1/1-raw.fif...
 Isotrak not found
     Range : 1975000 ... 5235000 =  19750.000 ... 52350.000 secs
 Ready.
@@ -1751,9 +1641,9 @@
 - Upper transition bandwidth: 7.50 Hz (-6 dB cutoff frequency: 33.75 Hz)
 - Filter length: 45 samples (0.450 s)
 
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa04412a530&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f1353110d60&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
-/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7fa04412a530&gt;] to the mne.io.Raw of an EEGWindowsDataset.
+/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:244: UserWarning: Applying preprocessors [&lt;braindecode.preprocessing.preprocess.Preprocessor object at 0x7f1353110d60&gt;] to the mne.io.Raw of an EEGWindowsDataset.
   warn(
 Extracting EDF parameters from /home/runner/mne_data/physionet-sleep-data/SC4001E0-PSG.edf...
 EDF file detected
@@ -1796,8 +1686,8 @@
 Depending on available resources (e.g. in limited memory settings), it might
 therefore be more advantageous to use both parallelization and serialization
 together.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (2 minutes 21.167 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  857 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (2 minutes 4.980 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  940 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-benchmark-preprocessing-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/1c6590d134fa0befda654e89aa55b2ac/plot_benchmark_preprocessing.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_benchmark_preprocessing.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/datasets_io/plot_custom_dataset_example.html b/dev/auto_examples/datasets_io/plot_custom_dataset_example.html
index d88f993c..4546a6a9 100644
--- a/dev/auto_examples/datasets_io/plot_custom_dataset_example.html
+++ b/dev/auto_examples/datasets_io/plot_custom_dataset_example.html
@@ -684,7 +684,7 @@
 start_ind=0 -- stop_ind=500
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 1.887 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 2.243 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-custom-dataset-example-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/datasets_io/plot_load_save_datasets.html b/dev/auto_examples/datasets_io/plot_load_save_datasets.html
index 7c0dd546..7aa41a6d 100644
--- a/dev/auto_examples/datasets_io/plot_load_save_datasets.html
+++ b/dev/auto_examples/datasets_io/plot_load_save_datasets.html
@@ -609,7 +609,7 @@
 48 events found on stim channel stim
 Event IDs: [1 2 3 4]
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f9f81ad4ee0&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f1353110c70&gt;
 </pre></div>
 </div>
 <p>We save the dataset to a an existing directory. It will create a ‘.fif’ file
@@ -625,41 +625,41 @@
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Writing /tmp/tmp_3ygye_x/0/0-raw.fif
-Closing /tmp/tmp_3ygye_x/0/0-raw.fif
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Writing /tmp/tmp8rqaf5x8/0/0-raw.fif
+Closing /tmp/tmp8rqaf5x8/0/0-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/1/1-raw.fif
-Closing /tmp/tmp_3ygye_x/1/1-raw.fif
+Writing /tmp/tmp8rqaf5x8/1/1-raw.fif
+Closing /tmp/tmp8rqaf5x8/1/1-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/2/2-raw.fif
-Closing /tmp/tmp_3ygye_x/2/2-raw.fif
+Writing /tmp/tmp8rqaf5x8/2/2-raw.fif
+Closing /tmp/tmp8rqaf5x8/2/2-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/3/3-raw.fif
-Closing /tmp/tmp_3ygye_x/3/3-raw.fif
+Writing /tmp/tmp8rqaf5x8/3/3-raw.fif
+Closing /tmp/tmp8rqaf5x8/3/3-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/4/4-raw.fif
-Closing /tmp/tmp_3ygye_x/4/4-raw.fif
+Writing /tmp/tmp8rqaf5x8/4/4-raw.fif
+Closing /tmp/tmp8rqaf5x8/4/4-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/5/5-raw.fif
-Closing /tmp/tmp_3ygye_x/5/5-raw.fif
+Writing /tmp/tmp8rqaf5x8/5/5-raw.fif
+Closing /tmp/tmp8rqaf5x8/5/5-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/6/6-raw.fif
-Closing /tmp/tmp_3ygye_x/6/6-raw.fif
+Writing /tmp/tmp8rqaf5x8/6/6-raw.fif
+Closing /tmp/tmp8rqaf5x8/6/6-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/7/7-raw.fif
-Closing /tmp/tmp_3ygye_x/7/7-raw.fif
+Writing /tmp/tmp8rqaf5x8/7/7-raw.fif
+Closing /tmp/tmp8rqaf5x8/7/7-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/8/8-raw.fif
-Closing /tmp/tmp_3ygye_x/8/8-raw.fif
+Writing /tmp/tmp8rqaf5x8/8/8-raw.fif
+Closing /tmp/tmp8rqaf5x8/8/8-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/9/9-raw.fif
-Closing /tmp/tmp_3ygye_x/9/9-raw.fif
+Writing /tmp/tmp8rqaf5x8/9/9-raw.fif
+Closing /tmp/tmp8rqaf5x8/9/9-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/10/10-raw.fif
-Closing /tmp/tmp_3ygye_x/10/10-raw.fif
+Writing /tmp/tmp8rqaf5x8/10/10-raw.fif
+Closing /tmp/tmp8rqaf5x8/10/10-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/11/11-raw.fif
-Closing /tmp/tmp_3ygye_x/11/11-raw.fif
+Writing /tmp/tmp8rqaf5x8/11/11-raw.fif
+Closing /tmp/tmp8rqaf5x8/11/11-raw.fif
 [done]
 </pre></div>
 </div>
@@ -677,11 +677,11 @@
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opening raw data file /tmp/tmp_3ygye_x/1/1-raw.fif...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opening raw data file /tmp/tmp8rqaf5x8/1/1-raw.fif...
     Range : 0 ... 3868 =      0.000 ...   386.800 secs
 Ready.
 Reading 0 ... 3868  =      0.000 ...   386.800 secs...
-Opening raw data file /tmp/tmp_3ygye_x/3/3-raw.fif...
+Opening raw data file /tmp/tmp8rqaf5x8/3/3-raw.fif...
     Range : 0 ... 3868 =      0.000 ...   386.800 secs
 Ready.
 Reading 0 ... 3868  =      0.000 ...   386.800 secs...
@@ -756,15 +756,15 @@
 <span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Writing /tmp/tmp_3ygye_x/0/0-raw.fif
-Closing /tmp/tmp_3ygye_x/0/0-raw.fif
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Writing /tmp/tmp8rqaf5x8/0/0-raw.fif
+Closing /tmp/tmp8rqaf5x8/0/0-raw.fif
 [done]
-Writing /tmp/tmp_3ygye_x/1/1-raw.fif
-Closing /tmp/tmp_3ygye_x/1/1-raw.fif
+Writing /tmp/tmp8rqaf5x8/1/1-raw.fif
+Closing /tmp/tmp8rqaf5x8/1/1-raw.fif
 [done]
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:773: UserWarning: The number of saved datasets (2) does not match the number of existing subdirectories (12). You may now encounter a mix of differently preprocessed datasets!
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:777: UserWarning: The number of saved datasets (2) does not match the number of existing subdirectories (12). You may now encounter a mix of differently preprocessed datasets!
   warnings.warn(
-/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:784: UserWarning: Chosen directory /tmp/tmp_3ygye_x contains other subdirectories or files [&#39;8&#39;, &#39;11&#39;, &#39;2&#39;, &#39;3&#39;, &#39;5&#39;, &#39;4&#39;, &#39;6&#39;, &#39;7&#39;, &#39;9&#39;, &#39;10&#39;].
+/home/runner/work/braindecode/braindecode/braindecode/datasets/base.py:788: UserWarning: Chosen directory /tmp/tmp8rqaf5x8 contains other subdirectories or files [&#39;8&#39;, &#39;11&#39;, &#39;2&#39;, &#39;3&#39;, &#39;5&#39;, &#39;4&#39;, &#39;6&#39;, &#39;7&#39;, &#39;9&#39;, &#39;10&#39;].
   warnings.warn(
 </pre></div>
 </div>
@@ -781,7 +781,7 @@
 <a href="../../generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset" class="sphx-glr-backref-module-braindecode-datasets sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">windows_dataset_loaded</span></a><span class="o">.</span><span class="n">description</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opening raw data file /tmp/tmp_3ygye_x/0/0-raw.fif...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opening raw data file /tmp/tmp8rqaf5x8/0/0-raw.fif...
     Range : 0 ... 3868 =      0.000 ...   386.800 secs
 Ready.
 </pre></div>
@@ -822,7 +822,7 @@
 </div>
 </div>
 <br />
-<br /><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 4.661 seconds)</p>
+<br /><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 5.148 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-load-save-datasets-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/datasets_io/plot_mne_dataset_example.html b/dev/auto_examples/datasets_io/plot_mne_dataset_example.html
index 8f26ede4..770bbf0b 100644
--- a/dev/auto_examples/datasets_io/plot_mne_dataset_example.html
+++ b/dev/auto_examples/datasets_io/plot_mne_dataset_example.html
@@ -750,7 +750,7 @@
 </div>
 </div>
 <br />
-<br /><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 1.313 seconds)</p>
+<br /><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 1.515 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-mne-dataset-example-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/datasets_io/plot_moabb_dataset_example.html b/dev/auto_examples/datasets_io/plot_moabb_dataset_example.html
index f833f767..69355726 100644
--- a/dev/auto_examples/datasets_io/plot_moabb_dataset_example.html
+++ b/dev/auto_examples/datasets_io/plot_moabb_dataset_example.html
@@ -756,7 +756,7 @@
 <p>See our <a class="reference external" href="../model_building/plot_bcic_iv_2a_moabb_trial.html">Trialwise Decoding</a> and
 <a class="reference external" href="../model_building/plot_bcic_iv_2a_moabb_cropped.html">Cropped Decoding</a> examples for
 training with this dataset.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 4.582 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 4.855 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-moabb-dataset-example-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/datasets_io/plot_split_dataset.html b/dev/auto_examples/datasets_io/plot_split_dataset.html
index 6e49ef1b..ecdcc00b 100644
--- a/dev/auto_examples/datasets_io/plot_split_dataset.html
+++ b/dev/auto_examples/datasets_io/plot_split_dataset.html
@@ -691,7 +691,7 @@ <h3><a class="toc-backref" href="#id3" role="doc-backlink">By description inform
 <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">splits</span></a><span class="p">[</span><span class="s2">&quot;4&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">description</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04735e8c0&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b850&gt;, &#39;2&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b6d0&gt;, &#39;3&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b820&gt;, &#39;4&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675bb20&gt;, &#39;5&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675ba30&gt;}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1353110d60&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160520&gt;, &#39;2&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160190&gt;, &#39;3&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160160&gt;, &#39;4&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354161000&gt;, &#39;5&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160040&gt;}
 </pre></div>
 </div>
 <div class="output_subarea output_html rendered_html output_result">
@@ -747,7 +747,7 @@ <h3><a class="toc-backref" href="#id4" role="doc-backlink">By row index</a><a cl
 <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">splits</span></a><span class="p">[</span><span class="s2">&quot;0&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">description</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04735f700&gt;}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354d0fee0&gt;}
 </pre></div>
 </div>
 <div class="output_subarea output_html rendered_html output_result">
@@ -807,7 +807,7 @@ <h3><a class="toc-backref" href="#id4" role="doc-backlink">By row index</a><a cl
 <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">splits</span></a><span class="p">[</span><span class="s2">&quot;2&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">description</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b370&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b130&gt;, &#39;2&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b760&gt;}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354161090&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160e50&gt;, &#39;2&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160910&gt;}
 </pre></div>
 </div>
 <div class="output_subarea output_html rendered_html output_result">
@@ -885,7 +885,7 @@ <h3><a class="toc-backref" href="#id4" role="doc-backlink">By row index</a><a cl
 <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">splits</span></a><span class="p">[</span><span class="s2">&quot;test&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">description</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;train&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675bbb0&gt;, &#39;valid&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b2e0&gt;, &#39;test&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675ba30&gt;}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{&#39;train&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354d80c40&gt;, &#39;valid&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160760&gt;, &#39;test&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354160220&gt;}
 </pre></div>
 </div>
 <div class="output_subarea output_html rendered_html output_result">
@@ -1002,19 +1002,19 @@ <h2><a class="toc-backref" href="#id5" role="doc-backlink">Observation</a><a cla
 </pre></div>
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Using description info
-{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f9f72dcf250&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b6d0&gt;, &#39;2&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa046758040&gt;, &#39;3&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa044129510&gt;, &#39;4&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa044129690&gt;, &#39;5&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa044128b80&gt;}
+{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75cd90&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75f700&gt;, &#39;2&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75dc00&gt;, &#39;3&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75e5f0&gt;, &#39;4&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75fac0&gt;, &#39;5&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75c820&gt;}
 
 Splitting by row index
-{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675acb0&gt;}
+{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f1354d0fee0&gt;}
 
 Multiple row index split
-{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa046758040&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675b3a0&gt;}
+{&#39;0&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75fac0&gt;, &#39;1&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75e5f0&gt;}
 
 Specifying keys
-{&#39;train&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675acb0&gt;, &#39;test&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7fa04675ba30&gt;}
+{&#39;train&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a67cd30&gt;, &#39;test&#39;: &lt;braindecode.datasets.base.BaseConcatDataset object at 0x7f136a75dc00&gt;}
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 4.314 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 4.811 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  633 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-split-dataset-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/datasets_io/plot_tuh_discrete_multitarget.html b/dev/auto_examples/datasets_io/plot_tuh_discrete_multitarget.html
index e264b029..a74ed1bc 100644
--- a/dev/auto_examples/datasets_io/plot_tuh_discrete_multitarget.html
+++ b/dev/auto_examples/datasets_io/plot_tuh_discrete_multitarget.html
@@ -710,7 +710,7 @@ <h2>Exploring DataLoader<a class="headerlink" href="#exploring-dataloader" title
 batch_ind=[tensor([0, 1, 2, 3]), tensor([   0, 1000, 2000, 2600]), tensor([1000, 2000, 3000, 3600])]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 2.794 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 3.223 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  634 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-datasets-io-plot-tuh-discrete-multitarget-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/datasets_io/sg_execution_times.html b/dev/auto_examples/datasets_io/sg_execution_times.html
index ecebf401..d046bc14 100644
--- a/dev/auto_examples/datasets_io/sg_execution_times.html
+++ b/dev/auto_examples/datasets_io/sg_execution_times.html
@@ -449,7 +449,7 @@
   
   <section id="computation-times">
 <span id="sphx-glr-auto-examples-datasets-io-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Link to this heading">#</a></h1>
-<p><strong>02:40.718</strong> total execution time for 8 files <strong>from auto_examples/datasets_io</strong>:</p>
+<p><strong>02:26.774</strong> total execution time for 8 files <strong>from auto_examples/datasets_io</strong>:</p>
 <div class="docutils container">
 <style scoped>
 <link href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css" rel="stylesheet" />
@@ -471,32 +471,32 @@
 </thead>
 <tbody>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_benchmark_preprocessing.html#sphx-glr-auto-examples-datasets-io-plot-benchmark-preprocessing-py"><span class="std std-ref">Benchmarking preprocessing with parallelization and serialization</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_benchmark_preprocessing.py</span></code>)</p></td>
-<td><p>02:21.167</p></td>
-<td><p>857.3</p></td>
+<td><p>02:04.980</p></td>
+<td><p>940.2</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_load_save_datasets.html#sphx-glr-auto-examples-datasets-io-plot-load-save-datasets-py"><span class="std std-ref">Load and save dataset example</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_load_save_datasets.py</span></code>)</p></td>
-<td><p>00:04.661</p></td>
-<td><p>633.0</p></td>
+<td><p>00:05.148</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_moabb_dataset_example.html#sphx-glr-auto-examples-datasets-io-plot-moabb-dataset-example-py"><span class="std std-ref">MOABB Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_moabb_dataset_example.py</span></code>)</p></td>
-<td><p>00:04.582</p></td>
-<td><p>632.9</p></td>
+<td><p>00:04.855</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_split_dataset.html#sphx-glr-auto-examples-datasets-io-plot-split-dataset-py"><span class="std std-ref">Split Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_split_dataset.py</span></code>)</p></td>
-<td><p>00:04.314</p></td>
-<td><p>632.9</p></td>
+<td><p>00:04.811</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_tuh_discrete_multitarget.html#sphx-glr-auto-examples-datasets-io-plot-tuh-discrete-multitarget-py"><span class="std std-ref">Multiple discrete targets with the TUH EEG Corpus</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_tuh_discrete_multitarget.py</span></code>)</p></td>
-<td><p>00:02.794</p></td>
+<td><p>00:03.223</p></td>
 <td><p>633.6</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_custom_dataset_example.html#sphx-glr-auto-examples-datasets-io-plot-custom-dataset-example-py"><span class="std std-ref">Custom Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_custom_dataset_example.py</span></code>)</p></td>
-<td><p>00:01.887</p></td>
-<td><p>632.9</p></td>
+<td><p>00:02.243</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_mne_dataset_example.html#sphx-glr-auto-examples-datasets-io-plot-mne-dataset-example-py"><span class="std std-ref">MNE Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_mne_dataset_example.py</span></code>)</p></td>
-<td><p>00:01.313</p></td>
-<td><p>632.9</p></td>
+<td><p>00:01.515</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="benchmark_lazy_eager_loading.html#sphx-glr-auto-examples-datasets-io-benchmark-lazy-eager-loading-py"><span class="std std-ref">Benchmarking eager and lazy loading</span></a> (<code class="docutils literal notranslate"><span class="pre">benchmark_lazy_eager_loading.py</span></code>)</p></td>
 <td><p>00:00.000</p></td>
diff --git a/dev/auto_examples/model_building/plot_basic_training_epochs.html b/dev/auto_examples/model_building/plot_basic_training_epochs.html
index ee70efb8..3036c464 100644
--- a/dev/auto_examples/model_building/plot_basic_training_epochs.html
+++ b/dev/auto_examples/model_building/plot_basic_training_epochs.html
@@ -572,7 +572,7 @@ <h3><a class="toc-backref" href="#id5" role="doc-backlink">Examining the model</
 <div class="highlight-Python notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../../generated/braindecode.models.ShallowFBCSPNet.html#braindecode.models.ShallowFBCSPNet" title="braindecode.models.ShallowFBCSPNet" class="sphx-glr-backref-module-braindecode-models sphx-glr-backref-type-py-class"><span class="n">ShallowFBCSPNet</span></a><span class="o">.</span><span class="vm">__doc__</span><span class="p">)</span>
 </pre></div>
 </div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Shallow ConvNet model from Schirrmeister et al 2017.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Shallow ConvNet model from Schirrmeister et al. 2017 [Schirrmeister2017]_.
 
 Model described in [Schirrmeister2017]_.
 
@@ -775,16 +775,16 @@ <h2><a class="toc-backref" href="#id7" role="doc-backlink">Training your model (
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    valid_acc    valid_loss     dur
 -------  -----------  ------------  ------
-      1       0.3500        2.3122  0.0158
-      2       0.3500        2.3122  0.0094
-      3       0.3500        2.3122  0.0084
-      4       0.3500        2.3122  0.0082
-      5       0.3500        2.3122  0.0082
-      6       0.3500        2.3122  0.0081
-      7       0.3500        2.3122  0.0080
-      8       0.3500        2.3122  0.0080
-      9       0.3500        2.3122  0.0080
-     10       0.3500        2.3122  0.0080
+      1       0.1500        4.3746  0.0154
+      2       0.1500        4.3746  0.0092
+      3       0.1500        4.3746  0.0086
+      4       0.1500        4.3746  0.0085
+      5       0.1500        4.3746  0.0082
+      6       0.1500        4.3746  0.0082
+      7       0.1500        4.3746  0.0082
+      8       0.1500        4.3746  0.0083
+      9       0.1500        4.3746  0.0082
+     10       0.1500        4.3746  0.0082
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=============================================================================================================================================
@@ -888,8 +888,8 @@ <h2><a class="toc-backref" href="#id8" role="doc-backlink">References</a><a clas
 Online: <a class="reference external" href="http://dx.doi.org/10.1002/hbm.23730">http://dx.doi.org/10.1002/hbm.23730</a></p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 1.788 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  667 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 1.827 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  669 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-basic-training-epochs-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/fff46913db5173d3ae22c1113acffb45/plot_basic_training_epochs.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_basic_training_epochs.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.html b/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.html
index f072c91b..49a8719f 100644
--- a/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.html
+++ b/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.html
@@ -637,56 +637,56 @@ <h2><a class="toc-backref" href="#id6" role="doc-backlink">Loading and preproces
   warnings.warn(
 
   0%|                                              | 0.00/44.1M [00:00&lt;?, ?B/s]
-  0%|                                     | 8.19k/44.1M [00:00&lt;15:17, 48.0kB/s]
-  0%|                                      | 32.8k/44.1M [00:00&lt;07:05, 103kB/s]
-  0%|                                      | 96.3k/44.1M [00:00&lt;03:16, 224kB/s]
-  0%|▏                                      | 209k/44.1M [00:00&lt;01:51, 392kB/s]
-  1%|▍                                      | 432k/44.1M [00:00&lt;01:00, 716kB/s]
-  2%|▊                                     | 889k/44.1M [00:01&lt;00:31, 1.37MB/s]
-  4%|█▌                                   | 1.80M/44.1M [00:01&lt;00:15, 2.64MB/s]
-  8%|███                                  | 3.62M/44.1M [00:01&lt;00:07, 5.15MB/s]
- 17%|██████                               | 7.27M/44.1M [00:01&lt;00:03, 10.1MB/s]
- 23%|████████▌                            | 10.2M/44.1M [00:01&lt;00:02, 12.1MB/s]
- 30%|███████████▏                         | 13.4M/44.1M [00:01&lt;00:02, 13.2MB/s]
- 39%|██████████████▍                      | 17.1M/44.1M [00:02&lt;00:01, 16.3MB/s]
- 46%|████████████████▉                    | 20.2M/44.1M [00:02&lt;00:01, 16.8MB/s]
- 55%|████████████████████▍                | 24.3M/44.1M [00:02&lt;00:01, 17.7MB/s]
- 64%|███████████████████████▊             | 28.4M/44.1M [00:02&lt;00:00, 18.9MB/s]
- 74%|███████████████████████████▏         | 32.4M/44.1M [00:02&lt;00:00, 19.8MB/s]
- 83%|██████████████████████████████▌      | 36.5M/44.1M [00:03&lt;00:00, 20.3MB/s]
- 92%|██████████████████████████████████   | 40.5M/44.1M [00:03&lt;00:00, 20.8MB/s]
+  0%|                                     | 8.19k/44.1M [00:00&lt;14:46, 49.7kB/s]
+  0%|                                      | 32.8k/44.1M [00:00&lt;06:50, 107kB/s]
+  0%|                                      | 96.3k/44.1M [00:00&lt;03:09, 232kB/s]
+  0%|▏                                      | 209k/44.1M [00:00&lt;01:47, 407kB/s]
+  1%|▍                                      | 432k/44.1M [00:00&lt;00:59, 739kB/s]
+  2%|▊                                     | 889k/44.1M [00:01&lt;00:30, 1.41MB/s]
+  4%|█▌                                   | 1.80M/44.1M [00:01&lt;00:15, 2.73MB/s]
+  8%|███                                  | 3.62M/44.1M [00:01&lt;00:07, 5.33MB/s]
+ 17%|██████                               | 7.27M/44.1M [00:01&lt;00:03, 10.5MB/s]
+ 20%|███████▏                             | 8.62M/44.1M [00:01&lt;00:03, 9.40MB/s]
+ 29%|██████████▌                          | 12.6M/44.1M [00:01&lt;00:02, 13.6MB/s]
+ 35%|████████████▉                        | 15.5M/44.1M [00:02&lt;00:01, 14.7MB/s]
+ 43%|███████████████▊                     | 18.9M/44.1M [00:02&lt;00:01, 16.4MB/s]
+ 51%|███████████████████                  | 22.7M/44.1M [00:02&lt;00:01, 18.3MB/s]
+ 60%|██████████████████████▎              | 26.5M/44.1M [00:02&lt;00:00, 19.7MB/s]
+ 69%|█████████████████████████▋           | 30.6M/44.1M [00:02&lt;00:00, 19.7MB/s]
+ 78%|████████████████████████████▊        | 34.2M/44.1M [00:02&lt;00:00, 20.3MB/s]
+ 86%|███████████████████████████████▉     | 38.1M/44.1M [00:03&lt;00:00, 21.0MB/s]
+ 93%|██████████████████████████████████▎  | 40.8M/44.1M [00:03&lt;00:00, 19.6MB/s]
   0%|                                              | 0.00/44.1M [00:00&lt;?, ?B/s]
-100%|██████████████████████████████████████| 44.1M/44.1M [00:00&lt;00:00, 267GB/s]
+100%|██████████████████████████████████████| 44.1M/44.1M [00:00&lt;00:00, 166GB/s]
 /home/runner/.local/lib/python3.10/site-packages/urllib3/connectionpool.py:1064: InsecureRequestWarning: Unverified HTTPS request is being made to host &#39;lampx.tugraz.at&#39;. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/1.26.x/advanced-usage.html#ssl-warnings
   warnings.warn(
 
   0%|                                              | 0.00/42.3M [00:00&lt;?, ?B/s]
-  0%|                                     | 8.19k/42.3M [00:00&lt;14:47, 47.7kB/s]
-  0%|                                      | 32.8k/42.3M [00:00&lt;06:49, 103kB/s]
-  0%|                                      | 96.3k/42.3M [00:00&lt;03:08, 224kB/s]
-  0%|▏                                      | 209k/42.3M [00:00&lt;01:47, 392kB/s]
-  1%|▍                                      | 432k/42.3M [00:00&lt;00:58, 715kB/s]
-  2%|▊                                     | 889k/42.3M [00:01&lt;00:30, 1.37MB/s]
-  4%|█▌                                   | 1.80M/42.3M [00:01&lt;00:15, 2.64MB/s]
-  9%|███▏                                 | 3.62M/42.3M [00:01&lt;00:07, 5.15MB/s]
- 13%|████▊                                | 5.54M/42.3M [00:01&lt;00:05, 6.99MB/s]
- 18%|██████▋                              | 7.62M/42.3M [00:01&lt;00:04, 8.55MB/s]
- 23%|████████▌                            | 9.75M/42.3M [00:01&lt;00:03, 9.68MB/s]
- 28%|██████████▍                          | 11.9M/42.3M [00:02&lt;00:02, 10.5MB/s]
- 33%|████████████▎                        | 14.1M/42.3M [00:02&lt;00:02, 11.2MB/s]
- 39%|██████████████▎                      | 16.4M/42.3M [00:02&lt;00:02, 11.7MB/s]
- 44%|████████████████▎                    | 18.6M/42.3M [00:02&lt;00:01, 12.2MB/s]
- 50%|██████████████████▎                  | 21.0M/42.3M [00:02&lt;00:01, 12.5MB/s]
- 55%|████████████████████▎                | 23.3M/42.3M [00:02&lt;00:01, 12.8MB/s]
- 61%|██████████████████████▍              | 25.7M/42.3M [00:03&lt;00:01, 13.1MB/s]
- 66%|████████████████████████▌            | 28.1M/42.3M [00:03&lt;00:01, 13.3MB/s]
- 72%|██████████████████████████▋          | 30.5M/42.3M [00:03&lt;00:00, 13.4MB/s]
- 78%|████████████████████████████▊        | 33.0M/42.3M [00:03&lt;00:00, 13.6MB/s]
- 84%|██████████████████████████████▉      | 35.4M/42.3M [00:03&lt;00:00, 13.8MB/s]
- 90%|█████████████████████████████████▏   | 37.9M/42.3M [00:03&lt;00:00, 14.0MB/s]
- 96%|███████████████████████████████████▍ | 40.5M/42.3M [00:04&lt;00:00, 14.2MB/s]
+  0%|                                     | 8.19k/42.3M [00:00&lt;14:35, 48.3kB/s]
+  0%|                                      | 32.8k/42.3M [00:00&lt;06:44, 105kB/s]
+  0%|                                      | 96.3k/42.3M [00:00&lt;03:06, 227kB/s]
+  0%|▏                                      | 209k/42.3M [00:00&lt;01:45, 397kB/s]
+  1%|▍                                      | 432k/42.3M [00:00&lt;00:57, 725kB/s]
+  2%|▊                                     | 889k/42.3M [00:01&lt;00:29, 1.39MB/s]
+  4%|█▌                                   | 1.80M/42.3M [00:01&lt;00:15, 2.68MB/s]
+  9%|███▏                                 | 3.62M/42.3M [00:01&lt;00:07, 5.22MB/s]
+ 17%|██████▎                              | 7.27M/42.3M [00:01&lt;00:03, 10.3MB/s]
+ 23%|████████▌                            | 9.80M/42.3M [00:01&lt;00:02, 11.0MB/s]
+ 31%|███████████▍                         | 13.1M/42.3M [00:01&lt;00:02, 13.9MB/s]
+ 35%|████████████▊                        | 14.7M/42.3M [00:02&lt;00:02, 11.7MB/s]
+ 44%|████████████████▎                    | 18.7M/42.3M [00:02&lt;00:01, 14.9MB/s]
+ 51%|██████████████████▉                  | 21.7M/42.3M [00:02&lt;00:01, 15.6MB/s]
+ 60%|██████████████████████               | 25.2M/42.3M [00:02&lt;00:01, 16.9MB/s]
+ 64%|███████████████████████▌             | 26.9M/42.3M [00:02&lt;00:01, 14.5MB/s]
+ 69%|█████████████████████████▌           | 29.2M/42.3M [00:02&lt;00:00, 14.3MB/s]
+ 75%|███████████████████████████▊         | 31.8M/42.3M [00:03&lt;00:00, 14.5MB/s]
+ 81%|██████████████████████████████▏      | 34.5M/42.3M [00:03&lt;00:00, 14.8MB/s]
+ 88%|████████████████████████████████▍    | 37.1M/42.3M [00:03&lt;00:00, 15.1MB/s]
+ 91%|█████████████████████████████████▊   | 38.7M/42.3M [00:03&lt;00:00, 12.9MB/s]
+ 95%|███████████████████████████████████▏ | 40.3M/42.3M [00:03&lt;00:00, 12.1MB/s]
+100%|████████████████████████████████████▉| 42.2M/42.3M [00:04&lt;00:00, 11.8MB/s]
   0%|                                              | 0.00/42.3M [00:00&lt;?, ?B/s]
-100%|██████████████████████████████████████| 42.3M/42.3M [00:00&lt;00:00, 243GB/s]
+100%|██████████████████████████████████████| 42.3M/42.3M [00:00&lt;00:00, 273GB/s]
 48 events found on stim channel stim
 Event IDs: [1 2 3 4]
 48 events found on stim channel stim
@@ -714,7 +714,7 @@ <h2><a class="toc-backref" href="#id6" role="doc-backlink">Loading and preproces
 /home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f9f81a8ff40&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f128f2bd690&gt;
 </pre></div>
 </div>
 </section>
@@ -925,8 +925,8 @@ <h2><a class="toc-backref" href="#id10" role="doc-backlink">Training</a><a class
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  ----------------  ------------  ------  ------
-      1            0.2569        1.2896            0.2847        1.6368  0.0006  8.1381
-      2            0.5069        1.1231            0.4549        1.2402  0.0000  8.1108
+      1            0.2569        1.2896            0.2847        1.6368  0.0006  8.1147
+      2            0.5069        1.1231            0.4549        1.2402  0.0000  8.0410
 </pre></div>
 </div>
 </section>
@@ -1034,8 +1034,8 @@ <h2><a class="toc-backref" href="#id13" role="doc-backlink">References</a><a cla
 Hum. Brain Mapping, 38: 5391-5420. <a class="reference external" href="https://doi.org/10.1002/hbm.23730">https://doi.org/10.1002/hbm.23730</a>.</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 45.109 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1478 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 44.249 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  1466 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-bcic-iv-2a-moabb-cropped-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/3862cafd7f0d815e434319ffe525afc8/plot_bcic_iv_2a_moabb_cropped.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_bcic_iv_2a_moabb_cropped.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.html b/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.html
index f4a48397..7c390f25 100644
--- a/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.html
+++ b/dev/auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.html
@@ -628,7 +628,7 @@ <h3><a class="toc-backref" href="#id10" role="doc-backlink">Preprocessing</a><a
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7fa0473e24a0&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f1354c2e080&gt;
 </pre></div>
 </div>
 </section>
@@ -815,10 +815,10 @@ <h2><a class="toc-backref" href="#id14" role="doc-backlink">Model Training</a><a
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2500        1.4121       0.2500            0.2500        1.9819  0.0006  1.6067
-      2            0.2743        1.2012       0.2396            0.2396        1.6471  0.0005  1.5157
-      3            0.3646        1.1829       0.3056            0.3056        1.3931  0.0002  1.5297
-      4            0.5486        1.0702       0.3854            0.3854        1.2944  0.0000  1.5135
+      1            0.2500        1.4121       0.2500            0.2500        1.9819  0.0006  1.6485
+      2            0.2743        1.2012       0.2396            0.2396        1.6471  0.0005  1.5039
+      3            0.3646        1.1829       0.3056            0.3056        1.3931  0.0002  1.5547
+      4            0.5486        1.0702       0.3854            0.3854        1.2944  0.0000  1.5111
 </pre></div>
 </div>
 </section>
@@ -929,8 +929,8 @@ <h2><a class="toc-backref" href="#id17" role="doc-backlink">References</a><a cla
 Hum. Brain Mapping, 38: 5391-5420. <a class="reference external" href="https://doi.org/10.1002/hbm.23730">https://doi.org/10.1002/hbm.23730</a>.</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 12.885 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1126 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 13.339 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  865 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-bcic-iv-2a-moabb-trial-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/9a4447462c3b255ba7e5ca212bbadd52/plot_bcic_iv_2a_moabb_trial.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_bcic_iv_2a_moabb_trial.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/model_building/plot_how_train_test_and_tune.html b/dev/auto_examples/model_building/plot_how_train_test_and_tune.html
index e5065b1d..51bec270 100644
--- a/dev/auto_examples/model_building/plot_how_train_test_and_tune.html
+++ b/dev/auto_examples/model_building/plot_how_train_test_and_tune.html
@@ -682,7 +682,7 @@ <h3><a class="toc-backref" href="#id11" role="doc-backlink">Preprocessing data</
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7fa05c1fa770&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f128f2e0f40&gt;
 </pre></div>
 </div>
 </section>
@@ -878,8 +878,8 @@ <h3><a class="toc-backref" href="#id16" role="doc-backlink">Option 1: Simple Tra
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.2500        1.4121  0.0006  1.2985
-      2            0.2778        1.2511  0.0000  1.1529
+      1            0.2500        1.4121  0.0006  1.2593
+      2            0.2778        1.2511  0.0000  1.1532
 Test acc: 25.35%
 </pre></div>
 </div>
@@ -997,8 +997,8 @@ <h3><a class="toc-backref" href="#id18" role="doc-backlink">Option 2: Train-Val-
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.4696        1.2018       0.3621            0.3621        1.3319  0.0006  1.0364
-      2            0.5565        1.0764       0.4310            0.4310        1.2548  0.0000  0.9357
+      1            0.4696        1.2018       0.3621            0.3621        1.3319  0.0006  1.0641
+      2            0.5565        1.0764       0.4310            0.4310        1.2548  0.0000  0.9305
 Test acc: 37.85%
 </pre></div>
 </div>
@@ -1121,24 +1121,24 @@ <h3><a class="toc-backref" href="#id20" role="doc-backlink">Option 3: k-Fold Cro
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.5565        1.1427  0.0006  0.9968
-      2            0.6304        1.0168  0.0000  0.9071
+      1            0.5565        1.1427  0.0006  0.9858
+      2            0.6304        1.0168  0.0000  0.8740
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.4087        1.1915  0.0006  0.9265
-      2            0.5478        1.0847  0.0000  0.9173
+      1            0.4087        1.1915  0.0006  0.8772
+      2            0.5478        1.0847  0.0000  0.8839
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.4870        1.1963  0.0006  0.9182
-      2            0.5696        1.0312  0.0000  0.8871
+      1            0.4870        1.1963  0.0006  0.8501
+      2            0.5696        1.0312  0.0000  0.8693
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.5714        1.0981  0.0006  0.8983
-      2            0.6407        1.0374  0.0000  0.9070
+      1            0.5714        1.0981  0.0006  0.8858
+      2            0.6407        1.0374  0.0000  0.8922
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.5411        1.1276  0.0006  0.9052
-      2            0.6494        1.0019  0.0000  0.9088
+      1            0.5411        1.1276  0.0006  0.8757
+      2            0.6494        1.0019  0.0000  0.8782
 Validation accuracy: 48.94+-4.01%
 </pre></div>
 </div>
@@ -1273,16 +1273,16 @@ <h3><a class="toc-backref" href="#id23" role="doc-backlink">Option 1: Train-Val-
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Fitting 1 folds for each of 2 candidates, totalling 2 fits
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.3957        1.3644  0.0063  0.9802
-      2            0.4217        1.0517  0.0000  0.8754
+      1            0.3957        1.3644  0.0063  1.0445
+      2            0.4217        1.0517  0.0000  0.9222
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.5739        1.0748  0.0006  0.8659
-      2            0.6565        1.0285  0.0000  0.8491
+      1            0.5739        1.0748  0.0006  0.9235
+      2            0.6565        1.0285  0.0000  0.9252
   epoch    train_accuracy    train_loss      lr     dur
 -------  ----------------  ------------  ------  ------
-      1            0.5868        1.1749  0.0006  1.1487
-      2            0.6389        1.0555  0.0000  1.1564
+      1            0.5868        1.1749  0.0006  1.2275
+      2            0.6389        1.0555  0.0000  1.2217
 </pre></div>
 </div>
 </section>
@@ -1320,8 +1320,8 @@ <h2><a class="toc-backref" href="#id25" role="doc-backlink">References</a><a cla
 Hum. Brain Mapping, 38: 5391-5420. <a class="reference external" href="https://doi.org/10.1002/hbm.23730">https://doi.org/10.1002/hbm.23730</a>.</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 33.996 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1075 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 34.426 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  864 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-how-train-test-and-tune-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/263464a28477cf8decb861ae6e2e9be7/plot_how_train_test_and_tune.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_how_train_test_and_tune.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.html b/dev/auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.html
index 42cc60ee..965cc59d 100644
--- a/dev/auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.html
+++ b/dev/auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.html
@@ -659,7 +659,7 @@ <h3><a class="toc-backref" href="#id11" role="doc-backlink">Preprocessing</a><a
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f9f81a78580&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f1354cb9870&gt;
 </pre></div>
 </div>
 </section>
@@ -861,92 +861,92 @@ <h2><a class="toc-backref" href="#id16" role="doc-backlink">Training</a><a class
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2609        1.4822       0.3448            0.3448       12.8587  0.0063  0.6145
-      2            0.2609        0.7629       0.3448            0.3448        3.4101  0.0000  0.5793
+      1            0.2609        1.4822       0.3448            0.3448       12.8587  0.0063  0.6291
+      2            0.2609        0.7629       0.3448            0.3448        3.4101  0.0000  0.5598
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2348        1.4107       0.3448            0.3448       12.3777  0.0063  0.5830
-      2            0.2783        0.7427       0.3448            0.3448        4.0815  0.0000  0.5557
+      1            0.2348        1.4107       0.3448            0.3448       12.3777  0.0063  0.5574
+      2            0.2783        0.7427       0.3448            0.3448        4.0815  0.0000  0.5536
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2783        1.4500       0.0690            0.0690        2.0014  0.0001  0.5543
-      2            0.3043        1.3866       0.1379            0.1379        1.5656  0.0000  0.5784
+      1            0.2783        1.4500       0.0690            0.0690        2.0014  0.0001  0.5548
+      2            0.3043        1.3866       0.1379            0.1379        1.5656  0.0000  0.5801
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2348        1.4712       0.3448            0.3448        1.7099  0.0001  0.5790
-      2            0.2957        1.3762       0.2759            0.2759        1.4668  0.0000  0.5733
+      1            0.2348        1.4712       0.3448            0.3448        1.7099  0.0001  0.5763
+      2            0.2957        1.3762       0.2759            0.2759        1.4668  0.0000  0.5528
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2609        1.5884       0.3448            0.3448        2.5505  0.0063  0.5716
-      2            0.4609        0.8677       0.3448            0.3448        1.6186  0.0000  0.5535
+      1            0.2609        1.5884       0.3448            0.3448        2.5505  0.0063  0.5578
+      2            0.4609        0.8677       0.3448            0.3448        1.6186  0.0000  0.5540
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2348        1.6299       0.3448            0.3448        5.0177  0.0063  0.5538
-      2            0.3739        0.9309       0.4138            0.4138        1.9423  0.0000  0.5826
+      1            0.2348        1.6299       0.3448            0.3448        5.0177  0.0063  0.5552
+      2            0.3739        0.9309       0.4138            0.4138        1.9423  0.0000  0.5813
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2957        1.4859       0.2759            0.2759        1.4425  0.0001  0.5816
-      2            0.3304        1.4221       0.2414            0.2414        1.4645  0.0000  0.5664
+      1            0.2957        1.4859       0.2759            0.2759        1.4425  0.0001  0.5810
+      2            0.3304        1.4221       0.2414            0.2414        1.4645  0.0000  0.5695
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2609        1.5369       0.3448            0.3448        1.3557  0.0001  0.5651
-      2            0.3304        1.4058       0.4828            0.4828        1.3220  0.0000  0.5549
+      1            0.2609        1.5369       0.3448            0.3448        1.3557  0.0001  0.5518
+      2            0.3304        1.4058       0.4828            0.4828        1.3220  0.0000  0.5537
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2348        1.7556       0.2759            0.2759        7.6143  0.0063  0.5539
-      2            0.2348        1.4904       0.2759            0.2759        2.4326  0.0000  0.5812
+      1            0.2348        1.7556       0.2759            0.2759        7.6143  0.0063  0.5544
+      2            0.2348        1.4904       0.2759            0.2759        2.4326  0.0000  0.6239
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.3739        1.6044       0.3793            0.3793        2.9512  0.0063  0.5779
-      2            0.3913        1.3977       0.4483            0.4483        1.5505  0.0000  0.5673
+      1            0.3739        1.6044       0.3793            0.3793        2.9512  0.0063  0.5819
+      2            0.3913        1.3977       0.4483            0.4483        1.5505  0.0000  0.5654
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2696        1.5889       0.2414            0.2414        2.0679  0.0001  0.5659
-      2            0.2435        1.5474       0.2069            0.2069        1.5949  0.0000  0.5534
+      1            0.2696        1.5889       0.2414            0.2414        2.0679  0.0001  0.5695
+      2            0.2435        1.5474       0.2069            0.2069        1.5949  0.0000  0.5562
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2870        1.6018       0.1379            0.1379        1.9570  0.0001  0.5563
-      2            0.2696        1.4638       0.2069            0.2069        1.5792  0.0000  0.5825
+      1            0.2870        1.6018       0.1379            0.1379        1.9570  0.0001  0.5572
+      2            0.2696        1.4638       0.2069            0.2069        1.5792  0.0000  0.5838
 Can only infer signal shape of array-like and Datasets, got &lt;class &#39;skorch.helper.SliceDataset&#39;&gt;.
 /home/runner/work/braindecode/braindecode/braindecode/models/base.py:24: UserWarning: ShallowFBCSPNet: &#39;input_window_samples&#39; is depreciated. Use &#39;n_times&#39; instead.
   warnings.warn(
   epoch    train_accuracy    train_loss    valid_acc    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  -----------  ----------------  ------------  ------  ------
-      1            0.2783        1.4333       0.2586            0.2586        1.4455  0.0001  1.1315
-      2            0.3174        1.3830       0.2586            0.2586        1.4360  0.0000  1.1387
+      1            0.2783        1.4333       0.2586            0.2586        1.4455  0.0001  1.1488
+      2            0.3174        1.3830       0.2586            0.2586        1.4360  0.0000  1.1478
 </pre></div>
 </div>
 </section>
@@ -1022,8 +1022,8 @@ <h2><a class="toc-backref" href="#id19" role="doc-backlink">References</a><a cla
 Hum. Brain Mapping, 38: 5391-5420. <a class="reference external" href="https://doi.org/10.1002/hbm.23730">https://doi.org/10.1002/hbm.23730</a>.</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 30.151 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  674 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 30.716 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  863 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-hyperparameter-tuning-with-scikit-learn-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/a39e4245738e55e0eb7084c545ed05bc/plot_hyperparameter_tuning_with_scikit-learn.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_hyperparameter_tuning_with_scikit-learn.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/model_building/plot_regression.html b/dev/auto_examples/model_building/plot_regression.html
index ea86a950..899a8373 100644
--- a/dev/auto_examples/model_building/plot_regression.html
+++ b/dev/auto_examples/model_building/plot_regression.html
@@ -807,9 +807,9 @@ <h2>Model training<a class="headerlink" href="#model-training" title="Link to th
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_loss    train_neg_root_mean_squared_error    valid_loss    valid_neg_root_mean_squared_error      lr     dur
 -------  ------------  -----------------------------------  ------------  -----------------------------------  ------  ------
-      1       10.7929                              -4.4190       21.6134                              -4.6526  0.0010  1.1119
-      2        5.0613                              -1.3083        1.8263                              -1.3513  0.0005  1.0925
-      3        4.5674                              -1.1753        1.9237                              -1.3850  0.0000  1.0467
+      1       10.7929                              -4.4190       21.6134                              -4.6526  0.0010  1.1033
+      2        5.0613                              -1.3083        1.8263                              -1.3513  0.0005  1.0739
+      3        4.5674                              -1.1753        1.9237                              -1.3850  0.0000  1.0482
 </pre></div>
 </div>
 </section>
@@ -835,7 +835,7 @@ <h2>Model evaluation<a class="headerlink" href="#model-evaluation" title="Link t
 <a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.html#matplotlib.axes.Axes" title="matplotlib.axes.Axes" class="sphx-glr-backref-module-matplotlib-axes sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">axes</span></a><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">&quot;Train&quot;</span><span class="p">,</span> <span class="s2">&quot;Valid&quot;</span><span class="p">])</span>
 </pre></div>
 </div>
-<img src="../../_images/sphx_glr_plot_regression_001.png" srcset="../../_images/sphx_glr_plot_regression_001.png" alt="Train and valid losses, Train and valid errors" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;matplotlib.legend.Legend object at 0x7fa05c159780&gt;
+<img src="../../_images/sphx_glr_plot_regression_001.png" srcset="../../_images/sphx_glr_plot_regression_001.png" alt="Train and valid losses, Train and valid errors" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;matplotlib.legend.Legend object at 0x7f1354d9df30&gt;
 </pre></div>
 </div>
 </section>
@@ -878,7 +878,7 @@ <h2>References<a class="headerlink" href="#references" title="Link to this headi
 “On the convergence of adam and beyond.” arXiv preprint arXiv:1904.09237 (2019).</p>
 </aside>
 </aside>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 7.172 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 7.292 seconds)</p>
 <p><strong>Estimated memory usage:</strong>  634 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-regression-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
diff --git a/dev/auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.html b/dev/auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.html
index 5ef3e5c8..c651f2bd 100644
--- a/dev/auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.html
+++ b/dev/auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.html
@@ -647,7 +647,7 @@ <h3><a class="toc-backref" href="#id4" role="doc-backlink">Preprocessing, the of
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/home/runner/work/braindecode/braindecode/braindecode/preprocessing/preprocess.py:69: UserWarning: Preprocessing choices with lambda functions cannot be saved.
   warn(&quot;Preprocessing choices with lambda functions cannot be saved.&quot;)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7fa04674ad70&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f1354c5c3a0&gt;
 </pre></div>
 </div>
 </section>
@@ -935,26 +935,26 @@ <h3><a class="toc-backref" href="#id9" role="doc-backlink">Option 1: Pure PyTorc
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/2:
   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Epoch 1/2, Batch 1/5, Loss: 1.438274:   0%|          | 0/5 [00:00&lt;?, ?it/s]
-Epoch 1/2, Batch 1/5, Loss: 1.438274:  20%|██        | 1/5 [00:00&lt;00:01,  2.64it/s]
-Epoch 1/2, Batch 2/5, Loss: 1.374445:  20%|██        | 1/5 [00:00&lt;00:01,  2.64it/s]
-Epoch 1/2, Batch 2/5, Loss: 1.374445:  40%|████      | 2/5 [00:00&lt;00:00,  3.07it/s]
-Epoch 1/2, Batch 3/5, Loss: 1.478137:  40%|████      | 2/5 [00:00&lt;00:00,  3.07it/s]
-Epoch 1/2, Batch 3/5, Loss: 1.478137:  60%|██████    | 3/5 [00:00&lt;00:00,  3.13it/s]
-Epoch 1/2, Batch 4/5, Loss: 1.357355:  60%|██████    | 3/5 [00:01&lt;00:00,  3.13it/s]
-Epoch 1/2, Batch 4/5, Loss: 1.357355:  80%|████████  | 4/5 [00:01&lt;00:00,  3.27it/s]
-Epoch 1/2, Batch 5/5, Loss: 1.563599:  80%|████████  | 4/5 [00:01&lt;00:00,  3.27it/s]
-Epoch 1/2, Batch 5/5, Loss: 1.563599: 100%|██████████| 5/5 [00:01&lt;00:00,  4.00it/s]
-Epoch 1/2, Batch 5/5, Loss: 1.563599: 100%|██████████| 5/5 [00:01&lt;00:00,  3.53it/s]
+Epoch 1/2, Batch 1/5, Loss: 1.438274:  20%|██        | 1/5 [00:00&lt;00:01,  2.49it/s]
+Epoch 1/2, Batch 2/5, Loss: 1.374445:  20%|██        | 1/5 [00:00&lt;00:01,  2.49it/s]
+Epoch 1/2, Batch 2/5, Loss: 1.374445:  40%|████      | 2/5 [00:00&lt;00:01,  2.99it/s]
+Epoch 1/2, Batch 3/5, Loss: 1.478137:  40%|████      | 2/5 [00:00&lt;00:01,  2.99it/s]
+Epoch 1/2, Batch 3/5, Loss: 1.478137:  60%|██████    | 3/5 [00:00&lt;00:00,  3.21it/s]
+Epoch 1/2, Batch 4/5, Loss: 1.357355:  60%|██████    | 3/5 [00:01&lt;00:00,  3.21it/s]
+Epoch 1/2, Batch 4/5, Loss: 1.357355:  80%|████████  | 4/5 [00:01&lt;00:00,  3.33it/s]
+Epoch 1/2, Batch 5/5, Loss: 1.563599:  80%|████████  | 4/5 [00:01&lt;00:00,  3.33it/s]
+Epoch 1/2, Batch 5/5, Loss: 1.563599: 100%|██████████| 5/5 [00:01&lt;00:00,  3.87it/s]
+Epoch 1/2, Batch 5/5, Loss: 1.563599: 100%|██████████| 5/5 [00:01&lt;00:00,  3.47it/s]
 
   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Batch 1/5, Loss: 1.912368:   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Batch 2/5, Loss: 1.797205:   0%|          | 0/5 [00:00&lt;?, ?it/s]
-Batch 2/5, Loss: 1.797205:  40%|████      | 2/5 [00:00&lt;00:00, 13.29it/s]
-Batch 3/5, Loss: 2.060518:  40%|████      | 2/5 [00:00&lt;00:00, 13.29it/s]
-Batch 4/5, Loss: 1.902958:  40%|████      | 2/5 [00:00&lt;00:00, 13.29it/s]
-Batch 4/5, Loss: 1.902958:  80%|████████  | 4/5 [00:00&lt;00:00, 13.29it/s]
-Batch 5/5, Loss: 1.936484:  80%|████████  | 4/5 [00:00&lt;00:00, 13.29it/s]
-Batch 5/5, Loss: 1.936484: 100%|██████████| 5/5 [00:00&lt;00:00, 14.71it/s]
+Batch 2/5, Loss: 1.797205:  40%|████      | 2/5 [00:00&lt;00:00, 13.25it/s]
+Batch 3/5, Loss: 2.060518:  40%|████      | 2/5 [00:00&lt;00:00, 13.25it/s]
+Batch 4/5, Loss: 1.902958:  40%|████      | 2/5 [00:00&lt;00:00, 13.25it/s]
+Batch 4/5, Loss: 1.902958:  80%|████████  | 4/5 [00:00&lt;00:00, 13.25it/s]
+Batch 5/5, Loss: 1.936484:  80%|████████  | 4/5 [00:00&lt;00:00, 13.25it/s]
+Batch 5/5, Loss: 1.936484: 100%|██████████| 5/5 [00:00&lt;00:00, 14.67it/s]
 Test Accuracy: 25.0%, Test Loss: 1.921907
 
 Train Accuracy: 28.47%, Average Train Loss: 1.442362, Test Accuracy: 25.0%, Average Test Loss: 1.921907
@@ -962,26 +962,26 @@ <h3><a class="toc-backref" href="#id9" role="doc-backlink">Option 1: Pure PyTorc
 Epoch 2/2:
   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Epoch 2/2, Batch 1/5, Loss: 1.174715:   0%|          | 0/5 [00:00&lt;?, ?it/s]
-Epoch 2/2, Batch 1/5, Loss: 1.174715:  20%|██        | 1/5 [00:00&lt;00:01,  3.23it/s]
-Epoch 2/2, Batch 2/5, Loss: 1.192104:  20%|██        | 1/5 [00:00&lt;00:01,  3.23it/s]
-Epoch 2/2, Batch 2/5, Loss: 1.192104:  40%|████      | 2/5 [00:00&lt;00:00,  3.39it/s]
-Epoch 2/2, Batch 3/5, Loss: 1.236566:  40%|████      | 2/5 [00:00&lt;00:00,  3.39it/s]
-Epoch 2/2, Batch 3/5, Loss: 1.236566:  60%|██████    | 3/5 [00:00&lt;00:00,  3.45it/s]
-Epoch 2/2, Batch 4/5, Loss: 1.246258:  60%|██████    | 3/5 [00:01&lt;00:00,  3.45it/s]
-Epoch 2/2, Batch 4/5, Loss: 1.246258:  80%|████████  | 4/5 [00:01&lt;00:00,  3.48it/s]
-Epoch 2/2, Batch 5/5, Loss: 1.033339:  80%|████████  | 4/5 [00:01&lt;00:00,  3.48it/s]
-Epoch 2/2, Batch 5/5, Loss: 1.033339: 100%|██████████| 5/5 [00:01&lt;00:00,  4.05it/s]
-Epoch 2/2, Batch 5/5, Loss: 1.033339: 100%|██████████| 5/5 [00:01&lt;00:00,  3.74it/s]
+Epoch 2/2, Batch 1/5, Loss: 1.174715:  20%|██        | 1/5 [00:00&lt;00:01,  3.53it/s]
+Epoch 2/2, Batch 2/5, Loss: 1.192104:  20%|██        | 1/5 [00:00&lt;00:01,  3.53it/s]
+Epoch 2/2, Batch 2/5, Loss: 1.192104:  40%|████      | 2/5 [00:00&lt;00:00,  3.52it/s]
+Epoch 2/2, Batch 3/5, Loss: 1.236566:  40%|████      | 2/5 [00:00&lt;00:00,  3.52it/s]
+Epoch 2/2, Batch 3/5, Loss: 1.236566:  60%|██████    | 3/5 [00:00&lt;00:00,  3.36it/s]
+Epoch 2/2, Batch 4/5, Loss: 1.246258:  60%|██████    | 3/5 [00:01&lt;00:00,  3.36it/s]
+Epoch 2/2, Batch 4/5, Loss: 1.246258:  80%|████████  | 4/5 [00:01&lt;00:00,  3.43it/s]
+Epoch 2/2, Batch 5/5, Loss: 1.033339:  80%|████████  | 4/5 [00:01&lt;00:00,  3.43it/s]
+Epoch 2/2, Batch 5/5, Loss: 1.033339: 100%|██████████| 5/5 [00:01&lt;00:00,  4.20it/s]
+Epoch 2/2, Batch 5/5, Loss: 1.033339: 100%|██████████| 5/5 [00:01&lt;00:00,  3.83it/s]
 
   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Batch 1/5, Loss: 1.442473:   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Batch 2/5, Loss: 1.365749:   0%|          | 0/5 [00:00&lt;?, ?it/s]
-Batch 2/5, Loss: 1.365749:  40%|████      | 2/5 [00:00&lt;00:00, 13.35it/s]
-Batch 3/5, Loss: 1.516186:  40%|████      | 2/5 [00:00&lt;00:00, 13.35it/s]
-Batch 4/5, Loss: 1.417750:  40%|████      | 2/5 [00:00&lt;00:00, 13.35it/s]
-Batch 4/5, Loss: 1.417750:  80%|████████  | 4/5 [00:00&lt;00:00, 13.34it/s]
-Batch 5/5, Loss: 1.447024:  80%|████████  | 4/5 [00:00&lt;00:00, 13.34it/s]
-Batch 5/5, Loss: 1.447024: 100%|██████████| 5/5 [00:00&lt;00:00, 14.78it/s]
+Batch 2/5, Loss: 1.365749:  40%|████      | 2/5 [00:00&lt;00:00, 13.36it/s]
+Batch 3/5, Loss: 1.516186:  40%|████      | 2/5 [00:00&lt;00:00, 13.36it/s]
+Batch 4/5, Loss: 1.417750:  40%|████      | 2/5 [00:00&lt;00:00, 13.36it/s]
+Batch 4/5, Loss: 1.417750:  80%|████████  | 4/5 [00:00&lt;00:00, 13.35it/s]
+Batch 5/5, Loss: 1.447024:  80%|████████  | 4/5 [00:00&lt;00:00, 13.35it/s]
+Batch 5/5, Loss: 1.447024: 100%|██████████| 5/5 [00:00&lt;00:00, 14.79it/s]
 Test Accuracy: 24.7%, Test Loss: 1.437836
 
 Train Accuracy: 47.22%, Average Train Loss: 1.176596, Test Accuracy: 24.7%, Average Test Loss: 1.437836
@@ -1061,32 +1061,32 @@ <h3><a class="toc-backref" href="#id10" role="doc-backlink">Option 2: Train it w
 Training: |          | 0/? [00:00&lt;?, ?it/s]
 Training:   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Epoch 0:   0%|          | 0/5 [00:00&lt;?, ?it/s]
-Epoch 0:  20%|██        | 1/5 [00:00&lt;00:01,  2.58it/s]
-Epoch 0:  20%|██        | 1/5 [00:00&lt;00:01,  2.58it/s, v_num=0]
-Epoch 0:  40%|████      | 2/5 [00:00&lt;00:01,  2.96it/s, v_num=0]
-Epoch 0:  40%|████      | 2/5 [00:00&lt;00:01,  2.95it/s, v_num=0]
-Epoch 0:  60%|██████    | 3/5 [00:00&lt;00:00,  3.08it/s, v_num=0]
-Epoch 0:  60%|██████    | 3/5 [00:00&lt;00:00,  3.08it/s, v_num=0]
-Epoch 0:  80%|████████  | 4/5 [00:01&lt;00:00,  3.19it/s, v_num=0]
-Epoch 0:  80%|████████  | 4/5 [00:01&lt;00:00,  3.19it/s, v_num=0]
-Epoch 0: 100%|██████████| 5/5 [00:01&lt;00:00,  3.55it/s, v_num=0]
-Epoch 0: 100%|██████████| 5/5 [00:01&lt;00:00,  3.55it/s, v_num=0]
-Epoch 0: 100%|██████████| 5/5 [00:01&lt;00:00,  3.55it/s, v_num=0]
+Epoch 0:  20%|██        | 1/5 [00:00&lt;00:01,  2.67it/s]
+Epoch 0:  20%|██        | 1/5 [00:00&lt;00:01,  2.66it/s, v_num=0]
+Epoch 0:  40%|████      | 2/5 [00:00&lt;00:00,  3.03it/s, v_num=0]
+Epoch 0:  40%|████      | 2/5 [00:00&lt;00:00,  3.03it/s, v_num=0]
+Epoch 0:  60%|██████    | 3/5 [00:00&lt;00:00,  3.10it/s, v_num=0]
+Epoch 0:  60%|██████    | 3/5 [00:00&lt;00:00,  3.10it/s, v_num=0]
+Epoch 0:  80%|████████  | 4/5 [00:01&lt;00:00,  3.20it/s, v_num=0]
+Epoch 0:  80%|████████  | 4/5 [00:01&lt;00:00,  3.20it/s, v_num=0]
+Epoch 0: 100%|██████████| 5/5 [00:01&lt;00:00,  3.56it/s, v_num=0]
+Epoch 0: 100%|██████████| 5/5 [00:01&lt;00:00,  3.56it/s, v_num=0]
+Epoch 0: 100%|██████████| 5/5 [00:01&lt;00:00,  3.56it/s, v_num=0]
 Epoch 0:   0%|          | 0/5 [00:00&lt;?, ?it/s, v_num=0]
 Epoch 1:   0%|          | 0/5 [00:00&lt;?, ?it/s, v_num=0]
-Epoch 1:  20%|██        | 1/5 [00:00&lt;00:01,  3.41it/s, v_num=0]
-Epoch 1:  20%|██        | 1/5 [00:00&lt;00:01,  3.41it/s, v_num=0]
-Epoch 1:  40%|████      | 2/5 [00:00&lt;00:00,  3.48it/s, v_num=0]
-Epoch 1:  40%|████      | 2/5 [00:00&lt;00:00,  3.48it/s, v_num=0]
-Epoch 1:  60%|██████    | 3/5 [00:00&lt;00:00,  3.50it/s, v_num=0]
-Epoch 1:  60%|██████    | 3/5 [00:00&lt;00:00,  3.50it/s, v_num=0]
-Epoch 1:  80%|████████  | 4/5 [00:01&lt;00:00,  3.44it/s, v_num=0]
-Epoch 1:  80%|████████  | 4/5 [00:01&lt;00:00,  3.44it/s, v_num=0]
-Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.83it/s, v_num=0]
-Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.82it/s, v_num=0]
-Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.82it/s, v_num=0]`Trainer.fit` stopped: `max_epochs=2` reached.
-
-Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.81it/s, v_num=0]
+Epoch 1:  20%|██        | 1/5 [00:00&lt;00:01,  3.54it/s, v_num=0]
+Epoch 1:  20%|██        | 1/5 [00:00&lt;00:01,  3.54it/s, v_num=0]
+Epoch 1:  40%|████      | 2/5 [00:00&lt;00:00,  3.51it/s, v_num=0]
+Epoch 1:  40%|████      | 2/5 [00:00&lt;00:00,  3.51it/s, v_num=0]
+Epoch 1:  60%|██████    | 3/5 [00:00&lt;00:00,  3.49it/s, v_num=0]
+Epoch 1:  60%|██████    | 3/5 [00:00&lt;00:00,  3.49it/s, v_num=0]
+Epoch 1:  80%|████████  | 4/5 [00:01&lt;00:00,  3.50it/s, v_num=0]
+Epoch 1:  80%|████████  | 4/5 [00:01&lt;00:00,  3.50it/s, v_num=0]
+Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.87it/s, v_num=0]
+Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.87it/s, v_num=0]
+Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.87it/s, v_num=0]`Trainer.fit` stopped: `max_epochs=2` reached.
+
+Epoch 1: 100%|██████████| 5/5 [00:01&lt;00:00,  3.86it/s, v_num=0]
 /home/runner/.local/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/checkpoint_connector.py:145: `.test(ckpt_path=None)` was called without a model. The best model of the previous `fit` call will be used. You can pass `.test(ckpt_path=&#39;best&#39;)` to use the best model or `.test(ckpt_path=&#39;last&#39;)` to use the last model. If you pass a value, this warning will be silenced.
 Restoring states from the checkpoint path at /home/runner/work/braindecode/braindecode/examples/model_building/lightning_logs/version_0/checkpoints/epoch=1-step=10.ckpt
 Loaded model weights from the checkpoint at /home/runner/work/braindecode/braindecode/examples/model_building/lightning_logs/version_0/checkpoints/epoch=1-step=10.ckpt
@@ -1095,12 +1095,12 @@ <h3><a class="toc-backref" href="#id10" role="doc-backlink">Option 2: Train it w
 Testing: |          | 0/? [00:00&lt;?, ?it/s]
 Testing:   0%|          | 0/5 [00:00&lt;?, ?it/s]
 Testing DataLoader 0:   0%|          | 0/5 [00:00&lt;?, ?it/s]
-Testing DataLoader 0:  20%|██        | 1/5 [00:00&lt;00:00,  8.69it/s]
-Testing DataLoader 0:  40%|████      | 2/5 [00:00&lt;00:00, 10.06it/s]
-Testing DataLoader 0:  60%|██████    | 3/5 [00:00&lt;00:00, 10.92it/s]
-Testing DataLoader 0:  80%|████████  | 4/5 [00:00&lt;00:00, 11.41it/s]
-Testing DataLoader 0: 100%|██████████| 5/5 [00:00&lt;00:00, 12.52it/s]
-Testing DataLoader 0: 100%|██████████| 5/5 [00:00&lt;00:00, 12.38it/s]
+Testing DataLoader 0:  20%|██        | 1/5 [00:00&lt;00:00,  8.93it/s]
+Testing DataLoader 0:  40%|████      | 2/5 [00:00&lt;00:00, 10.59it/s]
+Testing DataLoader 0:  60%|██████    | 3/5 [00:00&lt;00:00, 10.66it/s]
+Testing DataLoader 0:  80%|████████  | 4/5 [00:00&lt;00:00, 10.96it/s]
+Testing DataLoader 0: 100%|██████████| 5/5 [00:00&lt;00:00, 12.03it/s]
+Testing DataLoader 0: 100%|██████████| 5/5 [00:00&lt;00:00, 11.90it/s]
 ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
        Test metric             DataLoader 0
 ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
@@ -1111,8 +1111,8 @@ <h3><a class="toc-backref" href="#id10" role="doc-backlink">Option 2: Train it w
 [{&#39;test_acc&#39;: 0.3125, &#39;test_loss&#39;: 1.4919893741607666}]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 11.548 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1020 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> (0 minutes 11.972 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  770 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-model-building-plot-train-in-pure-pytorch-and-pytorch-lightning-py">
 <div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/a86d0c5f3a882a069df1683a708d3e25/plot_train_in_pure_pytorch_and_pytorch_lightning.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_train_in_pure_pytorch_and_pytorch_lightning.ipynb</span></code></a></p>
diff --git a/dev/auto_examples/model_building/sg_execution_times.html b/dev/auto_examples/model_building/sg_execution_times.html
index 3b61f90c..236dd813 100644
--- a/dev/auto_examples/model_building/sg_execution_times.html
+++ b/dev/auto_examples/model_building/sg_execution_times.html
@@ -449,7 +449,7 @@
   
   <section id="computation-times">
 <span id="sphx-glr-auto-examples-model-building-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Link to this heading">#</a></h1>
-<p><strong>02:22.647</strong> total execution time for 7 files <strong>from auto_examples/model_building</strong>:</p>
+<p><strong>02:23.822</strong> total execution time for 7 files <strong>from auto_examples/model_building</strong>:</p>
 <div class="docutils container">
 <style scoped>
 <link href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css" rel="stylesheet" />
@@ -471,32 +471,32 @@
 </thead>
 <tbody>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_bcic_iv_2a_moabb_cropped.html#sphx-glr-auto-examples-model-building-plot-bcic-iv-2a-moabb-cropped-py"><span class="std std-ref">Cropped Decoding on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_bcic_iv_2a_moabb_cropped.py</span></code>)</p></td>
-<td><p>00:45.109</p></td>
-<td><p>1477.9</p></td>
+<td><p>00:44.249</p></td>
+<td><p>1466.3</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_how_train_test_and_tune.html#sphx-glr-auto-examples-model-building-plot-how-train-test-and-tune-py"><span class="std std-ref">How to train, test and tune your model?</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_how_train_test_and_tune.py</span></code>)</p></td>
-<td><p>00:33.996</p></td>
-<td><p>1074.6</p></td>
+<td><p>00:34.426</p></td>
+<td><p>863.6</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_hyperparameter_tuning_with_scikit-learn.html#sphx-glr-auto-examples-model-building-plot-hyperparameter-tuning-with-scikit-learn-py"><span class="std std-ref">Hyperparameter tuning with scikit-learn</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_hyperparameter_tuning_with_scikit-learn.py</span></code>)</p></td>
-<td><p>00:30.151</p></td>
-<td><p>673.8</p></td>
+<td><p>00:30.716</p></td>
+<td><p>863.4</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_bcic_iv_2a_moabb_trial.html#sphx-glr-auto-examples-model-building-plot-bcic-iv-2a-moabb-trial-py"><span class="std std-ref">Basic Brain Decoding on EEG Data</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_bcic_iv_2a_moabb_trial.py</span></code>)</p></td>
-<td><p>00:12.885</p></td>
-<td><p>1125.9</p></td>
+<td><p>00:13.339</p></td>
+<td><p>865.2</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_train_in_pure_pytorch_and_pytorch_lightning.html#sphx-glr-auto-examples-model-building-plot-train-in-pure-pytorch-and-pytorch-lightning-py"><span class="std std-ref">Training a Braindecode model in PyTorch</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_train_in_pure_pytorch_and_pytorch_lightning.py</span></code>)</p></td>
-<td><p>00:11.548</p></td>
-<td><p>1020.1</p></td>
+<td><p>00:11.972</p></td>
+<td><p>770.4</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="plot_regression.html#sphx-glr-auto-examples-model-building-plot-regression-py"><span class="std std-ref">Convolutional neural network regression model on fake data.</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_regression.py</span></code>)</p></td>
-<td><p>00:07.172</p></td>
-<td><p>634.0</p></td>
+<td><p>00:07.292</p></td>
+<td><p>633.8</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="plot_basic_training_epochs.html#sphx-glr-auto-examples-model-building-plot-basic-training-epochs-py"><span class="std std-ref">Simple training on MNE epochs</span></a> (<code class="docutils literal notranslate"><span class="pre">plot_basic_training_epochs.py</span></code>)</p></td>
-<td><p>00:01.788</p></td>
-<td><p>666.5</p></td>
+<td><p>00:01.827</p></td>
+<td><p>668.7</p></td>
 </tr>
 </tbody>
 </table>
diff --git a/dev/generated/braindecode.augmentation.AugmentedDataLoader.html b/dev/generated/braindecode.augmentation.AugmentedDataLoader.html
index 43cac38e..63760d70 100644
--- a/dev/generated/braindecode.augmentation.AugmentedDataLoader.html
+++ b/dev/generated/braindecode.augmentation.AugmentedDataLoader.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.BandstopFilter.html b/dev/generated/braindecode.augmentation.BandstopFilter.html
index 94998229..6ae7526f 100644
--- a/dev/generated/braindecode.augmentation.BandstopFilter.html
+++ b/dev/generated/braindecode.augmentation.BandstopFilter.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.ChannelsDropout.html b/dev/generated/braindecode.augmentation.ChannelsDropout.html
index 0f257509..242a02d2 100644
--- a/dev/generated/braindecode.augmentation.ChannelsDropout.html
+++ b/dev/generated/braindecode.augmentation.ChannelsDropout.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.ChannelsShuffle.html b/dev/generated/braindecode.augmentation.ChannelsShuffle.html
index 0e2a7005..65d69ae6 100644
--- a/dev/generated/braindecode.augmentation.ChannelsShuffle.html
+++ b/dev/generated/braindecode.augmentation.ChannelsShuffle.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.ChannelsSymmetry.html b/dev/generated/braindecode.augmentation.ChannelsSymmetry.html
index 0a9175f1..e0f3acbf 100644
--- a/dev/generated/braindecode.augmentation.ChannelsSymmetry.html
+++ b/dev/generated/braindecode.augmentation.ChannelsSymmetry.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.Compose.html b/dev/generated/braindecode.augmentation.Compose.html
index a1b2180b..cbf394f0 100644
--- a/dev/generated/braindecode.augmentation.Compose.html
+++ b/dev/generated/braindecode.augmentation.Compose.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.FTSurrogate.html b/dev/generated/braindecode.augmentation.FTSurrogate.html
index efa91aeb..18dca62e 100644
--- a/dev/generated/braindecode.augmentation.FTSurrogate.html
+++ b/dev/generated/braindecode.augmentation.FTSurrogate.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.FrequencyShift.html b/dev/generated/braindecode.augmentation.FrequencyShift.html
index 7d400ddd..bbb85fc6 100644
--- a/dev/generated/braindecode.augmentation.FrequencyShift.html
+++ b/dev/generated/braindecode.augmentation.FrequencyShift.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.GaussianNoise.html b/dev/generated/braindecode.augmentation.GaussianNoise.html
index 4663c13f..c4d6d97f 100644
--- a/dev/generated/braindecode.augmentation.GaussianNoise.html
+++ b/dev/generated/braindecode.augmentation.GaussianNoise.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.IdentityTransform.html b/dev/generated/braindecode.augmentation.IdentityTransform.html
index 75472de2..f9e4c00e 100644
--- a/dev/generated/braindecode.augmentation.IdentityTransform.html
+++ b/dev/generated/braindecode.augmentation.IdentityTransform.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.MaskEncoding.html b/dev/generated/braindecode.augmentation.MaskEncoding.html
index 74b1cd14..dd344228 100644
--- a/dev/generated/braindecode.augmentation.MaskEncoding.html
+++ b/dev/generated/braindecode.augmentation.MaskEncoding.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,10 +602,11 @@
 <h1>braindecode.augmentation.MaskEncoding<a class="headerlink" href="#braindecode-augmentation-maskencoding" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.augmentation.MaskEncoding">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.</span></span><span class="sig-name descname"><span class="pre">MaskEncoding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probability</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_mask_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1183-L1268"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.MaskEncoding" title="Link to this definition">#</a></dt>
-<dd><p>Replaces randomly chosen contiguous part (or parts) of all channels by
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.</span></span><span class="sig-name descname"><span class="pre">MaskEncoding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probability</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_mask_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1185-L1272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.MaskEncoding" title="Link to this definition">#</a></dt>
+<dd><p>MaskEncoding from <a class="reference internal" href="#r9102599ed233-1" id="id1">[1]</a>.</p>
+<p>Replaces randomly chosen contiguous part (or parts) of all channels by
 zeros (if more than one segment, it may overlap).</p>
-<p>Implementation based on <a class="reference internal" href="#r9102599ed233-1" id="id1">[1]</a></p>
+<p>Implementation based on <a class="reference internal" href="#r9102599ed233-1" id="id2">[1]</a></p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -622,17 +622,18 @@ <h1>braindecode.augmentation.MaskEncoding<a class="headerlink" href="#braindecod
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r9102599ed233-1" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">1</a><span class="fn-bracket">]</span></span>
-<p>Ding, Wenlong, et al. “A Novel Data Augmentation Approach</p>
-</div>
-</div>
-<p>Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI.”
+<span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
+<p>Ding, Wenlong, et al. “A Novel Data Augmentation Approach
+Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI.”
 IEEE Transactions on Neural Systems and Rehabilitation Engineering
 32 (2024): 875-886.</p>
+</div>
+</div>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.augmentation.MaskEncoding.get_augmentation_params">
-<span class="sig-name descname"><span class="pre">get_augmentation_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">batch</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1233-L1268"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.MaskEncoding.get_augmentation_params" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_augmentation_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">batch</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1237-L1272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.MaskEncoding.get_augmentation_params" title="Link to this definition">#</a></dt>
 <dd><p>Return transform parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -652,38 +653,42 @@ <h1>braindecode.augmentation.MaskEncoding<a class="headerlink" href="#braindecod
 
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.augmentation.MaskEncoding.operation">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">operation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">segment_length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/functional.py#L1046-L1094"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.MaskEncoding.operation" title="Link to this definition">#</a></dt>
-<dd><p>Replaces a contiguous part (or parts) of all channels by zeros
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">operation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">segment_length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/functional.py#L1046-L1096"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.MaskEncoding.operation" title="Link to this definition">#</a></dt>
+<dd><p>Mark encoding from Ding et al. (2024) from <a class="reference internal" href="#raa3392861949-ding2024" id="id3">[ding2024]</a>.</p>
+<p>Replaces a contiguous part (or parts) of all channels by zeros
 (if more than one segment, it may overlap).</p>
-<blockquote>
-<div><p>Implementation based on <span id="id2">[Raa3392861949-1]</span></p>
-</div></blockquote>
+<p>Implementation based on <a class="reference internal" href="#raa3392861949-ding2024" id="id4">[ding2024]</a></p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><dl class="simple">
-<dt><strong>X</strong><span class="classifier">torch.Tensor</span></dt><dd><p>EEG input example or batch.</p>
-</dd>
-<dt><strong>y</strong><span class="classifier">torch.Tensor</span></dt><dd><p>EEG labels for the example or batch.</p>
-</dd>
-<dt><strong>time_start</strong><span class="classifier">torch.Tensor</span></dt><dd><p>Tensor of integers containing the position (in last dimension) where to
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>X</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – EEG input example or batch.</p></li>
+<li><p><strong>y</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – EEG labels for the example or batch.</p></li>
+<li><p><strong>time_start</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – Tensor of integers containing the position (in last dimension) where to
 start masking the signal. Should have “n_segments” times the size of the first
-dimension of X (i.e. “n_segments” start positions per example in the batch).</p>
-</dd>
-<dt><strong>segment_length: int</strong></dt><dd><p>Length of each segment to zero out.</p>
-</dd>
-<dt><strong>n_segments</strong><span class="classifier">int</span></dt><dd><p>Number of segments to zero out in each example.</p>
-</dd>
-</dl>
+dimension of X (i.e. “n_segments” start positions per example in the batch).</p></li>
+<li><p><strong>segment_length</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Length of each segment to zero out.</p></li>
+<li><p><strong>n_segments</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of segments to zero out in each example.</p></li>
+</ul>
 </dd>
 <dt class="field-even">Returns<span class="colon">:</span></dt>
-<dd class="field-even"><dl class="simple">
-<dt>torch.Tensor</dt><dd><p>Transformed inputs.</p>
-</dd>
-<dt>torch.Tensor</dt><dd><p>Transformed labels.</p>
-</dd>
-</dl>
+<dd class="field-even"><p><ul class="simple">
+<li><p><em>torch.Tensor</em> – Transformed inputs.</p></li>
+<li><p><em>torch.Tensor</em> – Transformed labels.</p></li>
+</ul>
+</p>
 </dd>
 </dl>
+<p class="rubric">References</p>
+<div role="list" class="citation-list">
+<div class="citation" id="raa3392861949-ding2024" role="doc-biblioentry">
+<span class="label"><span class="fn-bracket">[</span>ding2024<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id3">1</a>,<a role="doc-backlink" href="#id4">2</a>)</span>
+<p>Ding, Wenlong, et al. A Novel Data Augmentation Approach
+Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI.
+IEEE Transactions on Neural Systems and Rehabilitation Engineering
+32 (2024): 875-886.</p>
+</div>
+</div>
 </dd></dl>
 
 </dd></dl>
diff --git a/dev/generated/braindecode.augmentation.Mixup.html b/dev/generated/braindecode.augmentation.Mixup.html
index 8d02cd7d..657c0de7 100644
--- a/dev/generated/braindecode.augmentation.Mixup.html
+++ b/dev/generated/braindecode.augmentation.Mixup.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.SegmentationReconstruction.html b/dev/generated/braindecode.augmentation.SegmentationReconstruction.html
index e4fd896d..d74c94b3 100644
--- a/dev/generated/braindecode.augmentation.SegmentationReconstruction.html
+++ b/dev/generated/braindecode.augmentation.SegmentationReconstruction.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,13 +602,12 @@
 <h1>braindecode.augmentation.SegmentationReconstruction<a class="headerlink" href="#braindecode-augmentation-segmentationreconstruction" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.augmentation.SegmentationReconstruction">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.</span></span><span class="sig-name descname"><span class="pre">SegmentationReconstruction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probability</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1078-L1180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.SegmentationReconstruction" title="Link to this definition">#</a></dt>
-<dd><dl class="simple">
-<dt>Applies a segmentation-reconstruction transform to the input data, as</dt><dd><p>proposed in _[1]. It segments each trial in the batch and randomly mix
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.</span></span><span class="sig-name descname"><span class="pre">SegmentationReconstruction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probability</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1078-L1182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.SegmentationReconstruction" title="Link to this definition">#</a></dt>
+<dd><p>Segmentation Reconstruction from Lotte (2015) <a class="reference internal" href="#r78e7a66c7d6f-lotte2015" id="id1">[Lotte2015]</a>.</p>
+<p>Applies a segmentation-reconstruction transform to the input data, as
+proposed in <a class="reference internal" href="#r78e7a66c7d6f-lotte2015" id="id2">[Lotte2015]</a>. It segments each trial in the batch and randomly mix
 it to generate new synthetic trials by label, preserving the original
 order of the segments in time domain.</p>
-</dd>
-</dl>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -625,17 +623,18 @@ <h1>braindecode.augmentation.SegmentationReconstruction<a class="headerlink" hre
 </dl>
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
-<div class="citation" id="r78e7a66c7d6f-1" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
-<p>Lotte, F. (2015). Signal processing approaches to minimize or</p>
+<div class="citation" id="r78e7a66c7d6f-lotte2015" role="doc-biblioentry">
+<span class="label"><span class="fn-bracket">[</span>Lotte2015<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
+<p>Lotte, F. (2015). Signal processing approaches to minimize
+or suppress calibration time in oscillatory activity-based brain–computer
+interfaces. Proceedings of the IEEE, 103(6), 871-890.</p>
 </div>
 </div>
-<p>suppress calibration time in oscillatory activity-based brain–computer
-interfaces. Proceedings of the IEEE, 103(6), 871-890.</p>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.augmentation.SegmentationReconstruction.get_augmentation_params">
-<span class="sig-name descname"><span class="pre">get_augmentation_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">batch</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1118-L1180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.SegmentationReconstruction.get_augmentation_params" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_augmentation_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">batch</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/transforms.py#L1120-L1182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.SegmentationReconstruction.get_augmentation_params" title="Link to this definition">#</a></dt>
 <dd><p>Return transform parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -656,8 +655,8 @@ <h1>braindecode.augmentation.SegmentationReconstruction<a class="headerlink" hre
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.augmentation.SegmentationReconstruction.operation">
 <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">operation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rand_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx_shuffle</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/functional.py#L975-L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.SegmentationReconstruction.operation" title="Link to this definition">#</a></dt>
-<dd><p>Segment and reconstruct EEG data in the time domain preserving labels.</p>
-<p>See <a class="reference internal" href="#r0f989fe74e1d-1" id="id1">[1]</a> for details.</p>
+<dd><p>Segment and reconstruct EEG data from <a class="reference internal" href="#r0f989fe74e1d-1" id="id3">[1]</a>.</p>
+<p>See <a class="reference internal" href="#r0f989fe74e1d-1" id="id4">[1]</a> for details.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -679,12 +678,13 @@ <h1>braindecode.augmentation.SegmentationReconstruction<a class="headerlink" hre
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r0f989fe74e1d-1" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">1</a><span class="fn-bracket">]</span></span>
-<p>Lotte, F. (2015). Signal processing approaches to minimize or</p>
+<span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id3">1</a>,<a role="doc-backlink" href="#id4">2</a>)</span>
+<p>Lotte, F. (2015). Signal processing approaches to minimize or
+suppress calibration time in oscillatory activity-based brain–computer
+interfaces. Proceedings of the IEEE, 103(6), 871-890.</p>
 </div>
 </div>
-<p>suppress calibration time in oscillatory activity-based brain–computer
-interfaces. Proceedings of the IEEE, 103(6), 871-890.</p>
 </dd></dl>
 
 </dd></dl>
diff --git a/dev/generated/braindecode.augmentation.SensorsRotation.html b/dev/generated/braindecode.augmentation.SensorsRotation.html
index 13eb65dc..bd4cb529 100644
--- a/dev/generated/braindecode.augmentation.SensorsRotation.html
+++ b/dev/generated/braindecode.augmentation.SensorsRotation.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.SensorsXRotation.html b/dev/generated/braindecode.augmentation.SensorsXRotation.html
index 89090a0e..e18516e1 100644
--- a/dev/generated/braindecode.augmentation.SensorsXRotation.html
+++ b/dev/generated/braindecode.augmentation.SensorsXRotation.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.SensorsYRotation.html b/dev/generated/braindecode.augmentation.SensorsYRotation.html
index 20e6f4fd..2a854655 100644
--- a/dev/generated/braindecode.augmentation.SensorsYRotation.html
+++ b/dev/generated/braindecode.augmentation.SensorsYRotation.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.SensorsZRotation.html b/dev/generated/braindecode.augmentation.SensorsZRotation.html
index 48ad12f5..fdaa464e 100644
--- a/dev/generated/braindecode.augmentation.SensorsZRotation.html
+++ b/dev/generated/braindecode.augmentation.SensorsZRotation.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.SignFlip.html b/dev/generated/braindecode.augmentation.SignFlip.html
index d6eccaf1..9b28a3b5 100644
--- a/dev/generated/braindecode.augmentation.SignFlip.html
+++ b/dev/generated/braindecode.augmentation.SignFlip.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.SmoothTimeMask.html b/dev/generated/braindecode.augmentation.SmoothTimeMask.html
index e9f5139e..2d93d452 100644
--- a/dev/generated/braindecode.augmentation.SmoothTimeMask.html
+++ b/dev/generated/braindecode.augmentation.SmoothTimeMask.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.TimeReverse.html b/dev/generated/braindecode.augmentation.TimeReverse.html
index ea6bd9cd..29a6742a 100644
--- a/dev/generated/braindecode.augmentation.TimeReverse.html
+++ b/dev/generated/braindecode.augmentation.TimeReverse.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.Transform.html b/dev/generated/braindecode.augmentation.Transform.html
index 731ffa3c..0828a151 100644
--- a/dev/generated/braindecode.augmentation.Transform.html
+++ b/dev/generated/braindecode.augmentation.Transform.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.bandstop_filter.html b/dev/generated/braindecode.augmentation.functional.bandstop_filter.html
index b432988e..ece62d38 100644
--- a/dev/generated/braindecode.augmentation.functional.bandstop_filter.html
+++ b/dev/generated/braindecode.augmentation.functional.bandstop_filter.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.channels_dropout.html b/dev/generated/braindecode.augmentation.functional.channels_dropout.html
index 809357b4..9bc0b71a 100644
--- a/dev/generated/braindecode.augmentation.functional.channels_dropout.html
+++ b/dev/generated/braindecode.augmentation.functional.channels_dropout.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.channels_permute.html b/dev/generated/braindecode.augmentation.functional.channels_permute.html
index 446b2712..ba806220 100644
--- a/dev/generated/braindecode.augmentation.functional.channels_permute.html
+++ b/dev/generated/braindecode.augmentation.functional.channels_permute.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.channels_shuffle.html b/dev/generated/braindecode.augmentation.functional.channels_shuffle.html
index 1d7dfe81..98da6d6d 100644
--- a/dev/generated/braindecode.augmentation.functional.channels_shuffle.html
+++ b/dev/generated/braindecode.augmentation.functional.channels_shuffle.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.frequency_shift.html b/dev/generated/braindecode.augmentation.functional.frequency_shift.html
index 68953cb2..0a0236e7 100644
--- a/dev/generated/braindecode.augmentation.functional.frequency_shift.html
+++ b/dev/generated/braindecode.augmentation.functional.frequency_shift.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.ft_surrogate.html b/dev/generated/braindecode.augmentation.functional.ft_surrogate.html
index 122b3f6d..fea6d873 100644
--- a/dev/generated/braindecode.augmentation.functional.ft_surrogate.html
+++ b/dev/generated/braindecode.augmentation.functional.ft_surrogate.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.gaussian_noise.html b/dev/generated/braindecode.augmentation.functional.gaussian_noise.html
index fe5387e5..e57a9689 100644
--- a/dev/generated/braindecode.augmentation.functional.gaussian_noise.html
+++ b/dev/generated/braindecode.augmentation.functional.gaussian_noise.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.identity.html b/dev/generated/braindecode.augmentation.functional.identity.html
index 644e421e..e83e6149 100644
--- a/dev/generated/braindecode.augmentation.functional.identity.html
+++ b/dev/generated/braindecode.augmentation.functional.identity.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.mask_encoding.html b/dev/generated/braindecode.augmentation.functional.mask_encoding.html
index abe782c6..3eb3adc1 100644
--- a/dev/generated/braindecode.augmentation.functional.mask_encoding.html
+++ b/dev/generated/braindecode.augmentation.functional.mask_encoding.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,38 +602,42 @@
 <h1>braindecode.augmentation.functional.mask_encoding<a class="headerlink" href="#braindecode-augmentation-functional-mask-encoding" title="Link to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="braindecode.augmentation.functional.mask_encoding">
-<span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.functional.</span></span><span class="sig-name descname"><span class="pre">mask_encoding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">segment_length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/functional.py#L1046-L1094"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.functional.mask_encoding" title="Link to this definition">#</a></dt>
-<dd><p>Replaces a contiguous part (or parts) of all channels by zeros
+<span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.functional.</span></span><span class="sig-name descname"><span class="pre">mask_encoding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">segment_length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/functional.py#L1046-L1096"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.functional.mask_encoding" title="Link to this definition">#</a></dt>
+<dd><p>Mark encoding from Ding et al. (2024) from <a class="reference internal" href="#re49696d5b28b-ding2024" id="id1">[ding2024]</a>.</p>
+<p>Replaces a contiguous part (or parts) of all channels by zeros
 (if more than one segment, it may overlap).</p>
-<blockquote>
-<div><p>Implementation based on <span id="id1">[Re49696d5b28b-1]</span></p>
-</div></blockquote>
+<p>Implementation based on <a class="reference internal" href="#re49696d5b28b-ding2024" id="id2">[ding2024]</a></p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><dl class="simple">
-<dt><strong>X</strong><span class="classifier">torch.Tensor</span></dt><dd><p>EEG input example or batch.</p>
-</dd>
-<dt><strong>y</strong><span class="classifier">torch.Tensor</span></dt><dd><p>EEG labels for the example or batch.</p>
-</dd>
-<dt><strong>time_start</strong><span class="classifier">torch.Tensor</span></dt><dd><p>Tensor of integers containing the position (in last dimension) where to
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>X</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – EEG input example or batch.</p></li>
+<li><p><strong>y</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – EEG labels for the example or batch.</p></li>
+<li><p><strong>time_start</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – Tensor of integers containing the position (in last dimension) where to
 start masking the signal. Should have “n_segments” times the size of the first
-dimension of X (i.e. “n_segments” start positions per example in the batch).</p>
-</dd>
-<dt><strong>segment_length: int</strong></dt><dd><p>Length of each segment to zero out.</p>
-</dd>
-<dt><strong>n_segments</strong><span class="classifier">int</span></dt><dd><p>Number of segments to zero out in each example.</p>
-</dd>
-</dl>
+dimension of X (i.e. “n_segments” start positions per example in the batch).</p></li>
+<li><p><strong>segment_length</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Length of each segment to zero out.</p></li>
+<li><p><strong>n_segments</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of segments to zero out in each example.</p></li>
+</ul>
 </dd>
 <dt class="field-even">Returns<span class="colon">:</span></dt>
-<dd class="field-even"><dl class="simple">
-<dt>torch.Tensor</dt><dd><p>Transformed inputs.</p>
-</dd>
-<dt>torch.Tensor</dt><dd><p>Transformed labels.</p>
-</dd>
-</dl>
+<dd class="field-even"><p><ul class="simple">
+<li><p><em>torch.Tensor</em> – Transformed inputs.</p></li>
+<li><p><em>torch.Tensor</em> – Transformed labels.</p></li>
+</ul>
+</p>
 </dd>
 </dl>
+<p class="rubric">References</p>
+<div role="list" class="citation-list">
+<div class="citation" id="re49696d5b28b-ding2024" role="doc-biblioentry">
+<span class="label"><span class="fn-bracket">[</span>ding2024<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
+<p>Ding, Wenlong, et al. A Novel Data Augmentation Approach
+Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI.
+IEEE Transactions on Neural Systems and Rehabilitation Engineering
+32 (2024): 875-886.</p>
+</div>
+</div>
 </dd></dl>
 
 <div style='clear:both'></div></section>
diff --git a/dev/generated/braindecode.augmentation.functional.mixup.html b/dev/generated/braindecode.augmentation.functional.mixup.html
index 465612a7..937ed5ba 100644
--- a/dev/generated/braindecode.augmentation.functional.mixup.html
+++ b/dev/generated/braindecode.augmentation.functional.mixup.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.segmentation_reconstruction.html b/dev/generated/braindecode.augmentation.functional.segmentation_reconstruction.html
index b851262d..697e3016 100644
--- a/dev/generated/braindecode.augmentation.functional.segmentation_reconstruction.html
+++ b/dev/generated/braindecode.augmentation.functional.segmentation_reconstruction.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.augmentation.functional.segmentation_reconstruction<a class="hea
 <dl class="py function">
 <dt class="sig sig-object py" id="braindecode.augmentation.functional.segmentation_reconstruction">
 <span class="sig-prename descclassname"><span class="pre">braindecode.augmentation.functional.</span></span><span class="sig-name descname"><span class="pre">segmentation_reconstruction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_segments</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rand_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx_shuffle</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/augmentation/functional.py#L975-L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.augmentation.functional.segmentation_reconstruction" title="Link to this definition">#</a></dt>
-<dd><p>Segment and reconstruct EEG data in the time domain preserving labels.</p>
-<p>See <a class="reference internal" href="#rc19448ba78ac-1" id="id1">[1]</a> for details.</p>
+<dd><p>Segment and reconstruct EEG data from <a class="reference internal" href="#rc19448ba78ac-1" id="id1">[1]</a>.</p>
+<p>See <a class="reference internal" href="#rc19448ba78ac-1" id="id2">[1]</a> for details.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -627,12 +626,13 @@ <h1>braindecode.augmentation.functional.segmentation_reconstruction<a class="hea
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rc19448ba78ac-1" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">1</a><span class="fn-bracket">]</span></span>
-<p>Lotte, F. (2015). Signal processing approaches to minimize or</p>
+<span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
+<p>Lotte, F. (2015). Signal processing approaches to minimize or
+suppress calibration time in oscillatory activity-based brain–computer
+interfaces. Proceedings of the IEEE, 103(6), 871-890.</p>
 </div>
 </div>
-<p>suppress calibration time in oscillatory activity-based brain–computer
-interfaces. Proceedings of the IEEE, 103(6), 871-890.</p>
 </dd></dl>
 
 <div style='clear:both'></div></section>
diff --git a/dev/generated/braindecode.augmentation.functional.sensors_rotation.html b/dev/generated/braindecode.augmentation.functional.sensors_rotation.html
index 3e64df64..f41aa898 100644
--- a/dev/generated/braindecode.augmentation.functional.sensors_rotation.html
+++ b/dev/generated/braindecode.augmentation.functional.sensors_rotation.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.sign_flip.html b/dev/generated/braindecode.augmentation.functional.sign_flip.html
index 04aa47ca..2ec61b80 100644
--- a/dev/generated/braindecode.augmentation.functional.sign_flip.html
+++ b/dev/generated/braindecode.augmentation.functional.sign_flip.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.smooth_time_mask.html b/dev/generated/braindecode.augmentation.functional.smooth_time_mask.html
index 1785697a..35008552 100644
--- a/dev/generated/braindecode.augmentation.functional.smooth_time_mask.html
+++ b/dev/generated/braindecode.augmentation.functional.smooth_time_mask.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.augmentation.functional.time_reverse.html b/dev/generated/braindecode.augmentation.functional.time_reverse.html
index 07d77410..0c935b64 100644
--- a/dev/generated/braindecode.augmentation.functional.time_reverse.html
+++ b/dev/generated/braindecode.augmentation.functional.time_reverse.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.classifier.EEGClassifier.html b/dev/generated/braindecode.classifier.EEGClassifier.html
index 5198e84a..3fbc9bb4 100644
--- a/dev/generated/braindecode.classifier.EEGClassifier.html
+++ b/dev/generated/braindecode.classifier.EEGClassifier.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.BCICompetitionIVDataset4.html b/dev/generated/braindecode.datasets.BCICompetitionIVDataset4.html
index 047580d2..9353f2a1 100644
--- a/dev/generated/braindecode.datasets.BCICompetitionIVDataset4.html
+++ b/dev/generated/braindecode.datasets.BCICompetitionIVDataset4.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,7 +602,7 @@
 <h1>braindecode.datasets.BCICompetitionIVDataset4<a class="headerlink" href="#braindecode-datasets-bcicompetitionivdataset4" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.datasets.BCICompetitionIVDataset4">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.datasets.</span></span><span class="sig-name descname"><span class="pre">BCICompetitionIVDataset4</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">subject_ids</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/bcicomp.py#L26-L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BCICompetitionIVDataset4" title="Link to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.datasets.</span></span><span class="sig-name descname"><span class="pre">BCICompetitionIVDataset4</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">subject_ids</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/bcicomp.py#L26-L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BCICompetitionIVDataset4" title="Link to this definition">#</a></dt>
 <dd><p>BCI competition IV dataset 4.</p>
 <p>Contains ECoG recordings for three patients moving fingers during the experiment.
 Targets correspond to the time courses of the flexion of each of five fingers.
@@ -622,14 +621,15 @@ <h1>braindecode.datasets.BCICompetitionIVDataset4<a class="headerlink" href="#br
 <div role="list" class="citation-list">
 <div class="citation" id="rb33c1a7bbf7d-1" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">1</a><span class="fn-bracket">]</span></span>
-<p>Miller, Kai J. “A library of human electrocorticographic data and analyses.”</p>
+<p>Miller, Kai J. “A library of human electrocorticographic data and analyses.”
+Nature human behaviour 3, no. 11 (2019): 1225-1235.
+<a class="reference external" href="https://doi.org/10.1038/s41562-019-0678-3">https://doi.org/10.1038/s41562-019-0678-3</a></p>
 </div>
 </div>
-<p>Nature human behaviour 3, no. 11 (2019): 1225-1235. <a class="reference external" href="https://doi.org/10.1038/s41562-019-0678-3">https://doi.org/10.1038/s41562-019-0678-3</a></p>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.datasets.BCICompetitionIVDataset4.download">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">download</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_update</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/bcicomp.py#L78-L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BCICompetitionIVDataset4.download" title="Link to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">download</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_update</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/bcicomp.py#L79-L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BCICompetitionIVDataset4.download" title="Link to this definition">#</a></dt>
 <dd><p>Download the dataset.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
diff --git a/dev/generated/braindecode.datasets.BNCI2014001.html b/dev/generated/braindecode.datasets.BNCI2014001.html
index 3e1206ca..f088d622 100644
--- a/dev/generated/braindecode.datasets.BNCI2014001.html
+++ b/dev/generated/braindecode.datasets.BNCI2014001.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.BaseConcatDataset.html b/dev/generated/braindecode.datasets.BaseConcatDataset.html
index acca8706..b9c716a4 100644
--- a/dev/generated/braindecode.datasets.BaseConcatDataset.html
+++ b/dev/generated/braindecode.datasets.BaseConcatDataset.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,10 +602,10 @@
 <h1>braindecode.datasets.BaseConcatDataset<a class="headerlink" href="#braindecode-datasets-baseconcatdataset" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.datasets.BaseConcatDataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.datasets.</span></span><span class="sig-name descname"><span class="pre">BaseConcatDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">list_of_ds</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="braindecode.datasets.BaseDataset.html#braindecode.datasets.BaseDataset" title="braindecode.datasets.base.BaseDataset"><span class="pre">BaseDataset</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference internal" href="#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.base.BaseConcatDataset"><span class="pre">BaseConcatDataset</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference internal" href="braindecode.datasets.WindowsDataset.html#braindecode.datasets.WindowsDataset" title="braindecode.datasets.base.WindowsDataset"><span class="pre">WindowsDataset</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_transform</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Callable" title="(in Python v3.12)"><span class="pre">Callable</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L418-L835"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset" title="Link to this definition">#</a></dt>
-<dd><p>A base class for concatenated datasets. Holds either mne.Raw or
-mne.Epoch in self.datasets and has a pandas DataFrame with additional
-description.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.datasets.</span></span><span class="sig-name descname"><span class="pre">BaseConcatDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">list_of_ds</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="braindecode.datasets.BaseDataset.html#braindecode.datasets.BaseDataset" title="braindecode.datasets.base.BaseDataset"><span class="pre">BaseDataset</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference internal" href="#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.base.BaseConcatDataset"><span class="pre">BaseConcatDataset</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference internal" href="braindecode.datasets.WindowsDataset.html#braindecode.datasets.WindowsDataset" title="braindecode.datasets.base.WindowsDataset"><span class="pre">WindowsDataset</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_transform</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Callable" title="(in Python v3.12)"><span class="pre">Callable</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L418-L839"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset" title="Link to this definition">#</a></dt>
+<dd><p>A base class for concatenated datasets.</p>
+<p>Holds either mne.Raw or mne.Epoch in self.datasets and has
+a pandas DataFrame with additional description.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -618,7 +617,7 @@ <h1>braindecode.datasets.BaseConcatDataset<a class="headerlink" href="#braindeco
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.datasets.BaseConcatDataset.get_metadata">
-<span class="sig-name descname"><span class="pre">get_metadata</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">DataFrame</span></span></span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L539-L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.get_metadata" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_metadata</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">DataFrame</span></span></span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L543-L574"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.get_metadata" title="Link to this definition">#</a></dt>
 <dd><p>Concatenate the metadata and description of the wrapped Epochs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns<span class="colon">:</span></dt>
@@ -634,7 +633,7 @@ <h1>braindecode.datasets.BaseConcatDataset<a class="headerlink" href="#braindeco
 
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.datasets.BaseConcatDataset.save">
-<span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">overwrite</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L700-L787"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.save" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">overwrite</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offset</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L704-L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.save" title="Link to this definition">#</a></dt>
 <dd><p>Save datasets to files by creating one subdirectory for each dataset:
 path/</p>
 <blockquote>
@@ -676,7 +675,7 @@ <h1>braindecode.datasets.BaseConcatDataset<a class="headerlink" href="#braindeco
 
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.datasets.BaseConcatDataset.set_description">
-<span class="sig-name descname"><span class="pre">set_description</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">description</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">DataFrame</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overwrite</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L681-L698"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.set_description" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_description</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">description</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><span class="pre">DataFrame</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overwrite</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L685-L702"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.set_description" title="Link to this definition">#</a></dt>
 <dd><p>Update (add or overwrite) the dataset description.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -692,9 +691,9 @@ <h1>braindecode.datasets.BaseConcatDataset<a class="headerlink" href="#braindeco
 
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.datasets.BaseConcatDataset.split">
-<span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">by</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">property</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_ids</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset"><span class="pre">BaseConcatDataset</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L474-L537"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.split" title="Link to this definition">#</a></dt>
-<dd><p>Split the dataset based on information listed in its description
-DataFrame or based on indices.</p>
+<span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">by</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">property</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_ids</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.12)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset"><span class="pre">BaseConcatDataset</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/base.py#L476-L541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.BaseConcatDataset.split" title="Link to this definition">#</a></dt>
+<dd><p>Split the dataset based on information listed in its description.</p>
+<p>The format could be based on a DataFrame or based on indices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -705,7 +704,7 @@ <h1>braindecode.datasets.BaseConcatDataset<a class="headerlink" href="#braindeco
 datapoints of that split.
 If a dict then each key will be used in the returned
 splits dict and each value should be a list of int.</p></li>
-<li><p><strong>property</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><em>str</em></a>) – Some property which is listed in info DataFrame.</p></li>
+<li><p><strong>property</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><em>str</em></a>) – Some property which is listed in the info DataFrame.</p></li>
 <li><p><strong>split_ids</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em> | </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><em>dict</em></a>) – List of indices to be combined in a subset.
 It can be a list of int or a list of list of int.</p></li>
 </ul>
diff --git a/dev/generated/braindecode.datasets.BaseDataset.html b/dev/generated/braindecode.datasets.BaseDataset.html
index 6b868990..b9618925 100644
--- a/dev/generated/braindecode.datasets.BaseDataset.html
+++ b/dev/generated/braindecode.datasets.BaseDataset.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.HGD.html b/dev/generated/braindecode.datasets.HGD.html
index 1f74e7b0..b8638c13 100644
--- a/dev/generated/braindecode.datasets.HGD.html
+++ b/dev/generated/braindecode.datasets.HGD.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.MOABBDataset.html b/dev/generated/braindecode.datasets.MOABBDataset.html
index 022c7f08..ce169ff6 100644
--- a/dev/generated/braindecode.datasets.MOABBDataset.html
+++ b/dev/generated/braindecode.datasets.MOABBDataset.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.NMT.html b/dev/generated/braindecode.datasets.NMT.html
index d5064c1f..25f5d80c 100644
--- a/dev/generated/braindecode.datasets.NMT.html
+++ b/dev/generated/braindecode.datasets.NMT.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,7 +602,7 @@
 <h1>braindecode.datasets.NMT<a class="headerlink" href="#braindecode-datasets-nmt" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.datasets.NMT">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.datasets.</span></span><span class="sig-name descname"><span class="pre">NMT</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'pathological'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recording_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/nmt.py#L46-L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.NMT" title="Link to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.datasets.</span></span><span class="sig-name descname"><span class="pre">NMT</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'pathological'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recording_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_jobs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/datasets/nmt.py#L46-L173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.datasets.NMT" title="Link to this definition">#</a></dt>
 <dd><p>The NMT Scalp EEG Dataset.</p>
 <p>An Open-Source Annotated Dataset of Healthy and Pathological EEG
 Recordings for Predictive Modeling.</p>
@@ -633,12 +632,13 @@ <h1>braindecode.datasets.NMT<a class="headerlink" href="#braindecode-datasets-nm
 <div role="list" class="citation-list">
 <div class="citation" id="r610f33db09cb-khan2022" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Khan2022</a><span class="fn-bracket">]</span></span>
-<p>Khan, H.A.,Ul Ain, R., Kamboh, A.M., Butt, H.T.,Shafait,S.,</p>
+<p>Khan, H.A.,Ul Ain, R., Kamboh, A.M., Butt, H.T.,Shafait,S.,
+Alamgir, W., Stricker, D. and Shafait, F., 2022. The NMT scalp EEG
+dataset: an open-source annotated dataset of healthy and pathological
+EEG recordings for predictive modeling. Frontiers in neuroscience,
+15, p.755817.</p>
 </div>
 </div>
-<p>Alamgir, W., Stricker, D. and Shafait, F., 2022. The NMT scalp EEG dataset:
-an open-source annotated dataset of healthy and pathological EEG recordings
-for predictive modeling. Frontiers in neuroscience, 15, p.755817.</p>
 </dd></dl>
 
 <div style='clear:both'></div></section>
diff --git a/dev/generated/braindecode.datasets.SleepPhysionet.html b/dev/generated/braindecode.datasets.SleepPhysionet.html
index 9b0be483..8eee1f3e 100644
--- a/dev/generated/braindecode.datasets.SleepPhysionet.html
+++ b/dev/generated/braindecode.datasets.SleepPhysionet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.TUH.html b/dev/generated/braindecode.datasets.TUH.html
index 2974c451..12919251 100644
--- a/dev/generated/braindecode.datasets.TUH.html
+++ b/dev/generated/braindecode.datasets.TUH.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.TUHAbnormal.html b/dev/generated/braindecode.datasets.TUHAbnormal.html
index d1f4e5ee..06e84b6a 100644
--- a/dev/generated/braindecode.datasets.TUHAbnormal.html
+++ b/dev/generated/braindecode.datasets.TUHAbnormal.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.WindowsDataset.html b/dev/generated/braindecode.datasets.WindowsDataset.html
index aa22ee1a..75bb642d 100644
--- a/dev/generated/braindecode.datasets.WindowsDataset.html
+++ b/dev/generated/braindecode.datasets.WindowsDataset.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.create_from_X_y.html b/dev/generated/braindecode.datasets.create_from_X_y.html
index ef399b85..2fbe19f9 100644
--- a/dev/generated/braindecode.datasets.create_from_X_y.html
+++ b/dev/generated/braindecode.datasets.create_from_X_y.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.create_from_mne_epochs.html b/dev/generated/braindecode.datasets.create_from_mne_epochs.html
index 584a52f5..dc28ff1e 100644
--- a/dev/generated/braindecode.datasets.create_from_mne_epochs.html
+++ b/dev/generated/braindecode.datasets.create_from_mne_epochs.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datasets.create_from_mne_raw.html b/dev/generated/braindecode.datasets.create_from_mne_raw.html
index d43e5f07..c8b2774d 100644
--- a/dev/generated/braindecode.datasets.create_from_mne_raw.html
+++ b/dev/generated/braindecode.datasets.create_from_mne_raw.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datautil.load_concat_dataset.html b/dev/generated/braindecode.datautil.load_concat_dataset.html
index bcdba03b..e977243c 100644
--- a/dev/generated/braindecode.datautil.load_concat_dataset.html
+++ b/dev/generated/braindecode.datautil.load_concat_dataset.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.datautil.save_concat_dataset.html b/dev/generated/braindecode.datautil.save_concat_dataset.html
index b9422504..8de07810 100644
--- a/dev/generated/braindecode.datautil.save_concat_dataset.html
+++ b/dev/generated/braindecode.datautil.save_concat_dataset.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.models.ATCNet.html b/dev/generated/braindecode.models.ATCNet.html
index a7600788..04908d99 100644
--- a/dev/generated/braindecode.models.ATCNet.html
+++ b/dev/generated/braindecode.models.ATCNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,8 +602,8 @@
 <h1>braindecode.models.ATCNet<a class="headerlink" href="#braindecode-models-atcnet" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.ATCNet">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">ATCNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=250</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_n_filters=16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_kernel_length_1=64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_kernel_length_2=16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_pool_size_1=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_pool_size_2=7</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_depth_mult=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_dropout=0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_head_dim=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_num_heads=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_dropout=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_depth=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_kernel_size=4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_n_filters=32</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_dropout=0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concat=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm_const=0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/atcnet.py#L14-L303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.ATCNet" title="Link to this definition">#</a></dt>
-<dd><p>ATCNet model from <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id1">[1]</a></p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">ATCNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=250</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_n_filters=16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_kernel_length_1=64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_kernel_length_2=16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_pool_size_1=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_pool_size_2=7</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_depth_mult=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_block_dropout=0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_head_dim=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_num_heads=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_dropout=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_depth=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_kernel_size=4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_n_filters=32</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_dropout=0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tcn_activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concat=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm_const=0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/atcnet.py#L14-L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.ATCNet" title="Link to this definition">#</a></dt>
+<dd><p>ATCNet model from Altaheri et al. (2022) <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id1">[1]</a></p>
 <p>Pytorch implementation based on official tensorflow code <a class="reference internal" href="#r2ecdb73d6ab9-2" id="id2">[2]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -636,24 +635,24 @@ <h1>braindecode.models.ATCNet<a class="headerlink" href="#braindecode-models-atc
 <li><p><strong>att_head_dim</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Embedding dimension used in each self-attention head, denoted dh in
 table 1 of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id17">[1]</a>. Defaults to 8 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id18">[1]</a>.</p></li>
 <li><p><strong>att_num_heads</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of attention heads, denoted H in table 1 of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id19">[1]</a>.
-Defaults to 2 as in [<a href="#id32"><span class="problematic" id="id33">1_</span></a>.</p></li>
+Defaults to 2 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id20">[1]</a>.</p></li>
 <li><p><strong>att_dropout</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Dropout probability used in the attention block, denoted pa in table 1
-of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id20">[1]</a>. Defaults to 0.5 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id21">[1]</a>.</p></li>
+of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id21">[1]</a>. Defaults to 0.5 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id22">[1]</a>.</p></li>
 <li><p><strong>tcn_depth</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Depth of Temporal Convolutional Network block (i.e. number of TCN
-Residual blocks), denoted L in table 1 of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id22">[1]</a>. Defaults to 2
-as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id23">[1]</a>.</p></li>
+Residual blocks), denoted L in table 1 of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id23">[1]</a>. Defaults to 2
+as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id24">[1]</a>.</p></li>
 <li><p><strong>tcn_kernel_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Temporal kernel size used in TCN block, denoted Kt in table 1 of the
-paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id24">[1]</a>. Defaults to 4 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id25">[1]</a>.</p></li>
+paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id25">[1]</a>. Defaults to 4 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id26">[1]</a>.</p></li>
 <li><p><strong>tcn_n_filters</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of filters used in TCN convolutional layers (Ft). Defaults to
-32 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id26">[1]</a>.</p></li>
+32 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id27">[1]</a>.</p></li>
 <li><p><strong>tcn_dropout</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Dropout probability used in the TCN block, denoted pt in table 1
-of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id27">[1]</a>. Defaults to 0.3 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id28">[1]</a>.</p></li>
+of the paper <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id28">[1]</a>. Defaults to 0.3 as in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id29">[1]</a>.</p></li>
 <li><p><strong>tcn_activation</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module" title="(in PyTorch v2.4)"><em>torch.nn.Module</em></a>) – Nonlinear activation to use. Defaults to nn.ELU().</p></li>
 <li><p><strong>concat</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a>) – When <code class="docutils literal notranslate"><span class="pre">True</span></code>, concatenates each slidding window embedding before
-feeding it to a fully-connected layer, as done in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id29">[1]</a>. When <code class="docutils literal notranslate"><span class="pre">False</span></code>,
+feeding it to a fully-connected layer, as done in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id30">[1]</a>. When <code class="docutils literal notranslate"><span class="pre">False</span></code>,
 maps each slidding window to <cite>n_outputs</cite> logits and average them.
-Defaults to <code class="docutils literal notranslate"><span class="pre">False</span></code> contrary to what is reported in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id30">[1]</a>, but
-matching what the official code does <a class="reference internal" href="#r2ecdb73d6ab9-2" id="id31">[2]</a>.</p></li>
+Defaults to <code class="docutils literal notranslate"><span class="pre">False</span></code> contrary to what is reported in <a class="reference internal" href="#r2ecdb73d6ab9-1" id="id31">[1]</a>, but
+matching what the official code does <a class="reference internal" href="#r2ecdb73d6ab9-2" id="id32">[2]</a>.</p></li>
 <li><p><strong>max_norm_const</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Maximum L2-norm constraint imposed on weights of the last
 fully-connected layer. Defaults to 0.25.</p></li>
 <li><p><strong>chs_info</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em> of </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><em>dict</em></a>) – Information about each individual EEG channel. This should be filled with
@@ -683,22 +682,23 @@ <h1>braindecode.models.ATCNet<a class="headerlink" href="#braindecode-models-atc
 <div role="list" class="citation-list">
 <div class="citation" id="r2ecdb73d6ab9-1" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id3">2</a>,<a role="doc-backlink" href="#id4">3</a>,<a role="doc-backlink" href="#id5">4</a>,<a role="doc-backlink" href="#id6">5</a>,<a role="doc-backlink" href="#id7">6</a>,<a role="doc-backlink" href="#id8">7</a>,<a role="doc-backlink" href="#id9">8</a>,<a role="doc-backlink" href="#id10">9</a>,<a role="doc-backlink" href="#id11">10</a>,<a role="doc-backlink" href="#id12">11</a>,<a role="doc-backlink" href="#id13">12</a>,<a role="doc-backlink" href="#id14">13</a>,<a role="doc-backlink" href="#id15">14</a>,<a role="doc-backlink" href="#id16">15</a>,<a role="doc-backlink" href="#id17">16</a>,<a role="doc-backlink" href="#id18">17</a>,<a role="doc-backlink" href="#id19">18</a>,<a role="doc-backlink" href="#id20">19</a>,<a role="doc-backlink" href="#id21">20</a>,<a role="doc-backlink" href="#id22">21</a>,<a role="doc-backlink" href="#id23">22</a>,<a role="doc-backlink" href="#id24">23</a>,<a role="doc-backlink" href="#id25">24</a>,<a role="doc-backlink" href="#id26">25</a>,<a role="doc-backlink" href="#id27">26</a>,<a role="doc-backlink" href="#id28">27</a>,<a role="doc-backlink" href="#id29">28</a>,<a role="doc-backlink" href="#id30">29</a>)</span>
-<p>H. Altaheri, G. Muhammad and M. Alsulaiman, “Physics-informed
-attention temporal convolutional network for EEG-based motor imagery
-classification,” in IEEE Transactions on Industrial Informatics,
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id3">2</a>,<a role="doc-backlink" href="#id4">3</a>,<a role="doc-backlink" href="#id5">4</a>,<a role="doc-backlink" href="#id6">5</a>,<a role="doc-backlink" href="#id7">6</a>,<a role="doc-backlink" href="#id8">7</a>,<a role="doc-backlink" href="#id9">8</a>,<a role="doc-backlink" href="#id10">9</a>,<a role="doc-backlink" href="#id11">10</a>,<a role="doc-backlink" href="#id12">11</a>,<a role="doc-backlink" href="#id13">12</a>,<a role="doc-backlink" href="#id14">13</a>,<a role="doc-backlink" href="#id15">14</a>,<a role="doc-backlink" href="#id16">15</a>,<a role="doc-backlink" href="#id17">16</a>,<a role="doc-backlink" href="#id18">17</a>,<a role="doc-backlink" href="#id19">18</a>,<a role="doc-backlink" href="#id20">19</a>,<a role="doc-backlink" href="#id21">20</a>,<a role="doc-backlink" href="#id22">21</a>,<a role="doc-backlink" href="#id23">22</a>,<a role="doc-backlink" href="#id24">23</a>,<a role="doc-backlink" href="#id25">24</a>,<a role="doc-backlink" href="#id26">25</a>,<a role="doc-backlink" href="#id27">26</a>,<a role="doc-backlink" href="#id28">27</a>,<a role="doc-backlink" href="#id29">28</a>,<a role="doc-backlink" href="#id30">29</a>,<a role="doc-backlink" href="#id31">30</a>)</span>
+<p>H. Altaheri, G. Muhammad and M. Alsulaiman,
+Physics-informed attention temporal convolutional network for EEG-based
+motor imagery classification in IEEE Transactions on Industrial Informatics,
 2022, doi: 10.1109/TII.2022.3197419.</p>
 </div>
 <div class="citation" id="r2ecdb73d6ab9-2" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>2<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id2">1</a>,<a role="doc-backlink" href="#id31">2</a>)</span>
-<p><a class="github reference external" href="https://github.com/Altaheri/EEG-ATCNet/blob/main/models.py">Altaheri/EEG-ATCNet</a></p>
+<span class="backrefs">(<a role="doc-backlink" href="#id2">1</a>,<a role="doc-backlink" href="#id32">2</a>)</span>
+<p>EEE-ATCNet implementation.
+<a class="github reference external" href="https://github.com/Altaheri/EEG-ATCNet/blob/main/models.py">Altaheri/EEG-ATCNet</a></p>
 </div>
 </div>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.models.ATCNet.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/atcnet.py#L257-L303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.ATCNet.forward" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/atcnet.py#L258-L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.ATCNet.forward" title="Link to this definition">#</a></dt>
 <dd><p>Define the computation performed at every call.</p>
 <p>Should be overridden by all subclasses.</p>
 <div class="admonition note">
diff --git a/dev/generated/braindecode.models.AttentionBaseNet.html b/dev/generated/braindecode.models.AttentionBaseNet.html
index fdb8d37f..47be7226 100644
--- a/dev/generated/braindecode.models.AttentionBaseNet.html
+++ b/dev/generated/braindecode.models.AttentionBaseNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,12 +603,12 @@ <h1>braindecode.models.AttentionBaseNet<a class="headerlink" href="#braindecode-
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.AttentionBaseNet">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">AttentionBaseNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_temporal_filters:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">40</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">temp_filter_length_inp:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">spatial_expansion:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_length_inp:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_stride_inp:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout_inp:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ch_dim:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">temp_filter_length:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_length:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_stride:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attention_mode:</span> <span class="pre">str</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction_rate:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_mlp:</span> <span class="pre">bool</span> <span class="pre">=</span> <span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freq_idx:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_codewords:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_params:</span> <span class="pre">bool</span> <span class="pre">=</span> <span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/attentionbasenet.py#L247-L450"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.AttentionBaseNet" title="Link to this definition">#</a></dt>
-<dd><p>AttentionBaseNet.</p>
+<dd><p>AttentionBaseNet from Wimpff M et al. (2023) <a class="reference internal" href="#r523d6c831d64-martin2023" id="id1">[Martin2023]</a>.</p>
 <p>Neural Network from the paper: EEG motor imagery decoding:
 A framework for comparative analysis with channel attention
 mechanisms</p>
 <p>The paper and original code with more details about the methodological
-choices are available at the <a class="reference internal" href="#r523d6c831d64-martin2023" id="id1">[Martin2023]</a> and <a class="reference internal" href="#r523d6c831d64-martincode" id="id2">[MartinCode]</a>.</p>
+choices are available at the <a class="reference internal" href="#r523d6c831d64-martin2023" id="id2">[Martin2023]</a> and <a class="reference internal" href="#r523d6c831d64-martincode" id="id3">[MartinCode]</a>.</p>
 <p>The AttentionBaseNet architecture is composed of four modules:
 - Input Block that performs a temporal convolution and a spatial
 convolution.
@@ -692,13 +691,14 @@ <h1>braindecode.models.AttentionBaseNet<a class="headerlink" href="#braindecode-
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r523d6c831d64-martin2023" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Martin2023</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Martin2023<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Wimpff, M., Gizzi, L., Zerfowski, J. and Yang, B., 2023.
 EEG motor imagery decoding: A framework for comparative analysis with
 channel attention mechanisms. arXiv preprint arXiv:2310.11198.</p>
 </div>
 <div class="citation" id="r523d6c831d64-martincode" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id2">MartinCode</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id3">MartinCode</a><span class="fn-bracket">]</span></span>
 <p>Wimpff, M., Gizzi, L., Zerfowski, J. and Yang, B.
 GitHub <a class="github reference external" href="https://github.com/martinwimpff/channel-attention">martinwimpff/channel-attention</a> (accessed 2024-03-28)</p>
 </div>
diff --git a/dev/generated/braindecode.models.BIOT.html b/dev/generated/braindecode.models.BIOT.html
index bfa3abe4..96827705 100644
--- a/dev/generated/braindecode.models.BIOT.html
+++ b/dev/generated/braindecode.models.BIOT.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,8 +602,9 @@
 <h1>braindecode.models.BIOT<a class="headerlink" href="#braindecode-models-biot" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.BIOT">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">BIOT</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">emb_size=256</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_num_heads=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_layers=4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length=100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feature=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/biot.py#L326-L472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.BIOT" title="Link to this definition">#</a></dt>
-<dd><p>BIOT: Cross-data Biosignal Learning in the Wild from <a class="reference internal" href="#r606e26b38fe6-yang2023" id="id1">[Yang2023]</a></p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">BIOT</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">emb_size=256</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_num_heads=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_layers=4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length=100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feature=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/biot.py#L326-L474"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.BIOT" title="Link to this definition">#</a></dt>
+<dd><p>BIOT from Yang et al. (2023) <a class="reference internal" href="#r606e26b38fe6-yang2023" id="id1">[Yang2023]</a></p>
+<p>BIOT: Cross-data Biosignal Learning in the Wild.</p>
 <p>BIOT is a large language model for biosignal classification. It is
 a wrapper around the <cite>BIOTEncoder</cite> and <cite>ClassificationHead</cite> modules.</p>
 <p>It is designed for N-dimensional biosignal data such as EEG, ECG, etc.
@@ -677,7 +677,7 @@ <h1>braindecode.models.BIOT<a class="headerlink" href="#braindecode-models-biot"
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.models.BIOT.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/biot.py#L449-L472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.BIOT.forward" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/biot.py#L451-L474"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.BIOT.forward" title="Link to this definition">#</a></dt>
 <dd><p>Pass the input through the BIOT encoder, and then through the
 classification head.</p>
 <dl class="field-list simple">
diff --git a/dev/generated/braindecode.models.ContraWR.html b/dev/generated/braindecode.models.ContraWR.html
index c385855e..715c3db2 100644
--- a/dev/generated/braindecode.models.ContraWR.html
+++ b/dev/generated/braindecode.models.ContraWR.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,7 +603,7 @@ <h1>braindecode.models.ContraWR<a class="headerlink" href="#braindecode-models-c
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.ContraWR">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">ContraWR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="pre">n_chans:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">n_outputs:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">sfreq:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">emb_size:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">256,</span> <span class="pre">res_channels:</span> <span class="pre">list[int]</span> <span class="pre">=</span> <span class="pre">[32,</span> <span class="pre">64,</span> <span class="pre">128],</span> <span class="pre">steps=20,</span> <span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;,</span> <span class="pre">chs_info:</span> <span class="pre">list[dict[~typing.Any,</span> <span class="pre">~typing.Any]]</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">n_times:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">input_window_seconds:</span> <span class="pre">float</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/contrawr.py#L120-L258"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.ContraWR" title="Link to this definition">#</a></dt>
-<dd><p>Contrast with the World Representation (ContraWR) model <a class="reference internal" href="#ra71465cb6797-yang2021" id="id1">[Yang2021]</a>.</p>
+<dd><p>Contrast with the World Representation ContraWR from Yang et al. 2021 <a class="reference internal" href="#ra71465cb6797-yang2021" id="id1">[Yang2021]</a>.</p>
 <p>This model is a convolutional neural network that uses a spectral
 representation with a series of convolutional layers and residual blocks.
 The model is designed to learn a representation of the EEG signal that can
@@ -639,7 +638,7 @@ <h1>braindecode.models.ContraWR<a class="headerlink" href="#braindecode-models-c
 <p class="rubric">Notes</p>
 <p>This implementation is not guaranteed to be correct, has not been checked
 by original authors. The modifications are minimal and the model is expected
-to work as intended.</p>
+to work as intended. the original code from <a class="reference internal" href="#ra71465cb6797-code2023" id="id2">[Code2023]</a>.</p>
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="ra71465cb6797-yang2021" role="doc-biblioentry">
@@ -649,7 +648,7 @@ <h1>braindecode.models.ContraWR<a class="headerlink" href="#braindecode-models-c
 sleep staging: model development and evaluation study. JMIR AI, 2(1), e46769.</p>
 </div>
 <div class="citation" id="ra71465cb6797-code2023" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span>Code2023<span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id2">Code2023</a><span class="fn-bracket">]</span></span>
 <p>Yang, C., Westover, M.B. and Sun, J., 2023. BIOT
 Biosignal Transformer for Cross-data Learning in the Wild.
 GitHub <a class="github reference external" href="https://github.com/ycq091044/BIOT">ycq091044/BIOT</a> (accessed 2024-02-13)</p>
diff --git a/dev/generated/braindecode.models.Deep4Net.html b/dev/generated/braindecode.models.Deep4Net.html
index 4c41485e..f93f455e 100644
--- a/dev/generated/braindecode.models.Deep4Net.html
+++ b/dev/generated/braindecode.models.Deep4Net.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.Deep4Net<a class="headerlink" href="#braindecode-models-d
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.Deep4Net">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">Deep4Net</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_conv_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_time=25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_spat=25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_time_length=10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_time_length=3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_time_stride=3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_2=50</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_length_2=10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_3=100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_length_3=10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_4=200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_length_4=10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_first_conv_nonlin:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">first_pool_mode='max'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">first_pool_nonlin=&lt;function</span> <span class="pre">identity&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_later_conv_nonlin:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">later_pool_mode='max'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">later_pool_nonlin=&lt;function</span> <span class="pre">identity&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_first_layer=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_alpha=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride_before_pool=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/deep4.py#L15-L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.Deep4Net" title="Link to this definition">#</a></dt>
-<dd><p>Deep ConvNet model from Schirrmeister et al 2017.</p>
-<p>Model described in <a class="reference internal" href="#rb8ef6c2733ce-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<dd><p>Deep ConvNet model from Schirrmeister et al 2017 <a class="reference internal" href="#rb8ef6c2733ce-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<p>Model described in <a class="reference internal" href="#rb8ef6c2733ce-schirrmeister2017" id="id2">[Schirrmeister2017]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -665,7 +664,8 @@ <h1>braindecode.models.Deep4Net<a class="headerlink" href="#braindecode-models-d
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rb8ef6c2733ce-schirrmeister2017" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Schirrmeister2017</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Schirrmeister2017<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Schirrmeister, R. T., Springenberg, J. T., Fiederer,
 L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F.
 &amp; Ball, T. (2017).
diff --git a/dev/generated/braindecode.models.DeepSleepNet.html b/dev/generated/braindecode.models.DeepSleepNet.html
index d18f0992..53f4f5ec 100644
--- a/dev/generated/braindecode.models.DeepSleepNet.html
+++ b/dev/generated/braindecode.models.DeepSleepNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,9 +603,9 @@ <h1>braindecode.models.DeepSleepNet<a class="headerlink" href="#braindecode-mode
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.DeepSleepNet">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">DeepSleepNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_outputs=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feats=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_large:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_small:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/deepsleepnet.py#L187-L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.DeepSleepNet" title="Link to this definition">#</a></dt>
-<dd><p>Sleep staging architecture from Supratak et al 2017.</p>
+<dd><p>Sleep staging architecture from Supratak et al. 2017 <a class="reference internal" href="#r28b528aca953-supratak2017" id="id1">[Supratak2017]</a>.</p>
 <p>Convolutional neural network and bidirectional-Long Short-Term
-for single channels sleep staging described in <a class="reference internal" href="#r28b528aca953-supratak2017" id="id1">[Supratak2017]</a>.</p>
+for single channels sleep staging described in <a class="reference internal" href="#r28b528aca953-supratak2017" id="id2">[Supratak2017]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -641,7 +640,8 @@ <h1>braindecode.models.DeepSleepNet<a class="headerlink" href="#braindecode-mode
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r28b528aca953-supratak2017" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Supratak2017</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Supratak2017<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Supratak, A., Dong, H., Wu, C., &amp; Guo, Y. (2017).
 DeepSleepNet: A model for automatic sleep stage scoring based
 on raw single-channel EEG. IEEE Transactions on Neural Systems
diff --git a/dev/generated/braindecode.models.EEGConformer.html b/dev/generated/braindecode.models.EEGConformer.html
index 364ffc5f..14027b4e 100644
--- a/dev/generated/braindecode.models.EEGConformer.html
+++ b/dev/generated/braindecode.models.EEGConformer.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,10 +603,10 @@ <h1>braindecode.models.EEGConformer<a class="headerlink" href="#braindecode-mode
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGConformer">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGConformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_time=40</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_time_length=25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_time_length=75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_time_stride=15</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_depth=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_heads=10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_fc_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_features=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_transfor:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.GELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegconformer.py#L14-L193"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGConformer" title="Link to this definition">#</a></dt>
-<dd><p>EEG Conformer.</p>
+<dd><p>EEG Conformer from Song et al. (2022) from <a class="reference internal" href="#rd6c0fefc356a-song2022" id="id1">[song2022]</a>.</p>
 <p>Convolutional Transformer for EEG decoding.</p>
 <p>The paper and original code with more details about the methodological
-choices are available at the <a class="reference internal" href="#rd6c0fefc356a-song2022" id="id1">[Song2022]</a> and <a class="reference internal" href="#rd6c0fefc356a-conformercode" id="id2">[ConformerCode]</a>.</p>
+choices are available at the <a class="reference internal" href="#rd6c0fefc356a-song2022" id="id2">[song2022]</a> and <a class="reference internal" href="#rd6c0fefc356a-conformercode" id="id3">[ConformerCode]</a>.</p>
 <p>This neural network architecture receives a traditional braindecode input.
 The input shape should be three-dimensional matrix representing the EEG
 signals.</p>
@@ -679,14 +678,15 @@ <h1>braindecode.models.EEGConformer<a class="headerlink" href="#braindecode-mode
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rd6c0fefc356a-song2022" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Song2022</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>song2022<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Song, Y., Zheng, Q., Liu, B. and Gao, X., 2022. EEG
 conformer: Convolutional transformer for EEG decoding and visualization.
 IEEE Transactions on Neural Systems and Rehabilitation Engineering,
 31, pp.710-719. <a class="reference external" href="https://ieeexplore.ieee.org/document/9991178">https://ieeexplore.ieee.org/document/9991178</a></p>
 </div>
 <div class="citation" id="rd6c0fefc356a-conformercode" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id2">ConformerCode</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id3">ConformerCode</a><span class="fn-bracket">]</span></span>
 <p>Song, Y., Zheng, Q., Liu, B. and Gao, X., 2022. EEG
 conformer: Convolutional transformer for EEG decoding and visualization.
 <a class="github reference external" href="https://github.com/eeyhsong/EEG-Conformer">eeyhsong/EEG-Conformer</a>.</p>
diff --git a/dev/generated/braindecode.models.EEGITNet.html b/dev/generated/braindecode.models.EEGITNet.html
index 7e5b3e82..0e3d17e4 100644
--- a/dev/generated/braindecode.models.EEGITNet.html
+++ b/dev/generated/braindecode.models.EEGITNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,13 +602,12 @@
 <h1>braindecode.models.EEGITNet<a class="headerlink" href="#braindecode-models-eegitnet" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGITNet">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGITNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegitnet.py#L164-L375"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGITNet" title="Link to this definition">#</a></dt>
-<dd><dl class="simple">
-<dt>EEG-ITNet: An Explainable Inception Temporal</dt><dd><p>Convolutional Network for motor imagery classification from
-Salami et. al 2022.</p>
-</dd>
-</dl>
-<p>See <a class="reference internal" href="#r7fe571f46200-salami2022" id="id1">[Salami2022]</a> for details.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGITNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegitnet.py#L164-L378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGITNet" title="Link to this definition">#</a></dt>
+<dd><p>EEG-ITNet from Salami, et al. <a class="reference internal" href="#r7fe571f46200-salami2022" id="id1">[Salami2022]</a></p>
+<p>EEG-ITNet: An Explainable Inception Temporal
+Convolutional Network for motor imagery classification from
+Salami et al. 2022.</p>
+<p>See <a class="reference internal" href="#r7fe571f46200-salami2022" id="id2">[Salami2022]</a> for details.</p>
 <p>Code adapted from <a class="github reference external" href="https://github.com/abbassalami/eeg-itnet">abbassalami/eeg-itnet</a></p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -648,14 +646,14 @@ <h1>braindecode.models.EEGITNet<a class="headerlink" href="#braindecode-models-e
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r7fe571f46200-salami2022" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Salami2022</a><span class="fn-bracket">]</span></span>
-<ol class="upperalpha simple">
-<li><p>Salami, J. Andreu-Perez and H. Gillmeister, “EEG-ITNet: An Explainable</p></li>
-</ol>
+<span class="label"><span class="fn-bracket">[</span>Salami2022<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
+<p>A. Salami, J. Andreu-Perez and H. Gillmeister, “EEG-ITNet:
+An Explainable Inception Temporal Convolutional Network for motor
+imagery classification,” in IEEE Access,
+doi: 10.1109/ACCESS.2022.3161489.</p>
 </div>
 </div>
-<p>Inception Temporal Convolutional Network for motor imagery classification,” in IEEE Access,
-doi: 10.1109/ACCESS.2022.3161489.</p>
 </dd></dl>
 
 <div style='clear:both'></div></section>
diff --git a/dev/generated/braindecode.models.EEGInceptionERP.html b/dev/generated/braindecode.models.EEGInceptionERP.html
index 5a6fcdc2..151771d8 100644
--- a/dev/generated/braindecode.models.EEGInceptionERP.html
+++ b/dev/generated/braindecode.models.EEGInceptionERP.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,10 +602,10 @@
 <h1>braindecode.models.EEGInceptionERP<a class="headerlink" href="#braindecode-models-eeginceptionerp" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGInceptionERP">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGInceptionERP</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=1000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scales_samples_s=(0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">0.125)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_alpha=0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth_multiplier=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pooling_sizes=(4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eeginception_erp.py#L16-L324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGInceptionERP" title="Link to this definition">#</a></dt>
-<dd><p>EEG Inception for ERP-based classification</p>
-<p>The code for the paper and this model is also available at <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id1">[Santamaria2020]</a>
-and an adaptation for PyTorch <a class="reference internal" href="#r37c4761d4e92-2" id="id2">[2]</a>.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGInceptionERP</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=1000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scales_samples_s=(0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">0.125)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_alpha=0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth_multiplier=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pooling_sizes=(4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eeginception_erp.py#L16-L325"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGInceptionERP" title="Link to this definition">#</a></dt>
+<dd><p>EEG Inception for ERP-based from Santamaria-Vazquez <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id1">[santamaria2020]</a>.</p>
+<p>The code for the paper and this model is also available at <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id2">[santamaria2020]</a>
+and an adaptation for PyTorch <a class="reference internal" href="#r37c4761d4e92-2" id="id3">[2]</a>.</p>
 <p>The model is strongly based on the original InceptionNet for an image. The main goal is
 to extract features in parallel with different scales. The authors extracted three scales
 proportional to the window sample size. The network had three parts:
@@ -614,8 +613,9 @@ <h1>braindecode.models.EEGInceptionERP<a class="headerlink" href="#braindecode-m
 for classification.</p>
 <p>One advantage of the EEG-Inception block is that it allows a network
 to learn simultaneous components of low and high frequency associated with the signal.
-The winners of BEETL Competition/NeurIps 2021 used parts of the model <span id="id3">[R37c4761d4e92-beetl]</span>.</p>
-<p>The model is fully described in <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id4">[Santamaria2020]</a>.</p>
+The winners of BEETL Competition/NeurIps 2021 used parts of the
+model <a class="reference internal" href="#r37c4761d4e92-beetl" id="id4">[beetl]</a>.</p>
+<p>The model is fully described in <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id5">[santamaria2020]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -623,23 +623,23 @@ <h1>braindecode.models.EEGInceptionERP<a class="headerlink" href="#braindecode-m
 <li><p><strong>n_outputs</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of outputs of the model. This is the number of classes
 in the case of classification.</p></li>
 <li><p><strong>n_times</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – Size of the input, in number of samples. Set to 128 (1s) as in
-<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id5">[Santamaria2020]</a>.</p></li>
-<li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>, </em><em>optional</em>) – EEG sampling frequency. Defaults to 128 as in <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id6">[Santamaria2020]</a>.</p></li>
+<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id6">[santamaria2020]</a>.</p></li>
+<li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>, </em><em>optional</em>) – EEG sampling frequency. Defaults to 128 as in <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id7">[santamaria2020]</a>.</p></li>
 <li><p><strong>drop_prob</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>, </em><em>optional</em>) – Dropout rate inside all the network. Defaults to 0.5 as in
-<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id7">[Santamaria2020]</a>.</p></li>
+<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id8">[santamaria2020]</a>.</p></li>
 <li><p><strong>scales_samples_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em>(</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>)</em><em>, </em><em>optional</em>) – Windows for inception block. Temporal scale (s) of the convolutions on
 each Inception module. This parameter determines the kernel sizes of
 the filters. Defaults to 0.5, 0.25, 0.125 seconds, as in
-<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id8">[Santamaria2020]</a>.</p></li>
+<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id9">[santamaria2020]</a>.</p></li>
 <li><p><strong>n_filters</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – Initial number of convolutional filters. Defaults to 8 as in
-<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id9">[Santamaria2020]</a>.</p></li>
+<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id10">[santamaria2020]</a>.</p></li>
 <li><p><strong>activation</strong> (<em>nn.Module</em><em>, </em><em>optional</em>) – Activation function. Defaults to ELU activation as in
-<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id10">[Santamaria2020]</a>.</p></li>
+<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id11">[santamaria2020]</a>.</p></li>
 <li><p><strong>batch_norm_alpha</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>, </em><em>optional</em>) – Momentum for BatchNorm2d. Defaults to 0.01.</p></li>
 <li><p><strong>depth_multiplier</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>, </em><em>optional</em>) – Depth multiplier for the depthwise convolution. Defaults to 2 as in
-<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id11">[Santamaria2020]</a>.</p></li>
+<a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id12">[santamaria2020]</a>.</p></li>
 <li><p><strong>pooling_sizes</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em>(</em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em>)</em><em>, </em><em>optional</em>) – Pooling sizes for the inception blocks. Defaults to 4, 2, 2 and 2, as
-in <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id12">[Santamaria2020]</a>.</p></li>
+in <a class="reference internal" href="#r37c4761d4e92-santamaria2020" id="id13">[santamaria2020]</a>.</p></li>
 <li><p><strong>chs_info</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em> of </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><em>dict</em></a>) – Information about each individual EEG channel. This should be filled with
 <code class="docutils literal notranslate"><span class="pre">info[&quot;chs&quot;]</span></code>. Refer to <a class="reference external" href="https://mne.tools/stable/generated/mne.Info.html#mne.Info" title="(in MNE v1.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">mne.Info</span></code></a> for more details.</p></li>
 <li><p><strong>input_window_seconds</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Length of the input window in seconds.</p></li>
@@ -662,12 +662,12 @@ <h1>braindecode.models.EEGInceptionERP<a class="headerlink" href="#braindecode-m
 </dl>
 <p class="rubric">Notes</p>
 <p>This implementation is not guaranteed to be correct, has not been checked
-by original authors, only reimplemented from the paper based on <a class="reference internal" href="#r37c4761d4e92-2" id="id13">[2]</a>.</p>
+by original authors, only reimplemented from the paper based on <a class="reference internal" href="#r37c4761d4e92-2" id="id14">[2]</a>.</p>
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r37c4761d4e92-santamaria2020" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span>Santamaria2020<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id4">2</a>,<a role="doc-backlink" href="#id5">3</a>,<a role="doc-backlink" href="#id6">4</a>,<a role="doc-backlink" href="#id7">5</a>,<a role="doc-backlink" href="#id8">6</a>,<a role="doc-backlink" href="#id9">7</a>,<a role="doc-backlink" href="#id10">8</a>,<a role="doc-backlink" href="#id11">9</a>,<a role="doc-backlink" href="#id12">10</a>)</span>
+<span class="label"><span class="fn-bracket">[</span>santamaria2020<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id5">3</a>,<a role="doc-backlink" href="#id6">4</a>,<a role="doc-backlink" href="#id7">5</a>,<a role="doc-backlink" href="#id8">6</a>,<a role="doc-backlink" href="#id9">7</a>,<a role="doc-backlink" href="#id10">8</a>,<a role="doc-backlink" href="#id11">9</a>,<a role="doc-backlink" href="#id12">10</a>,<a role="doc-backlink" href="#id13">11</a>)</span>
 <p>Santamaria-Vazquez, E., Martinez-Cagigal, V.,
 Vaquerizo-Villar, F., &amp; Hornero, R. (2020).
 EEG-inception: A novel deep convolutional neural network for assistive
@@ -677,9 +677,20 @@ <h1>braindecode.models.EEGInceptionERP<a class="headerlink" href="#braindecode-m
 </div>
 <div class="citation" id="r37c4761d4e92-2" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>2<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id2">1</a>,<a role="doc-backlink" href="#id13">2</a>)</span>
+<span class="backrefs">(<a role="doc-backlink" href="#id3">1</a>,<a role="doc-backlink" href="#id14">2</a>)</span>
 <p>Grifcc. Implementation of the EEGInception in torch (2022).
-Online: <a class="github reference external" href="https://github.com/Grifcc/EEG/tree/90e412a407c5242dfc953d5ffb490bdb32faf022">Grifcc/EEG</a></p>
+Online: <a class="github reference external" href="https://github.com/Grifcc/EEG/">Grifcc/EEG</a></p>
+</div>
+<div class="citation" id="r37c4761d4e92-beetl" role="doc-biblioentry">
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id4">beetl</a><span class="fn-bracket">]</span></span>
+<p>Wei, X., Faisal, A.A., Grosse-Wentrup, M., Gramfort, A., Chevallier, S.,
+Jayaram, V., Jeunet, C., Bakas, S., Ludwig, S., Barmpas, K., Bahri, M., Panagakis,
+Y., Laskaris, N., Adamos, D.A., Zafeiriou, S., Duong, W.C., Gordon, S.M.,
+Lawhern, V.J., Śliwowski, M., Rouanne, V. &amp;amp; Tempczyk, P. (2022).
+2021 BEETL Competition: Advancing Transfer Learning for Subject Independence &amp;amp;
+Heterogeneous EEG Data Sets. Proceedings of the NeurIPS 2021 Competitions and
+Demonstrations Track, in Proceedings of Machine Learning Research
+176:205-219 Available from <a class="reference external" href="https://proceedings.mlr.press/v176/wei22a.html">https://proceedings.mlr.press/v176/wei22a.html</a>.</p>
 </div>
 </div>
 </dd></dl>
diff --git a/dev/generated/braindecode.models.EEGInceptionMI.html b/dev/generated/braindecode.models.EEGInceptionMI.html
index dfcb8830..7cc0ec70 100644
--- a/dev/generated/braindecode.models.EEGInceptionMI.html
+++ b/dev/generated/braindecode.models.EEGInceptionMI.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,7 +603,7 @@ <h1>braindecode.models.EEGInceptionMI<a class="headerlink" href="#braindecode-mo
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGInceptionMI">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGInceptionMI</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=250</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_convs=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters=48</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_unit_s=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eeginception_mi.py#L13-L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGInceptionMI" title="Link to this definition">#</a></dt>
-<dd><p>EEG Inception for Motor Imagery, as proposed in <a class="reference internal" href="#rc36ed781f4f5-1" id="id1">[1]</a></p>
+<dd><p>EEG Inception for Motor Imagery, as proposed in Zhang et al. (2021) <a class="reference internal" href="#rc36ed781f4f5-1" id="id1">[1]</a></p>
 <p>The model is strongly based on the original InceptionNet for computer
 vision. The main goal is to extract features in parallel with different
 scales. The network has two blocks made of 3 inception modules with a skip
@@ -627,7 +626,7 @@ <h1>braindecode.models.EEGInceptionMI<a class="headerlink" href="#braindecode-mo
 <li><p><strong>kernel_unit_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a><em>, </em><em>optional</em>) – Size in seconds of the basic 1D convolutional kernel used in inception
 modules. Each convolutional layer in such modules have kernels of
 increasing size, odd multiples of this value (e.g. 0.1, 0.3, 0.5, 0.7,
-0.9 here for <a href="#id7"><span class="problematic" id="id8">`</span></a>n_convs`=5). Defaults to 0.1 s.</p></li>
+0.9 here for <code class="docutils literal notranslate"><span class="pre">n_convs=5</span></code>). Defaults to 0.1 s.</p></li>
 <li><p><strong>activation</strong> (<em>nn.Module</em>) – Activation function. Defaults to ReLU activation.</p></li>
 <li><p><strong>chs_info</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em> of </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><em>dict</em></a>) – Information about each individual EEG channel. This should be filled with
 <code class="docutils literal notranslate"><span class="pre">info[&quot;chs&quot;]</span></code>. Refer to <a class="reference external" href="https://mne.tools/stable/generated/mne.Info.html#mne.Info" title="(in MNE v1.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">mne.Info</span></code></a> for more details.</p></li>
@@ -651,12 +650,12 @@ <h1>braindecode.models.EEGInceptionMI<a class="headerlink" href="#braindecode-mo
 </dl>
 <p class="rubric">Notes</p>
 <p>This implementation is not guaranteed to be correct, has not been checked
-by original authors, only reimplemented bosed on the paper <a class="reference internal" href="#rc36ed781f4f5-1" id="id9">[1]</a>.</p>
+by original authors, only reimplemented bosed on the paper <a class="reference internal" href="#rc36ed781f4f5-1" id="id7">[1]</a>.</p>
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rc36ed781f4f5-1" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>,<a role="doc-backlink" href="#id5">5</a>,<a role="doc-backlink" href="#id6">6</a>,<a role="doc-backlink" href="#id9">7</a>)</span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>,<a role="doc-backlink" href="#id5">5</a>,<a role="doc-backlink" href="#id6">6</a>,<a role="doc-backlink" href="#id7">7</a>)</span>
 <p>Zhang, C., Kim, Y. K., &amp; Eskandarian, A. (2021).
 EEG-inception: an accurate and robust end-to-end neural network
 for EEG-based motor imagery classification.
diff --git a/dev/generated/braindecode.models.EEGModuleMixin.html b/dev/generated/braindecode.models.EEGModuleMixin.html
index 8c96f25d..866d72f1 100644
--- a/dev/generated/braindecode.models.EEGModuleMixin.html
+++ b/dev/generated/braindecode.models.EEGModuleMixin.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.models.EEGNeX.html b/dev/generated/braindecode.models.EEGNeX.html
index 099a1730..cfb2b419 100644
--- a/dev/generated/braindecode.models.EEGNeX.html
+++ b/dev/generated/braindecode.models.EEGNeX.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,7 +603,7 @@ <h1>braindecode.models.EEGNeX<a class="headerlink" href="#braindecode-models-eeg
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGNeX">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGNeX</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth_multiplier:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_1:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_2:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">32</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_rate:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_block_4:</span> <span class="pre">tuple[int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">int]</span> <span class="pre">=</span> <span class="pre">(1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">16)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation_block_4:</span> <span class="pre">tuple[int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">int]</span> <span class="pre">=</span> <span class="pre">(1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">avg_pool_block4:</span> <span class="pre">tuple[int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">int]</span> <span class="pre">=</span> <span class="pre">(1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">4)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_block_5:</span> <span class="pre">tuple[int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">int]</span> <span class="pre">=</span> <span class="pre">(1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">16)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation_block_5:</span> <span class="pre">tuple[int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">int]</span> <span class="pre">=</span> <span class="pre">(1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">4)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">avg_pool_block5:</span> <span class="pre">tuple[int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">int]</span> <span class="pre">=</span> <span class="pre">(1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">8)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegnex.py#L13-L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGNeX" title="Link to this definition">#</a></dt>
-<dd><p>EEGNeX model from <a class="reference internal" href="#r60f8df15fd80-eegnex" id="id1">[EEGNeX]</a>.</p>
+<dd><p>EEGNeX model from Chen et al. (2024) <a class="reference internal" href="#r60f8df15fd80-eegnex" id="id1">[eegnex]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -643,7 +642,7 @@ <h1>braindecode.models.EEGNeX<a class="headerlink" href="#braindecode-models-eeg
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r60f8df15fd80-eegnex" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">EEGNeX</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">eegnex</a><span class="fn-bracket">]</span></span>
 <p>Chen, X., Teng, X., Chen, H., Pan, Y., &amp; Geyer, P. (2024).
 Toward reliable signals decoding for electroencephalogram: A benchmark
 study to EEGNeX. Biomedical Signal Processing and Control, 87, 105475.</p>
diff --git a/dev/generated/braindecode.models.EEGNetv1.html b/dev/generated/braindecode.models.EEGNetv1.html
index 8a523ca3..cd87042a 100644
--- a/dev/generated/braindecode.models.EEGNetv1.html
+++ b/dev/generated/braindecode.models.EEGNetv1.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.EEGNetv1<a class="headerlink" href="#braindecode-models-e
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGNetv1">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGNetv1</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_conv_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_mode='max'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">second_kernel_size=(2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">32)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">third_kernel_size=(8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">4)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegnet.py#L227-L411"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGNetv1" title="Link to this definition">#</a></dt>
-<dd><p>EEGNet model from Lawhern et al. 2016.</p>
-<p>See details in <a class="reference internal" href="#rcbe3da2652d4-eegnet" id="id1">[EEGNet]</a>.</p>
+<dd><p>EEGNet model from Lawhern et al. 2016 from <a class="reference internal" href="#rcbe3da2652d4-eegnet" id="id1">[EEGNet]</a>.</p>
+<p>See details in <a class="reference internal" href="#rcbe3da2652d4-eegnet" id="id2">[EEGNet]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -647,7 +646,8 @@ <h1>braindecode.models.EEGNetv1<a class="headerlink" href="#braindecode-models-e
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rcbe3da2652d4-eegnet" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">EEGNet</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>EEGNet<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon,
 S. M., Hung, C. P., &amp; Lance, B. J. (2016).
 EEGNet: A Compact Convolutional Network for EEG-based
diff --git a/dev/generated/braindecode.models.EEGNetv4.html b/dev/generated/braindecode.models.EEGNetv4.html
index 093cd3aa..697b7b64 100644
--- a/dev/generated/braindecode.models.EEGNetv4.html
+++ b/dev/generated/braindecode.models.EEGNetv4.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.EEGNetv4<a class="headerlink" href="#braindecode-models-e
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGNetv4">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGNetv4</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_conv_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_mode='mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">F1=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">D=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">F2=16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_length=64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">third_kernel_size=(8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">4)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegnet.py#L27-L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGNetv4" title="Link to this definition">#</a></dt>
-<dd><p>EEGNet v4 model from Lawhern et al 2018.</p>
-<p>See details in <a class="reference internal" href="#rbd7837e27d7f-eegnet4" id="id1">[EEGNet4]</a>.</p>
+<dd><p>EEGNet v4 model from Lawhern et al. 2018 <a class="reference internal" href="#rbd7837e27d7f-eegnet4" id="id1">[EEGNet4]</a>.</p>
+<p>See details in <a class="reference internal" href="#rbd7837e27d7f-eegnet4" id="id2">[EEGNet4]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -644,7 +643,8 @@ <h1>braindecode.models.EEGNetv4<a class="headerlink" href="#braindecode-models-e
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rbd7837e27d7f-eegnet4" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">EEGNet4</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>EEGNet4<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon,
 S. M., Hung, C. P., &amp; Lance, B. J. (2018).
 EEGNet: A Compact Convolutional Network for EEG-based
diff --git a/dev/generated/braindecode.models.EEGResNet.html b/dev/generated/braindecode.models.EEGResNet.html
index f8803e78..797b95ca 100644
--- a/dev/generated/braindecode.models.EEGResNet.html
+++ b/dev/generated/braindecode.models.EEGResNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,9 +602,9 @@
 <h1>braindecode.models.EEGResNet<a class="headerlink" href="#braindecode-models-eegresnet" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGResNet">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGResNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_pool_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_first_filters=20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_layers_per_block=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">first_filter_length=3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_first_layer=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_alpha=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_epsilon=0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_weight_init_fn=&lt;function</span> <span class="pre">EEGResNet.&lt;lambda&gt;&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=250</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegresnet.py#L19-L291"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGResNet" title="Link to this definition">#</a></dt>
-<dd><p>Residual Network for EEG  from Schirrmeister et al 2017.</p>
-<p>Model described in <a class="reference internal" href="#r625b4a01fbf7-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGResNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_pool_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_first_filters=20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_layers_per_block=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">first_filter_length=3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_first_layer=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_alpha=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_epsilon=0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_weight_init_fn=&lt;function</span> <span class="pre">EEGResNet.&lt;lambda&gt;&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=250</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegresnet.py#L18-L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGResNet" title="Link to this definition">#</a></dt>
+<dd><p>EEGResNet from Schirrmeister et al. 2017 <a class="reference internal" href="#r625b4a01fbf7-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<p>Model described in <a class="reference internal" href="#r625b4a01fbf7-schirrmeister2017" id="id2">[Schirrmeister2017]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -627,18 +626,9 @@ <h1>braindecode.models.EEGResNet<a class="headerlink" href="#braindecode-models-
 <code class="docutils literal notranslate"><span class="pre">info[&quot;chs&quot;]</span></code>. Refer to <a class="reference external" href="https://mne.tools/stable/generated/mne.Info.html#mne.Info" title="(in MNE v1.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">mne.Info</span></code></a> for more details.</p></li>
 <li><p><strong>input_window_seconds</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Length of the input window in seconds.</p></li>
 <li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Sampling frequency of the EEG recordings.</p></li>
-<li><p><strong>in_chans</strong> – <p>Alias for <cite>n_chans</cite>.
-n_classes :</p>
-<blockquote>
-<div><p>Alias for <cite>n_outputs</cite>.</p>
-</div></blockquote>
-<dl class="simple">
-<dt>input_window_samples :</dt><dd><p>Alias for <cite>n_times</cite>.</p>
-</dd>
-</dl>
-</p></li>
-<li><p><strong>n_classes</strong> – The description is missing.</p></li>
-<li><p><strong>input_window_samples</strong> – The description is missing.</p></li>
+<li><p><strong>in_chans</strong> – Alias for <code class="docutils literal notranslate"><span class="pre">n_chans</span></code>.</p></li>
+<li><p><strong>n_classes</strong> – Alias for <code class="docutils literal notranslate"><span class="pre">n_outputs</span></code>.</p></li>
+<li><p><strong>input_window_samples</strong> – Alias for <code class="docutils literal notranslate"><span class="pre">n_times</span></code>.</p></li>
 <li><p><strong>add_log_softmax</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a>) – Whether to use log-softmax non-linearity as the output function.
 LogSoftmax final layer will be removed in the future.
 Please adjust your loss function accordingly (e.g. CrossEntropyLoss)!
@@ -659,13 +649,12 @@ <h1>braindecode.models.EEGResNet<a class="headerlink" href="#braindecode-models-
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r625b4a01fbf7-schirrmeister2017" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Schirrmeister2017</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Schirrmeister2017<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Schirrmeister, R. T., Springenberg, J. T., Fiederer,
 L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F.
-&amp; Ball, T. (2017).
-Deep learning with convolutional neural networks for EEG decoding and
-visualization.
-Human Brain Mapping , Aug. 2017.
+&amp; Ball, T. (2017). Deep learning with convolutional neural networks for ,
+EEG decoding and visualization. Human Brain Mapping, Aug. 2017.
 Online: <a class="reference external" href="http://dx.doi.org/10.1002/hbm.23730">http://dx.doi.org/10.1002/hbm.23730</a></p>
 </div>
 </div>
diff --git a/dev/generated/braindecode.models.EEGSimpleConv.html b/dev/generated/braindecode.models.EEGSimpleConv.html
index 15a72b3e..418b8368 100644
--- a/dev/generated/braindecode.models.EEGSimpleConv.html
+++ b/dev/generated/braindecode.models.EEGSimpleConv.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,8 +602,8 @@
 <h1>braindecode.models.EEGSimpleConv<a class="headerlink" href="#braindecode-models-eegsimpleconv" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGSimpleConv">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGSimpleConv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_maps=128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_convs=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resampling_freq=80</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feature=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegsimpleconv.py#L21-L197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGSimpleConv" title="Link to this definition">#</a></dt>
-<dd><p>EEGSimpleConv from <a class="reference internal" href="#r5661533ddc63-yassine2023" id="id1">[Yassine2023]</a>.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGSimpleConv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_maps=128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_convs=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resampling_freq=80</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feature=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegsimpleconv.py#L21-L195"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGSimpleConv" title="Link to this definition">#</a></dt>
+<dd><p>EEGSimpleConv from Ouahidi, YE et al. (2023) <a class="reference internal" href="#r5661533ddc63-yassine2023" id="id1">[Yassine2023]</a>.</p>
 <p>EEGSimpleConv is a 1D Convolutional Neural Network originally designed
 for decoding motor imagery from EEG signals. The model aims to have a
 very simple and straightforward architecture that allows a low latency,
@@ -618,10 +617,10 @@ <h1>braindecode.models.EEGSimpleConv<a class="headerlink" href="#braindecode-mod
 is performed to obtain a single value per feature map, which is then fed
 into a linear layer to obtain the final classification prediction output.</p>
 <p>The paper and original code with more details about the methodological
-choices are available at the <a class="reference internal" href="#r5661533ddc63-yassine2023" id="id2">[Yassine2023]</a> and <span id="id3">[R5661533ddc63-Yassine2023Code]</span>.</p>
+choices are available at the <a class="reference internal" href="#r5661533ddc63-yassine2023" id="id2">[Yassine2023]</a> and <a class="reference internal" href="#r5661533ddc63-yassine2023code" id="id3">[Yassine2023Code]</a>.</p>
 <p>The input shape should be three-dimensional matrix representing the EEG
 signals.</p>
-<p><cite>(batch_size, n_channels, n_timesteps)</cite>.</p>
+<p><code class="docutils literal notranslate"><span class="pre">(batch_size,</span> <span class="pre">n_channels,</span> <span class="pre">n_timesteps)</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -655,13 +654,14 @@ <h1>braindecode.models.EEGSimpleConv<a class="headerlink" href="#braindecode-mod
 <p>Recommended range for the choice of the hyperparameters, regarding the
 evaluation paradigm.</p>
 <div class="line-block">
+<div class="line-block">
 <div class="line">Parameter    | Within-Subject | Cross-Subject |</div>
 </div>
-<p><a href="#id4"><span class="problematic" id="id5">|-----------------|</span></a>—————-<a href="#id6"><span class="problematic" id="id7">|---------------|</span></a>
-| feature_maps    | [64-144]       |   [64-144]    |
-| n_convs         |    1           |   [2-4]       |
-| resampling_freq | [70-100]       |   [50-80]     |
-| kernel_size     | [12-17]        |   [5-8]       |</p>
+<div class="line">feature_maps    | [64-144]       |   [64-144]    |</div>
+<div class="line">n_convs         |    1           |   [2-4]       |</div>
+<div class="line">resampling_freq | [70-100]       |   [50-80]     |</div>
+<div class="line">kernel_size     | [12-17]        |   [5-8]       |</div>
+</div>
 <p>An intensive ablation study is included in the paper to understand the
 of each parameter on the model performance.</p>
 <div class="versionadded">
@@ -672,19 +672,22 @@ <h1>braindecode.models.EEGSimpleConv<a class="headerlink" href="#braindecode-mod
 <div class="citation" id="r5661533ddc63-yassine2023" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>Yassine2023<span class="fn-bracket">]</span></span>
 <span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
-<p>Yassine El Ouahidi, V. Gripon, B. Pasdeloup, G. Bouallegue</p>
-</div>
+<p>Yassine El Ouahidi, V. Gripon, B. Pasdeloup, G. Bouallegue
+N. Farrugia, G. Lioi, 2023. A Strong and Simple Deep Learning Baseline for
+BCI Motor Imagery Decoding. Arxiv preprint. arxiv.org/abs/2309.07159</p>
 </div>
-<p>N. Farrugia, G. Lioi, 2023. A Strong and Simple Deep Learning Baseline for
-BCI Motor Imagery Decoding. Arxiv preprint. arxiv.org/abs/2309.07159
-.. [R5661533ddc63-Yassine2023Code] Yassine El Ouahidi, V. Gripon, B. Pasdeloup, G. Bouallegue
+<div class="citation" id="r5661533ddc63-yassine2023code" role="doc-biblioentry">
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id3">Yassine2023Code</a><span class="fn-bracket">]</span></span>
+<p>Yassine El Ouahidi, V. Gripon, B. Pasdeloup, G. Bouallegue
 N. Farrugia, G. Lioi, 2023. A Strong and Simple Deep Learning Baseline for
 BCI Motor Imagery Decoding. GitHub repository.
 <a class="github reference external" href="https://github.com/elouayas/EEGSimpleConv">elouayas/EEGSimpleConv</a>.</p>
+</div>
+</div>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.models.EEGSimpleConv.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegsimpleconv.py#L175-L197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGSimpleConv.forward" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegsimpleconv.py#L173-L195"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGSimpleConv.forward" title="Link to this definition">#</a></dt>
 <dd><p>Forward pass of the model.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
diff --git a/dev/generated/braindecode.models.EEGTCNet.html b/dev/generated/braindecode.models.EEGTCNet.html
index ab2a486f..9fd2f8b4 100644
--- a/dev/generated/braindecode.models.EEGTCNet.html
+++ b/dev/generated/braindecode.models.EEGTCNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,8 +602,9 @@
 <h1>braindecode.models.EEGTCNet<a class="headerlink" href="#braindecode-models-eegtcnet" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.EEGTCNet">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGTCNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth_multiplier:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_1:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kern_length:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filters:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm_const:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.25</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegtcnet.py#L197-L330"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGTCNet" title="Link to this definition">#</a></dt>
-<dd><p>EEGTCNet model combining EEGNet and TCN blocks.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">EEGTCNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth_multiplier:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_1:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kern_length:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">64</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filters:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm_const:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.25</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegtcnet.py#L197-L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGTCNet" title="Link to this definition">#</a></dt>
+<dd><p>EEGTCNet model from Ingolfsson et al. (2020) <a class="reference internal" href="#rc25b3d8a3a40-ingolfsson2020" id="id1">[ingolfsson2020]</a>.</p>
+<p>Combining EEGNet and TCN blocks.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -640,18 +640,18 @@ <h1>braindecode.models.EEGTCNet<a class="headerlink" href="#braindecode-models-e
 there will be an attempt to infer them from the other parameters.</p>
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
-<div class="citation" id="rc25b3d8a3a40-1" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
-<p>Ingolfsson, T. M., Hersche, M., Wang, X., Kobayashi, N., Cavigelli, L., &amp; Benini, L.
-(2020). EEG-TCNet: An accurate temporal convolutional network for embedded motor-imagery
-brain–machine interfaces. arXiv preprint arXiv:2006.00622.
-https://doi.org/10.48550/arXiv.2006.00622</p>
+<div class="citation" id="rc25b3d8a3a40-ingolfsson2020" role="doc-biblioentry">
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">ingolfsson2020</a><span class="fn-bracket">]</span></span>
+<p>Ingolfsson, T. M., Hersche, M., Wang, X., Kobayashi, N.,
+Cavigelli, L., &amp; Benini, L. (2020). EEG-TCNet: An accurate temporal
+convolutional network for embedded motor-imagery brain–machine interfaces.
+<a class="reference external" href="https://doi.org/10.48550/arXiv.2006.00622">https://doi.org/10.48550/arXiv.2006.00622</a></p>
 </div>
 </div>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.models.EEGTCNet.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><span class="pre">Tensor</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegtcnet.py#L304-L330"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGTCNet.forward" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><span class="pre">Tensor</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/eegtcnet.py#L306-L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.EEGTCNet.forward" title="Link to this definition">#</a></dt>
 <dd><p>Forward pass of the EEGTCNet model.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
diff --git a/dev/generated/braindecode.models.HybridNet.html b/dev/generated/braindecode.models.HybridNet.html
index 0afee07a..8f08eac1 100644
--- a/dev/generated/braindecode.models.HybridNet.html
+++ b/dev/generated/braindecode.models.HybridNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.HybridNet<a class="headerlink" href="#braindecode-models-
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.HybridNet">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">HybridNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/hybrid.py#L15-L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.HybridNet" title="Link to this definition">#</a></dt>
-<dd><p>Hybrid ConvNet model from Schirrmeister et al 2017.</p>
-<p>See <a class="reference internal" href="#r4d1af390a17e-schirrmeister2017" id="id1">[Schirrmeister2017]</a> for details.</p>
+<dd><p>Hybrid ConvNet model from Schirrmeister et al 2017  <a class="reference internal" href="#r4d1af390a17e-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<p>See <a class="reference internal" href="#r4d1af390a17e-schirrmeister2017" id="id2">[Schirrmeister2017]</a> for details.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -641,7 +640,8 @@ <h1>braindecode.models.HybridNet<a class="headerlink" href="#braindecode-models-
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r4d1af390a17e-schirrmeister2017" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Schirrmeister2017</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Schirrmeister2017<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Schirrmeister, R. T., Springenberg, J. T., Fiederer,
 L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F.
 &amp; Ball, T. (2017).
diff --git a/dev/generated/braindecode.models.Labram.html b/dev/generated/braindecode.models.Labram.html
index a9fb395d..fa993111 100644
--- a/dev/generated/braindecode.models.Labram.html
+++ b/dev/generated/braindecode.models.Labram.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,19 +603,15 @@ <h1>braindecode.models.Labram<a class="headerlink" href="#braindecode-models-lab
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.Labram">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">Labram</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">patch_size=200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">emb_size=200</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_channels=1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_layers=12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">att_num_heads=10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mlp_ratio=4.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qkv_bias=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qk_norm=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qk_scale=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_rate=0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_drop_rate=0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_path_rate=0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_layer=&lt;class</span> <span class="pre">'torch.nn.modules.normalization.LayerNorm'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_values=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_abs_pos_emb=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_mean_pooling=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_scale=0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">neural_tokenizer=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_head_dim=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.GELU'&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/labram.py#L22-L547"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.Labram" title="Link to this definition">#</a></dt>
-<dd><p>Labram.</p>
+<dd><p>Labram from <a class="reference internal" href="#rb5cdfc6ea4fe-jiang2024" id="id1">[Jiang2024]</a>.</p>
 <p>Large Brain Model for Learning Generic Representations with Tremendous
-EEG Data in BCI from <a class="reference internal" href="#rb5cdfc6ea4fe-jiang2024" id="id1">[Jiang2024]</a></p>
-<p>This an <strong>adaptation</strong> of the code <a class="reference internal" href="#rb5cdfc6ea4fe-code2024" id="id2">[Code2024]</a> from the Labram model.</p>
+EEG Data in BCI from <a class="reference internal" href="#rb5cdfc6ea4fe-jiang2024" id="id2">[Jiang2024]</a></p>
+<p>This an <strong>adaptation</strong> of the code <a class="reference internal" href="#rb5cdfc6ea4fe-code2024" id="id3">[Code2024]</a> from the Labram model.</p>
 <p>The model is transformer architecture with <strong>strong</strong> inspiration from
-BEiTv2 <a class="reference internal" href="#rb5cdfc6ea4fe-beitv2" id="id3">[BeiTv2]</a>.</p>
-<dl class="simple">
-<dt>The models can be used in two modes:</dt><dd><ul class="simple">
-<li><p>Neural Tokenizor: Design to get an embedding layers (e.g. classification).</p></li>
-<li><p>Neural Decoder: To extract the ampliture and phase outputs with a VQSNP.</p></li>
-</ul>
-</dd>
-</dl>
+BEiTv2 <a class="reference internal" href="#rb5cdfc6ea4fe-beitv2" id="id4">[BeiTv2]</a>.</p>
+<p>The models can be used in two modes:
+- Neural Tokenizor: Design to get an embedding layers (e.g. classification).
+- Neural Decoder: To extract the ampliture and phase outputs with a VQSNP.</p>
 <p>The braindecode’s modification is to allow the model to be used in
 with an input shape of (batch, n_chans, n_times), if neural tokenizer
 equals True. The original implementation uses (batch, n_chans, n_patches,
@@ -697,21 +692,22 @@ <h1>braindecode.models.Labram<a class="headerlink" href="#braindecode-models-lab
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rb5cdfc6ea4fe-jiang2024" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Jiang2024</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Jiang2024<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Wei-Bang Jiang, Li-Ming Zhao, Bao-Liang Lu. 2024, May.
 Large Brain Model for Learning Generic Representations with Tremendous
 EEG Data in BCI. The Twelfth International Conference on Learning
 Representations, ICLR.</p>
 </div>
 <div class="citation" id="rb5cdfc6ea4fe-code2024" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id2">Code2024</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id3">Code2024</a><span class="fn-bracket">]</span></span>
 <p>Wei-Bang Jiang, Li-Ming Zhao, Bao-Liang Lu. 2024. Labram
 Large Brain Model for Learning Generic Representations with Tremendous
 EEG Data in BCI. GitHub <a class="github reference external" href="https://github.com/935963004/LaBraM">935963004/LaBraM</a>
 (accessed 2024-03-02)</p>
 </div>
 <div class="citation" id="rb5cdfc6ea4fe-beitv2" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id3">BeiTv2</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id4">BeiTv2</a><span class="fn-bracket">]</span></span>
 <p>Zhiliang Peng, Li Dong, Hangbo Bao, Qixiang Ye, Furu Wei. 2024.
 BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers.
 arXiv:2208.06366 [cs.CV]</p>
diff --git a/dev/generated/braindecode.models.SPARCNet.html b/dev/generated/braindecode.models.SPARCNet.html
index b6bcac47..a1736a98 100644
--- a/dev/generated/braindecode.models.SPARCNet.html
+++ b/dev/generated/braindecode.models.SPARCNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,7 +603,7 @@ <h1>braindecode.models.SPARCNet<a class="headerlink" href="#braindecode-models-s
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.SPARCNet">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">SPARCNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">block_layers:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_rate:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bottleneck_size:</span> <span class="pre">int</span> <span class="pre">=</span> <span class="pre">16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_rate:</span> <span class="pre">float</span> <span class="pre">=</span> <span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_bias:</span> <span class="pre">bool</span> <span class="pre">=</span> <span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm:</span> <span class="pre">bool</span> <span class="pre">=</span> <span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info:</span> <span class="pre">list[dict[~typing.Any</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">~typing.Any]]</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds:</span> <span class="pre">float</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/sparcnet.py#L207-L376"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.SPARCNet" title="Link to this definition">#</a></dt>
-<dd><p>Seizures, Periodic and Rhythmic pattern Continuum Neural Network (SPaRCNet) <a class="reference internal" href="#rf8eed20f8ca2-jing2023" id="id1">[jing2023]</a>.</p>
+<dd><p>Seizures, Periodic and Rhythmic pattern Continuum Neural Network (SPaRCNet) from Jing et al. (2023) <a class="reference internal" href="#rf8eed20f8ca2-jing2023" id="id1">[jing2023]</a>.</p>
 <p>This is a temporal CNN model for biosignal classification based on the DenseNet
 architecture.</p>
 <p>The model is based on the unofficial implementation <a class="reference internal" href="#rf8eed20f8ca2-code2023" id="id2">[Code2023]</a>.</p>
diff --git a/dev/generated/braindecode.models.ShallowFBCSPNet.html b/dev/generated/braindecode.models.ShallowFBCSPNet.html
index 36455bc9..0103f8f3 100644
--- a/dev/generated/braindecode.models.ShallowFBCSPNet.html
+++ b/dev/generated/braindecode.models.ShallowFBCSPNet.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.ShallowFBCSPNet<a class="headerlink" href="#braindecode-m
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.ShallowFBCSPNet">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">ShallowFBCSPNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_time=40</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filter_time_length=25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters_spat=40</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_time_length=75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_time_stride=15</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_conv_length='auto'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_nonlin=&lt;function</span> <span class="pre">square&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool_mode='mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_pool_nonlin:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'braindecode.models.modules.SafeLog'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_first_layer=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_norm_alpha=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/shallow_fbcsp.py#L15-L218"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.ShallowFBCSPNet" title="Link to this definition">#</a></dt>
-<dd><p>Shallow ConvNet model from Schirrmeister et al 2017.</p>
-<p>Model described in <a class="reference internal" href="#r9432a19f6121-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<dd><p>Shallow ConvNet model from Schirrmeister et al. 2017 <a class="reference internal" href="#r9432a19f6121-schirrmeister2017" id="id1">[Schirrmeister2017]</a>.</p>
+<p>Model described in <a class="reference internal" href="#r9432a19f6121-schirrmeister2017" id="id2">[Schirrmeister2017]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -655,7 +654,8 @@ <h1>braindecode.models.ShallowFBCSPNet<a class="headerlink" href="#braindecode-m
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r9432a19f6121-schirrmeister2017" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Schirrmeister2017</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Schirrmeister2017<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Schirrmeister, R. T., Springenberg, J. T., Fiederer,
 L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F.
 &amp; Ball, T. (2017).
diff --git a/dev/generated/braindecode.models.SleepStagerBlanco2020.html b/dev/generated/braindecode.models.SleepStagerBlanco2020.html
index 11ad035a..fe21513f 100644
--- a/dev/generated/braindecode.models.SleepStagerBlanco2020.html
+++ b/dev/generated/braindecode.models.SleepStagerBlanco2020.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.SleepStagerBlanco2020<a class="headerlink" href="#brainde
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.SleepStagerBlanco2020">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">SleepStagerBlanco2020</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_conv_chans=20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_groups=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_pool_size=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">apply_batch_norm=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feats=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/sleep_stager_blanco_2020.py#L11-L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.SleepStagerBlanco2020" title="Link to this definition">#</a></dt>
-<dd><p>Sleep staging architecture from Blanco et al 2020.</p>
-<p>Convolutional neural network for sleep staging described in <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id1">[Blanco2020]</a>.
+<dd><p>Sleep staging architecture from Blanco et al. 2020 from <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id1">[Blanco2020]</a></p>
+<p>Convolutional neural network for sleep staging described in <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id2">[Blanco2020]</a>.
 A series of seven convolutional layers with kernel sizes running down from 7 to 3,
 in an attempt to extract more general features at the beginning, while more specific
 and complex features were extracted in the final stages.</p>
@@ -614,11 +613,11 @@ <h1>braindecode.models.SleepStagerBlanco2020<a class="headerlink" href="#brainde
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>n_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of EEG channels.</p></li>
 <li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Sampling frequency of the EEG recordings.</p></li>
-<li><p><strong>n_conv_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of convolutional channels. Set to 20 in <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id2">[Blanco2020]</a>.</p></li>
+<li><p><strong>n_conv_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of convolutional channels. Set to 20 in <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id3">[Blanco2020]</a>.</p></li>
 <li><p><strong>input_window_seconds</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Length of the input window in seconds.</p></li>
 <li><p><strong>n_outputs</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of outputs of the model. This is the number of classes
 in the case of classification.</p></li>
-<li><p><strong>n_groups</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of groups for the convolution. Set to 2 in <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id3">[Blanco2020]</a> for 2 Channel EEG.
+<li><p><strong>n_groups</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of groups for the convolution. Set to 2 in <a class="reference internal" href="#rb3eee9d9e81a-blanco2020" id="id4">[Blanco2020]</a> for 2 Channel EEG.
 controls the connections between inputs and outputs. n_channels and n_conv_chans must be
 divisible by n_groups.</p></li>
 <li><p><strong>max_pool_size</strong> – The description is missing.</p></li>
@@ -657,7 +656,7 @@ <h1>braindecode.models.SleepStagerBlanco2020<a class="headerlink" href="#brainde
 <div role="list" class="citation-list">
 <div class="citation" id="rb3eee9d9e81a-blanco2020" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>Blanco2020<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>)</span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>)</span>
 <p>Fernandez-Blanco, E., Rivero, D. &amp; Pazos, A. Convolutional
 neural networks for sleep stage scoring on a two-channel EEG signal.
 Soft Comput 24, 4067–4079 (2020). <a class="reference external" href="https://doi.org/10.1007/s00500-019-04174-1">https://doi.org/10.1007/s00500-019-04174-1</a></p>
diff --git a/dev/generated/braindecode.models.SleepStagerChambon2018.html b/dev/generated/braindecode.models.SleepStagerChambon2018.html
index 8c2168c1..07d61e7a 100644
--- a/dev/generated/braindecode.models.SleepStagerChambon2018.html
+++ b/dev/generated/braindecode.models.SleepStagerChambon2018.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,19 +603,19 @@ <h1>braindecode.models.SleepStagerChambon2018<a class="headerlink" href="#braind
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.SleepStagerChambon2018">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">SleepStagerChambon2018</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_conv_chs=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_conv_size_s=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_pool_size_s=0.125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_size_s=0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">apply_batch_norm=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feats=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_channels=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/sleep_stager_chambon_2018.py#L11-L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.SleepStagerChambon2018" title="Link to this definition">#</a></dt>
-<dd><p>Sleep staging architecture from Chambon et al 2018.</p>
-<p>Convolutional neural network for sleep staging described in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id1">[Chambon2018]</a>.</p>
+<dd><p>Sleep staging architecture from Chambon et al. 2018 <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id1">[Chambon2018]</a>.</p>
+<p>Convolutional neural network for sleep staging described in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id2">[Chambon2018]</a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>n_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of EEG channels.</p></li>
 <li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Sampling frequency of the EEG recordings.</p></li>
-<li><p><strong>n_conv_chs</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of convolutional channels. Set to 8 in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id2">[Chambon2018]</a>.</p></li>
+<li><p><strong>n_conv_chs</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of convolutional channels. Set to 8 in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id3">[Chambon2018]</a>.</p></li>
 <li><p><strong>time_conv_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Size of filters in temporal convolution layers, in seconds. Set to 0.5
-in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id3">[Chambon2018]</a> (64 samples at sfreq=128).</p></li>
-<li><p><strong>max_pool_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Max pooling size, in seconds. Set to 0.125 in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id4">[Chambon2018]</a> (16
+in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id4">[Chambon2018]</a> (64 samples at sfreq=128).</p></li>
+<li><p><strong>max_pool_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Max pooling size, in seconds. Set to 0.125 in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id5">[Chambon2018]</a> (16
 samples at sfreq=128).</p></li>
-<li><p><strong>pad_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Padding size, in seconds. Set to 0.25 in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id5">[Chambon2018]</a> (half the
+<li><p><strong>pad_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Padding size, in seconds. Set to 0.25 in <a class="reference internal" href="#r89163c5eab6a-chambon2018" id="id6">[Chambon2018]</a> (half the
 temporal convolution kernel size).</p></li>
 <li><p><strong>activation</strong> (<em>nn.Module</em><em>, </em><em>default=nn.ReLU</em>) – Activation function class to apply. Should be a PyTorch activation
 module class like <code class="docutils literal notranslate"><span class="pre">nn.ReLU</span></code> or <code class="docutils literal notranslate"><span class="pre">nn.ELU</span></code>. Default is <code class="docutils literal notranslate"><span class="pre">nn.ReLU</span></code>.</p></li>
@@ -651,7 +650,7 @@ <h1>braindecode.models.SleepStagerChambon2018<a class="headerlink" href="#braind
 <div role="list" class="citation-list">
 <div class="citation" id="r89163c5eab6a-chambon2018" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>Chambon2018<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>,<a role="doc-backlink" href="#id5">5</a>)</span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>,<a role="doc-backlink" href="#id5">5</a>,<a role="doc-backlink" href="#id6">6</a>)</span>
 <p>Chambon, S., Galtier, M. N., Arnal, P. J., Wainrib, G., &amp;
 Gramfort, A. (2018). A deep learning architecture for temporal sleep
 stage classification using multivariate and multimodal time series.
diff --git a/dev/generated/braindecode.models.SleepStagerEldele2021.html b/dev/generated/braindecode.models.SleepStagerEldele2021.html
index 4d47d8c0..d5bb6a0c 100644
--- a/dev/generated/braindecode.models.SleepStagerEldele2021.html
+++ b/dev/generated/braindecode.models.SleepStagerEldele2021.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,16 +603,16 @@ <h1>braindecode.models.SleepStagerEldele2021<a class="headerlink" href="#brainde
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.SleepStagerEldele2021">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">SleepStagerEldele2021</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_tce=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">d_model=80</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">d_ff=120</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_attn_heads=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation_mrcnn:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.GELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">after_reduced_cnn_size=30</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_feats=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/sleep_stager_eldele_2021.py#L16-L199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.SleepStagerEldele2021" title="Link to this definition">#</a></dt>
-<dd><p>Sleep Staging Architecture from Eldele et al 2021.</p>
-<p>Attention based Neural Net for sleep staging as described in <a class="reference internal" href="#r63c3502458ce-eldele2021" id="id1">[Eldele2021]</a>.
-The code for the paper and this model is also available at <a class="reference internal" href="#r63c3502458ce-1" id="id2">[1]</a>.
+<dd><p>Sleep Staging Architecture from Eldele et al. 2021 <a class="reference internal" href="#r63c3502458ce-eldele2021" id="id1">[Eldele2021]</a>.</p>
+<p>Attention based Neural Net for sleep staging as described in <a class="reference internal" href="#r63c3502458ce-eldele2021" id="id2">[Eldele2021]</a>.
+The code for the paper and this model is also available at <a class="reference internal" href="#r63c3502458ce-1" id="id3">[1]</a>.
 Takes single channel EEG as input.
 Feature extraction module based on multi-resolution convolutional neural network (MRCNN)
 and adaptive feature recalibration (AFR).
 The second module is the temporal context encoder (TCE) that leverages a multi-head attention
 mechanism to capture the temporal dependencies among the extracted features.</p>
 <p>Warning - This model was designed for signals of 30 seconds at 100Hz or 125Hz (in which case
-the reference architecture from <a class="reference internal" href="#r63c3502458ce-1" id="id3">[1]</a> which was validated on SHHS dataset <a class="reference internal" href="#r63c3502458ce-2" id="id4">[2]</a> will be used)
+the reference architecture from <a class="reference internal" href="#r63c3502458ce-1" id="id4">[1]</a> which was validated on SHHS dataset <a class="reference internal" href="#r63c3502458ce-2" id="id5">[2]</a> will be used)
 to use any other input is likely to make the model perform in unintended ways.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -662,18 +661,19 @@ <h1>braindecode.models.SleepStagerEldele2021<a class="headerlink" href="#brainde
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="r63c3502458ce-eldele2021" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Eldele2021</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Eldele2021<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>E. Eldele et al., “An Attention-Based Deep Learning Approach for Sleep Stage
 Classification With Single-Channel EEG,” in IEEE Transactions on Neural Systems and
 Rehabilitation Engineering, vol. 29, pp. 809-818, 2021, doi: 10.1109/TNSRE.2021.3076234.</p>
 </div>
 <div class="citation" id="r63c3502458ce-1" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id2">1</a>,<a role="doc-backlink" href="#id3">2</a>)</span>
+<span class="backrefs">(<a role="doc-backlink" href="#id3">1</a>,<a role="doc-backlink" href="#id4">2</a>)</span>
 <p><a class="github reference external" href="https://github.com/emadeldeen24/AttnSleep">emadeldeen24/AttnSleep</a></p>
 </div>
 <div class="citation" id="r63c3502458ce-2" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id4">2</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id5">2</a><span class="fn-bracket">]</span></span>
 <p><a class="reference external" href="https://sleepdata.org/datasets/shhs">https://sleepdata.org/datasets/shhs</a></p>
 </div>
 </div>
diff --git a/dev/generated/braindecode.models.SyncNet.html b/dev/generated/braindecode.models.SyncNet.html
index c55116e2..624ccb68 100644
--- a/dev/generated/braindecode.models.SyncNet.html
+++ b/dev/generated/braindecode.models.SyncNet.html
@@ -447,7 +447,6 @@
 <li class="toctree-l1 current active"><a class="current reference internal" href="#">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.models.TCN.html b/dev/generated/braindecode.models.TCN.html
index d9a63bb5..6683537a 100644
--- a/dev/generated/braindecode.models.TCN.html
+++ b/dev/generated/braindecode.models.TCN.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1 current active"><a class="current reference internal" href="#">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.TCN<a class="headerlink" href="#braindecode-models-tcn" t
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.TCN">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">TCN</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_blocks=3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_filters=30</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ReLU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/tcn.py#L15-L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.TCN" title="Link to this definition">#</a></dt>
-<dd><p>Temporal Convolutional Network (TCN) from Bai et al 2018.</p>
-<p>See <a class="reference internal" href="#rcfca6ae7a220-bai2018" id="id1">[Bai2018]</a> for details.</p>
+<dd><p>Temporal Convolutional Network (TCN) from Bai et al. 2018 <a class="reference internal" href="#rcfca6ae7a220-bai2018" id="id1">[Bai2018]</a>.</p>
+<p>See <a class="reference internal" href="#rcfca6ae7a220-bai2018" id="id2">[Bai2018]</a> for details.</p>
 <p>Code adapted from <a class="github reference external" href="https://github.com/locuslab/TCN/blob/master/TCN/tcn.py">locuslab/TCN</a></p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
@@ -645,7 +644,8 @@ <h1>braindecode.models.TCN<a class="headerlink" href="#braindecode-models-tcn" t
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="rcfca6ae7a220-bai2018" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">Bai2018</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>Bai2018<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Bai, S., Kolter, J. Z., &amp; Koltun, V. (2018).
 An empirical evaluation of generic convolutional and recurrent networks
 for sequence modeling.
diff --git a/dev/generated/braindecode.models.TIDNet.html b/dev/generated/braindecode.models.TIDNet.html
index e63253ca..aaf60eb7 100644
--- a/dev/generated/braindecode.models.TIDNet.html
+++ b/dev/generated/braindecode.models.TIDNet.html
@@ -67,7 +67,7 @@
         </script>
     <link rel="index" title="Index" href="../genindex.html" />
     <link rel="search" title="Search" href="../search.html" />
-    <link rel="next" title="braindecode.models.TimeDistributed" href="braindecode.models.TimeDistributed.html" />
+    <link rel="next" title="braindecode.models.USleep" href="braindecode.models.USleep.html" />
     <link rel="prev" title="braindecode.models.TCN" href="braindecode.models.TCN.html" />
     <link rel="canonical" href="braindecode.org/index.html" />
     
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1 current active"><a class="current reference internal" href="#">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -604,8 +603,8 @@ <h1>braindecode.models.TIDNet<a class="headerlink" href="#braindecode-models-tid
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.TIDNet">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">TIDNet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_samples=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">s_growth=24</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t_filters=32</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_prob=0.4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pooling=15</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">temp_layers=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">spat_layers=2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">temp_span=0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bottleneck=3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">summary=-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.LeakyReLU'&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/tidnet.py#L257-L403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.TIDNet" title="Link to this definition">#</a></dt>
-<dd><p>Thinker Invariance DenseNet model from Kostas et al 2020.</p>
-<p>See <a class="reference internal" href="#re74dd80418c9-tidnet" id="id1">[TIDNet]</a> for details.</p>
+<dd><p>Thinker Invariance DenseNet model from Kostas et al. 2020 <a class="reference internal" href="#re74dd80418c9-tidnet" id="id1">[TIDNet]</a>.</p>
+<p>See <a class="reference internal" href="#re74dd80418c9-tidnet" id="id2">[TIDNet]</a> for details.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
@@ -654,7 +653,8 @@ <h1>braindecode.models.TIDNet<a class="headerlink" href="#braindecode-models-tid
 <p class="rubric">References</p>
 <div role="list" class="citation-list">
 <div class="citation" id="re74dd80418c9-tidnet" role="doc-biblioentry">
-<span class="label"><span class="fn-bracket">[</span><a role="doc-backlink" href="#id1">TIDNet</a><span class="fn-bracket">]</span></span>
+<span class="label"><span class="fn-bracket">[</span>TIDNet<span class="fn-bracket">]</span></span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>)</span>
 <p>Kostas, D. &amp; Rudzicz, F.
 Thinker invariance: enabling deep neural networks for BCI across more
 people.
@@ -699,11 +699,11 @@ <h1>braindecode.models.TIDNet<a class="headerlink" href="#braindecode-models-tid
       </div>
     </a>
     <a class="right-next"
-       href="braindecode.models.TimeDistributed.html"
+       href="braindecode.models.USleep.html"
        title="next page">
       <div class="prev-next-info">
         <p class="prev-next-subtitle">next</p>
-        <p class="prev-next-title">braindecode.models.TimeDistributed</p>
+        <p class="prev-next-title">braindecode.models.USleep</p>
       </div>
       <i class="fa-solid fa-angle-right"></i>
     </a>
diff --git a/dev/generated/braindecode.models.TimeDistributed.html b/dev/generated/braindecode.models.TimeDistributed.html
deleted file mode 100644
index 17ff3b25..00000000
--- a/dev/generated/braindecode.models.TimeDistributed.html
+++ /dev/null
@@ -1,748 +0,0 @@
-
-<!DOCTYPE html>
-
-
-<html lang="en" data-content_root="../" data-theme="light">
-
-  <head>
-    <meta charset="utf-8" />
-    <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
-
-    <title>braindecode.models.TimeDistributed &#8212; Braindecode 0.8.1 documentation</title>
-  
-  
-  
-  <script data-cfasync="false">
-    document.documentElement.dataset.mode = localStorage.getItem("mode") || "light";
-    document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
-  </script>
-  
-  <!-- Loaded before other Sphinx assets -->
-  <link href="../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
-<link href="../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
-<link href="../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
-
-  
-  <link href="../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
-  <link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
-<link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
-<link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
-
-    <link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=fa44fd50" />
-    <link rel="stylesheet" type="text/css" href="../_static/sg_gallery.css?v=d2d258e8" />
-    <link rel="stylesheet" type="text/css" href="../_static/sg_gallery-binder.css?v=f4aeca0c" />
-    <link rel="stylesheet" type="text/css" href="../_static/sg_gallery-dataframe.css?v=2082cf3c" />
-    <link rel="stylesheet" type="text/css" href="../_static/sg_gallery-rendered-html.css?v=1277b6f3" />
-    <link rel="stylesheet" type="text/css" href="../_static/sphinx-design.min.css?v=95c83b7e" />
-    <link rel="stylesheet" type="text/css" href="../_static/style.css?v=09706775" />
-  
-  <!-- Pre-loaded scripts that we'll load fully later -->
-  <link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
-<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
-  <script src="../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
-
-    <script src="../_static/documentation_options.js?v=cc929139"></script>
-    <script src="../_static/doctools.js?v=9a2dae69"></script>
-    <script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
-    <script src="../_static/design-tabs.js?v=f930bc37"></script>
-    <script async="async" src="https://www.googletagmanager.com/gtag/js?id=G-7Q43R82K6D"></script>
-    <script>
-                window.dataLayer = window.dataLayer || [];
-                function gtag(){ dataLayer.push(arguments); }
-                gtag('js', new Date());
-                gtag('config', 'G-7Q43R82K6D');
-            </script>
-    <script>
-                window.dataLayer = window.dataLayer || [];
-                function gtag(){ dataLayer.push(arguments); }
-                gtag('js', new Date());
-                gtag('config', 'G-7Q43R82K6D');
-            </script>
-    <script>DOCUMENTATION_OPTIONS.pagename = 'generated/braindecode.models.TimeDistributed';</script>
-    <script>
-        DOCUMENTATION_OPTIONS.theme_version = '0.15.4';
-        DOCUMENTATION_OPTIONS.theme_switcher_json_url = 'https://braindecode.org/stable/_static/versions.json';
-        DOCUMENTATION_OPTIONS.theme_switcher_version_match = '0.8';
-        DOCUMENTATION_OPTIONS.show_version_warning_banner = false;
-        </script>
-    <link rel="index" title="Index" href="../genindex.html" />
-    <link rel="search" title="Search" href="../search.html" />
-    <link rel="next" title="braindecode.models.USleep" href="braindecode.models.USleep.html" />
-    <link rel="prev" title="braindecode.models.TIDNet" href="braindecode.models.TIDNet.html" />
-    <link rel="canonical" href="braindecode.org/index.html" />
-    
-  <meta name="viewport" content="width=device-width, initial-scale=1"/>
-  <meta name="docsearch:language" content="en"/>
-
-  </head>
-  
-  
-  <body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="light">
-
-  
-  
-  <div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
-  
-  <div id="pst-scroll-pixel-helper"></div>
-  
-  <button type="button" class="btn rounded-pill" id="pst-back-to-top">
-    <i class="fa-solid fa-arrow-up"></i>Back to top</button>
-
-  
-  <input type="checkbox"
-          class="sidebar-toggle"
-          id="pst-primary-sidebar-checkbox"/>
-  <label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
-  
-  <input type="checkbox"
-          class="sidebar-toggle"
-          id="pst-secondary-sidebar-checkbox"/>
-  <label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
-  
-  <div class="search-button__wrapper">
-    <div class="search-button__overlay"></div>
-    <div class="search-button__search-container">
-<form class="bd-search d-flex align-items-center"
-      action="../search.html"
-      method="get">
-  <i class="fa-solid fa-magnifying-glass"></i>
-  <input type="search"
-         class="form-control"
-         name="q"
-         id="search-input"
-         placeholder="Search the docs ..."
-         aria-label="Search the docs ..."
-         autocomplete="off"
-         autocorrect="off"
-         autocapitalize="off"
-         spellcheck="false"/>
-  <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
-</form></div>
-  </div>
-
-  <div class="pst-async-banner-revealer d-none">
-  <aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
-</div>
-
-  
-    <header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
-<div class="bd-header__inner bd-page-width">
-  <button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation">
-    <span class="fa-solid fa-bars"></span>
-  </button>
-  
-  
-  <div class="col-lg-3 navbar-header-items__start">
-    
-      <div class="navbar-item">
-
-  
-    
-  
-
-<a class="navbar-brand logo" href="../index.html">
-  
-  
-  
-  
-  
-    
-    
-    
-    <img src="../_static/braindecode_symbol.png" class="logo__image only-light" alt="Braindecode Logo"/>
-    <script>document.write(`<img src="../_static/braindecode_symbol.png" class="logo__image only-dark" alt="Braindecode Logo"/>`);</script>
-  
-  
-</a></div>
-    
-  </div>
-  
-  <div class="col-lg-9 navbar-header-items">
-    
-    <div class="me-auto navbar-header-items__center">
-      
-        <div class="navbar-item">
-<nav>
-  <ul class="bd-navbar-elements navbar-nav">
-    
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../install/install.html">
-    Install
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../cite.html">
-    Cite
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../auto_examples/index.html">
-    Tutorial and Examples
-  </a>
-</li>
-
-
-<li class="nav-item current active">
-  <a class="nav-link nav-internal" href="../api.html">
-    API Reference
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../help.html">
-    Get help
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../whats_new.html">
-    What’s new
-  </a>
-</li>
-
-  </ul>
-</nav></div>
-      
-    </div>
-    
-    
-    <div class="navbar-header-items__end">
-      
-        <div class="navbar-item navbar-persistent--container">
-          
-
- <script>
- document.write(`
-   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
-    <i class="fa-solid fa-magnifying-glass"></i>
-    <span class="search-button__default-text">Search</span>
-    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
-   </button>
- `);
- </script>
-        </div>
-      
-      
-        <div class="navbar-item">
-
-<script>
-document.write(`
-  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
-    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
-    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
-    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
-  </button>
-`);
-</script></div>
-      
-        <div class="navbar-item">
-<script>
-document.write(`
-  <div class="version-switcher__container dropdown">
-    <button id="pst-version-switcher-button-2"
-      type="button"
-      class="version-switcher__button btn btn-sm dropdown-toggle"
-      data-bs-toggle="dropdown"
-      aria-haspopup="listbox"
-      aria-controls="pst-version-switcher-list-2"
-      aria-label="Version switcher list"
-    >
-      Choose version  <!-- this text may get changed later by javascript -->
-      <span class="caret"></span>
-    </button>
-    <div id="pst-version-switcher-list-2"
-      class="version-switcher__menu dropdown-menu list-group-flush py-0"
-      role="listbox" aria-labelledby="pst-version-switcher-button-2">
-      <!-- dropdown will be populated by javascript on page load -->
-    </div>
-  </div>
-`);
-</script></div>
-      
-    </div>
-    
-  </div>
-  
-  
-    <div class="navbar-persistent--mobile">
-
- <script>
- document.write(`
-   <button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
-    <i class="fa-solid fa-magnifying-glass"></i>
-    <span class="search-button__default-text">Search</span>
-    <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
-   </button>
- `);
- </script>
-    </div>
-  
-
-  
-    <button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page">
-      <span class="fa-solid fa-outdent"></span>
-    </button>
-  
-</div>
-
-    </header>
-  
-
-  <div class="bd-container">
-    <div class="bd-container__inner bd-page-width">
-      
-      
-      
-      <div class="bd-sidebar-primary bd-sidebar">
-        
-
-  
-  <div class="sidebar-header-items sidebar-primary__section">
-    
-    
-      <div class="sidebar-header-items__center">
-        
-          
-          
-            <div class="navbar-item">
-<nav>
-  <ul class="bd-navbar-elements navbar-nav">
-    
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../install/install.html">
-    Install
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../cite.html">
-    Cite
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../auto_examples/index.html">
-    Tutorial and Examples
-  </a>
-</li>
-
-
-<li class="nav-item current active">
-  <a class="nav-link nav-internal" href="../api.html">
-    API Reference
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../help.html">
-    Get help
-  </a>
-</li>
-
-
-<li class="nav-item ">
-  <a class="nav-link nav-internal" href="../whats_new.html">
-    What’s new
-  </a>
-</li>
-
-  </ul>
-</nav></div>
-          
-        
-      </div>
-    
-    
-    
-      <div class="sidebar-header-items__end">
-        
-          <div class="navbar-item">
-
-<script>
-document.write(`
-  <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
-    <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
-    <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
-    <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
-  </button>
-`);
-</script></div>
-        
-          <div class="navbar-item">
-<script>
-document.write(`
-  <div class="version-switcher__container dropdown">
-    <button id="pst-version-switcher-button-3"
-      type="button"
-      class="version-switcher__button btn btn-sm dropdown-toggle"
-      data-bs-toggle="dropdown"
-      aria-haspopup="listbox"
-      aria-controls="pst-version-switcher-list-3"
-      aria-label="Version switcher list"
-    >
-      Choose version  <!-- this text may get changed later by javascript -->
-      <span class="caret"></span>
-    </button>
-    <div id="pst-version-switcher-list-3"
-      class="version-switcher__menu dropdown-menu list-group-flush py-0"
-      role="listbox" aria-labelledby="pst-version-switcher-button-3">
-      <!-- dropdown will be populated by javascript on page load -->
-    </div>
-  </div>
-`);
-</script></div>
-        
-      </div>
-    
-  </div>
-  
-    <div class="sidebar-primary-items__start sidebar-primary__section">
-        <div class="sidebar-primary-item">
-<nav class="bd-docs-nav bd-links"
-     aria-label="Section Navigation">
-  <p class="bd-links__title" role="heading" aria-level="1">Section Navigation</p>
-  <div class="bd-toc-item navbar-nav"><ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.classifier.EEGClassifier.html">braindecode.classifier.EEGClassifier</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.regressor.EEGRegressor.html">braindecode.regressor.EEGRegressor</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGModuleMixin.html">braindecode.models.EEGModuleMixin</a></li>
-</ul>
-<ul class="current nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.ATCNet.html">braindecode.models.ATCNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.AttentionBaseNet.html">braindecode.models.AttentionBaseNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.BIOT.html">braindecode.models.BIOT</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.ContraWR.html">braindecode.models.ContraWR</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.Deep4Net.html">braindecode.models.Deep4Net</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.DeepSleepNet.html">braindecode.models.DeepSleepNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGConformer.html">braindecode.models.EEGConformer</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGInceptionERP.html">braindecode.models.EEGInceptionERP</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGInceptionMI.html">braindecode.models.EEGInceptionMI</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGITNet.html">braindecode.models.EEGITNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGNetv1.html">braindecode.models.EEGNetv1</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGNetv4.html">braindecode.models.EEGNetv4</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGNeX.html">braindecode.models.EEGNeX</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGResNet.html">braindecode.models.EEGResNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGSimpleConv.html">braindecode.models.EEGSimpleConv</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.EEGTCNet.html">braindecode.models.EEGTCNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.HybridNet.html">braindecode.models.HybridNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.Labram.html">braindecode.models.Labram</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.ShallowFBCSPNet.html">braindecode.models.ShallowFBCSPNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.SleepStagerBlanco2020.html">braindecode.models.SleepStagerBlanco2020</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.SleepStagerChambon2018.html">braindecode.models.SleepStagerChambon2018</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.SleepStagerEldele2021.html">braindecode.models.SleepStagerEldele2021</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.SPARCNet.html">braindecode.models.SPARCNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1 current active"><a class="current reference internal" href="#">braindecode.models.TimeDistributed</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.CroppedLoss.html">braindecode.training.CroppedLoss</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.TimeSeriesLoss.html">braindecode.training.TimeSeriesLoss</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.CroppedTrialEpochScoring.html">braindecode.training.CroppedTrialEpochScoring</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.CroppedTimeSeriesEpochScoring.html">braindecode.training.CroppedTimeSeriesEpochScoring</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.PostEpochTrainScoring.html">braindecode.training.PostEpochTrainScoring</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.mixup_criterion.html">braindecode.training.mixup_criterion</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.trial_preds_from_window_preds.html">braindecode.training.trial_preds_from_window_preds</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.training.predict_trials.html">braindecode.training.predict_trials</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.BaseDataset.html">braindecode.datasets.BaseDataset</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.BaseConcatDataset.html">braindecode.datasets.BaseConcatDataset</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.WindowsDataset.html">braindecode.datasets.WindowsDataset</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.MOABBDataset.html">braindecode.datasets.MOABBDataset</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.HGD.html">braindecode.datasets.HGD</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.BNCI2014001.html">braindecode.datasets.BNCI2014001</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.TUH.html">braindecode.datasets.TUH</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.TUHAbnormal.html">braindecode.datasets.TUHAbnormal</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.NMT.html">braindecode.datasets.NMT</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.SleepPhysionet.html">braindecode.datasets.SleepPhysionet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.BCICompetitionIVDataset4.html">braindecode.datasets.BCICompetitionIVDataset4</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.create_from_X_y.html">braindecode.datasets.create_from_X_y</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.create_from_mne_raw.html">braindecode.datasets.create_from_mne_raw</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datasets.create_from_mne_epochs.html">braindecode.datasets.create_from_mne_epochs</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.create_windows_from_events.html">braindecode.preprocessing.create_windows_from_events</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.create_fixed_length_windows.html">braindecode.preprocessing.create_fixed_length_windows</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.create_windows_from_target_channels.html">braindecode.preprocessing.create_windows_from_target_channels</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.exponential_moving_demean.html">braindecode.preprocessing.exponential_moving_demean</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.exponential_moving_standardize.html">braindecode.preprocessing.exponential_moving_standardize</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.filterbank.html">braindecode.preprocessing.filterbank</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.preprocess.html">braindecode.preprocessing.preprocess</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.Preprocessor.html">braindecode.preprocessing.Preprocessor</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.Resample.html">braindecode.preprocessing.Resample</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.DropChannels.html">braindecode.preprocessing.DropChannels</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.SetEEGReference.html">braindecode.preprocessing.SetEEGReference</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.Filter.html">braindecode.preprocessing.Filter</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.Pick.html">braindecode.preprocessing.Pick</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.preprocessing.Crop.html">braindecode.preprocessing.Crop</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datautil.save_concat_dataset.html">braindecode.datautil.save_concat_dataset</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.datautil.load_concat_dataset.html">braindecode.datautil.load_concat_dataset</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.samplers.RecordingSampler.html">braindecode.samplers.RecordingSampler</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.samplers.SequenceSampler.html">braindecode.samplers.SequenceSampler</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.samplers.RelativePositioningSampler.html">braindecode.samplers.RelativePositioningSampler</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.samplers.BalancedSequenceSampler.html">braindecode.samplers.BalancedSequenceSampler</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.Transform.html">braindecode.augmentation.Transform</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.IdentityTransform.html">braindecode.augmentation.IdentityTransform</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.Compose.html">braindecode.augmentation.Compose</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.AugmentedDataLoader.html">braindecode.augmentation.AugmentedDataLoader</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.TimeReverse.html">braindecode.augmentation.TimeReverse</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SignFlip.html">braindecode.augmentation.SignFlip</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.FTSurrogate.html">braindecode.augmentation.FTSurrogate</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.ChannelsShuffle.html">braindecode.augmentation.ChannelsShuffle</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.ChannelsDropout.html">braindecode.augmentation.ChannelsDropout</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.GaussianNoise.html">braindecode.augmentation.GaussianNoise</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.ChannelsSymmetry.html">braindecode.augmentation.ChannelsSymmetry</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SmoothTimeMask.html">braindecode.augmentation.SmoothTimeMask</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.BandstopFilter.html">braindecode.augmentation.BandstopFilter</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.FrequencyShift.html">braindecode.augmentation.FrequencyShift</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SensorsRotation.html">braindecode.augmentation.SensorsRotation</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SensorsZRotation.html">braindecode.augmentation.SensorsZRotation</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SensorsYRotation.html">braindecode.augmentation.SensorsYRotation</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SensorsXRotation.html">braindecode.augmentation.SensorsXRotation</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.Mixup.html">braindecode.augmentation.Mixup</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.SegmentationReconstruction.html">braindecode.augmentation.SegmentationReconstruction</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.MaskEncoding.html">braindecode.augmentation.MaskEncoding</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.identity.html">braindecode.augmentation.functional.identity</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.time_reverse.html">braindecode.augmentation.functional.time_reverse</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.sign_flip.html">braindecode.augmentation.functional.sign_flip</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.ft_surrogate.html">braindecode.augmentation.functional.ft_surrogate</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.channels_dropout.html">braindecode.augmentation.functional.channels_dropout</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.channels_shuffle.html">braindecode.augmentation.functional.channels_shuffle</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.channels_permute.html">braindecode.augmentation.functional.channels_permute</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.gaussian_noise.html">braindecode.augmentation.functional.gaussian_noise</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.smooth_time_mask.html">braindecode.augmentation.functional.smooth_time_mask</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.bandstop_filter.html">braindecode.augmentation.functional.bandstop_filter</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.frequency_shift.html">braindecode.augmentation.functional.frequency_shift</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.sensors_rotation.html">braindecode.augmentation.functional.sensors_rotation</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.mixup.html">braindecode.augmentation.functional.mixup</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.segmentation_reconstruction.html">braindecode.augmentation.functional.segmentation_reconstruction</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.augmentation.functional.mask_encoding.html">braindecode.augmentation.functional.mask_encoding</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.util.set_random_seeds.html">braindecode.util.set_random_seeds</a></li>
-</ul>
-<ul class="nav bd-sidenav">
-<li class="toctree-l1"><a class="reference internal" href="braindecode.visualization.compute_amplitude_gradients.html">braindecode.visualization.compute_amplitude_gradients</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.visualization.plot_confusion_matrix.html">braindecode.visualization.plot_confusion_matrix</a></li>
-</ul>
-</div>
-</nav></div>
-    </div>
-  
-  
-  <div class="sidebar-primary-items__end sidebar-primary__section">
-  </div>
-  
-  <div id="rtd-footer-container"></div>
-
-
-      </div>
-      
-      <main id="main-content" class="bd-main" role="main">
-        
-        
-          <div class="bd-content">
-            <div class="bd-article-container">
-              
-              <div class="bd-header-article d-print-none">
-<div class="header-article-items header-article__inner">
-  
-    <div class="header-article-items__start">
-      
-        <div class="header-article-item">
-
-
-
-<nav aria-label="Breadcrumb" class="d-print-none">
-  <ul class="bd-breadcrumbs">
-    
-    <li class="breadcrumb-item breadcrumb-home">
-      <a href="../index.html" class="nav-link" aria-label="Home">
-        <i class="fa-solid fa-home"></i>
-      </a>
-    </li>
-    
-    <li class="breadcrumb-item"><a href="../api.html" class="nav-link">API Reference</a></li>
-    
-    <li class="breadcrumb-item active" aria-current="page">braindecode....</li>
-  </ul>
-</nav>
-</div>
-      
-    </div>
-  
-  
-</div>
-</div>
-              
-              
-<div>
-  
-  <section id="braindecode-models-timedistributed">
-<h1>braindecode.models.TimeDistributed<a class="headerlink" href="#braindecode-models-timedistributed" title="Link to this heading">#</a></h1>
-<dl class="py class">
-<dt class="sig sig-object py" id="braindecode.models.TimeDistributed">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">TimeDistributed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/modules.py#L202-L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.TimeDistributed" title="Link to this definition">#</a></dt>
-<dd><p>Apply module on multiple windows.</p>
-<p>Apply the provided module on a sequence of windows and return their
-concatenation.
-Useful with sequence-to-prediction models (e.g. sleep stager which must map
-a sequence of consecutive windows to the label of the middle window in the
-sequence).</p>
-<dl class="field-list simple">
-<dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>module</strong> (<em>nn.Module</em>) – Module to be applied to the input windows. Must accept an input of
-shape (batch_size, n_channels, n_times).</p>
-</dd>
-</dl>
-<p class="rubric">Methods</p>
-<dl class="py method">
-<dt class="sig sig-object py" id="braindecode.models.TimeDistributed.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/modules.py#L222-L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.TimeDistributed.forward" title="Link to this definition">#</a></dt>
-<dd><dl class="field-list simple">
-<dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>x</strong> (<a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)"><em>torch.Tensor</em></a>) – Sequence of windows, of shape (batch_size, seq_len, n_channels,
-n_times).</p>
-</dd>
-<dt class="field-even">Returns<span class="colon">:</span></dt>
-<dd class="field-even"><p>Shape (batch_size, seq_len, output_size).</p>
-</dd>
-<dt class="field-odd">Return type<span class="colon">:</span></dt>
-<dd class="field-odd"><p><a class="reference external" href="https://pytorch.org/docs/stable/tensors.html#torch.Tensor" title="(in PyTorch v2.4)">torch.Tensor</a></p>
-</dd>
-</dl>
-</dd></dl>
-
-</dd></dl>
-
-<section id="examples-using-braindecode-models-timedistributed">
-<h2>Examples using <code class="docutils literal notranslate"><span class="pre">braindecode.models.TimeDistributed</span></code><a class="headerlink" href="#examples-using-braindecode-models-timedistributed" title="Link to this heading">#</a></h2>
-<div class="sphx-glr-thumbnails"><div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to train and test a sleep staging neural network with Braindecode. We adapt the time distributed approach of [1]_ to learn on sequences of EEG windows using the openly accessible Sleep Physionet dataset [2]_ [3]_."><img alt="" src="../_images/sphx_glr_plot_sleep_staging_chambon2018_thumb.png" />
-<p><a class="reference internal" href="../auto_examples/applied_examples/plot_sleep_staging_chambon2018.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-chambon2018-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Chambon2018 network</span></a></p>
-  <div class="sphx-glr-thumbnail-title">Sleep staging on the Sleep Physionet dataset using Chambon2018 network</div>
-</div><div class="sphx-glr-thumbcontainer" tooltip="This tutorial shows how to train and test a sleep staging neural network with Braindecode. We use the attention-based model from [1]_ with the time distributed approach of [2]_ to learn on sequences of EEG windows using the openly accessible Sleep Physionet dataset [3]_ [4]_."><img alt="" src="../_images/sphx_glr_plot_sleep_staging_eldele2021_thumb.png" />
-<p><a class="reference internal" href="../auto_examples/applied_examples/plot_sleep_staging_eldele2021.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-eldele2021-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Eldele2021</span></a></p>
-  <div class="sphx-glr-thumbnail-title">Sleep staging on the Sleep Physionet dataset using Eldele2021</div>
-</div></div><div style='clear:both'></div></section>
-</section>
-
-
-  
-</div>
-
-              
-              
-              
-              
-                <footer class="prev-next-footer d-print-none">
-                  
-<div class="prev-next-area">
-    <a class="left-prev"
-       href="braindecode.models.TIDNet.html"
-       title="previous page">
-      <i class="fa-solid fa-angle-left"></i>
-      <div class="prev-next-info">
-        <p class="prev-next-subtitle">previous</p>
-        <p class="prev-next-title">braindecode.models.TIDNet</p>
-      </div>
-    </a>
-    <a class="right-next"
-       href="braindecode.models.USleep.html"
-       title="next page">
-      <div class="prev-next-info">
-        <p class="prev-next-subtitle">next</p>
-        <p class="prev-next-title">braindecode.models.USleep</p>
-      </div>
-      <i class="fa-solid fa-angle-right"></i>
-    </a>
-</div>
-                </footer>
-              
-            </div>
-            
-            
-              
-                <div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
-
-
-  <div class="sidebar-secondary-item">
-<div
-    id="pst-page-navigation-heading-2"
-    class="page-toc tocsection onthispage">
-    <i class="fa-solid fa-list"></i> On this page
-  </div>
-  <nav class="bd-toc-nav page-toc" aria-labelledby="pst-page-navigation-heading-2">
-    <ul class="visible nav section-nav flex-column">
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#braindecode.models.TimeDistributed"><code class="docutils literal notranslate"><span class="pre">TimeDistributed</span></code></a><ul class="nav section-nav flex-column">
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#braindecode.models.TimeDistributed.forward"><code class="docutils literal notranslate"><span class="pre">TimeDistributed.forward()</span></code></a></li>
-</ul>
-</li>
-<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#examples-using-braindecode-models-timedistributed">Examples using <code class="docutils literal notranslate"><span class="pre">braindecode.models.TimeDistributed</span></code></a></li>
-</ul>
-  </nav></div>
-
-</div></div>
-              
-            
-          </div>
-          <footer class="bd-footer-content">
-            
-          </footer>
-        
-      </main>
-    </div>
-  </div>
-  
-    
-  <!-- Scripts loaded after <body> so the DOM is not blocked -->
-  <script src="../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
-<script src="../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
-
-    <script src="https://braindecode.org/versionwarning.js"></script>
-    
-  <footer class="bd-footer">
-<div class="bd-footer__inner bd-page-width">
-  
-    <div class="footer-items__start">
-      
-        <div class="footer-item"><p class="text-center text-muted small">&copy; Copyright 2018–2024, Braindecode Developers.</p></div>
-      
-    </div>
-  
-  
-  
-    <div class="footer-items__end">
-      
-        <div class="footer-item">
-<p class="theme-version">
-  Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.15.4.
-</p></div>
-      
-    </div>
-  
-</div>
-
-  </footer>
-  </body>
-</html>
\ No newline at end of file
diff --git a/dev/generated/braindecode.models.USleep.html b/dev/generated/braindecode.models.USleep.html
index 7f9fb1f2..ed060ad7 100644
--- a/dev/generated/braindecode.models.USleep.html
+++ b/dev/generated/braindecode.models.USleep.html
@@ -68,7 +68,7 @@
     <link rel="index" title="Index" href="../genindex.html" />
     <link rel="search" title="Search" href="../search.html" />
     <link rel="next" title="braindecode.training.CroppedLoss" href="braindecode.training.CroppedLoss.html" />
-    <link rel="prev" title="braindecode.models.TimeDistributed" href="braindecode.models.TimeDistributed.html" />
+    <link rel="prev" title="braindecode.models.TIDNet" href="braindecode.models.TIDNet.html" />
     <link rel="canonical" href="braindecode.org/index.html" />
     
   <meta name="viewport" content="width=device-width, initial-scale=1"/>
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1 current active"><a class="current reference internal" href="#">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,52 +602,50 @@
 <h1>braindecode.models.USleep<a class="headerlink" href="#braindecode-models-usleep" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.models.USleep">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">USleep</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth=12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_time_filters=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">complexity_factor=1.67</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_skip_connection=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_conv_size_s=0.0703125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ensure_odd_conv_size=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/usleep.py#L120-L357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.USleep" title="Link to this definition">#</a></dt>
-<dd><p>Sleep staging architecture from Perslev et al 2021.</p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.models.</span></span><span class="sig-name descname"><span class="pre">USleep</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sfreq=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">depth=12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_time_filters=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">complexity_factor=1.67</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_skip_connection=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_outputs=5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_window_seconds=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">time_conv_size_s=0.0703125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ensure_odd_conv_size=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation:</span> <span class="pre">~torch.nn.modules.module.Module</span> <span class="pre">=</span> <span class="pre">&lt;class</span> <span class="pre">'torch.nn.modules.activation.ELU'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chs_info=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_times=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_chans=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size_s=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_log_softmax=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/usleep.py#L120-L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.USleep" title="Link to this definition">#</a></dt>
+<dd><p>Sleep staging architecture from Perslev et al. 2021 <a class="reference internal" href="#r58a5e8182f0a-1" id="id1">[1]</a>.</p>
 <p>U-Net (autoencoder with skip connections) feature-extractor for sleep
-staging described in <a class="reference internal" href="#r58a5e8182f0a-1" id="id1">[1]</a>.</p>
-<dl>
-<dt>For the encoder (‘down’):</dt><dd><p>– the temporal dimension shrinks (via maxpooling in the time-domain)
-– the spatial dimension expands (via more conv1d filters in the</p>
-<blockquote>
-<div><p>time-domain)</p>
-</div></blockquote>
+staging described in <a class="reference internal" href="#r58a5e8182f0a-1" id="id2">[1]</a>.</p>
+<dl class="simple">
+<dt>For the encoder (‘down’):</dt><dd><ul class="simple">
+<li><p>the temporal dimension shrinks (via maxpooling in the time-domain)</p></li>
+<li><p>the spatial dimension expands (via more conv1d filters in the time-domain)</p></li>
+</ul>
 </dd>
-<dt>For the decoder (‘up’):</dt><dd><p>– the temporal dimension expands (via upsampling in the time-domain)
-– the spatial dimension shrinks (via fewer conv1d filters in the</p>
-<blockquote>
-<div><p>time-domain)</p>
-</div></blockquote>
+<dt>For the decoder (‘up’):</dt><dd><ul class="simple">
+<li><p>the temporal dimension expands (via upsampling in the time-domain)</p></li>
+<li><p>the spatial dimension shrinks (via fewer conv1d filters in the time-domain)</p></li>
+</ul>
 </dd>
 </dl>
 <p>Both do so at exponential rates.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>n_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of EEG or EOG channels. Set to 2 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id2">[1]</a> (1 EEG, 1 EOG).</p></li>
-<li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – EEG sampling frequency. Set to 128 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id3">[1]</a>.</p></li>
-<li><p><strong>depth</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of conv blocks in encoding layer (number of 2x2 max pools)
-Note: each block halve the spatial dimensions of the features.</p></li>
-<li><p><strong>n_time_filters</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Initial number of convolutional filters. Set to 5 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id4">[1]</a>.</p></li>
-<li><p><strong>complexity_factor</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Multiplicative factor for number of channels at each layer of the U-Net.
-Set to 2 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id5">[1]</a>.</p></li>
+<li><p><strong>n_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of EEG or EOG channels. Set to 2 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id3">[1]</a> (1 EEG, 1 EOG).</p></li>
+<li><p><strong>sfreq</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – EEG sampling frequency. Set to 128 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id4">[1]</a>.</p></li>
+<li><p><strong>depth</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of conv blocks in encoding layer (number of 2x2 max pools).
+Note: each block halves the spatial dimensions of the features.</p></li>
+<li><p><strong>n_time_filters</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Initial number of convolutional filters. Set to 5 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id5">[1]</a>.</p></li>
+<li><p><strong>complexity_factor</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Multiplicative factor for the number of channels at each layer of the U-Net.
+Set to 2 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id6">[1]</a>.</p></li>
 <li><p><strong>with_skip_connection</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a>) – If True, use skip connections in decoder blocks.</p></li>
 <li><p><strong>n_outputs</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of outputs/classes. Set to 5.</p></li>
-<li><p><strong>input_window_seconds</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Size of the input, in seconds. Set to 30 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id6">[1]</a>.</p></li>
+<li><p><strong>input_window_seconds</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Size of the input, in seconds. Set to 30 in <a class="reference internal" href="#r58a5e8182f0a-1" id="id7">[1]</a>.</p></li>
 <li><p><strong>time_conv_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Size of the temporal convolution kernel, in seconds. Set to 9 / 128 in
-<a class="reference internal" href="#r58a5e8182f0a-1" id="id7">[1]</a>.</p></li>
+<a class="reference internal" href="#r58a5e8182f0a-1" id="id8">[1]</a>.</p></li>
 <li><p><strong>ensure_odd_conv_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a>) – If True and the size of the convolutional kernel is an even number, one
 will be added to it to ensure it is odd, so that the decoder blocks can
-work. This can useful when using different sampling rates from 128
+work. This can be useful when using different sampling rates from 128
 or 100 Hz.</p></li>
 <li><p><strong>activation</strong> (<em>nn.Module</em><em>, </em><em>default=nn.ELU</em>) – Activation function class to apply. Should be a PyTorch activation
 module class like <code class="docutils literal notranslate"><span class="pre">nn.ReLU</span></code> or <code class="docutils literal notranslate"><span class="pre">nn.ELU</span></code>. Default is <code class="docutils literal notranslate"><span class="pre">nn.ELU</span></code>.</p></li>
 <li><p><strong>chs_info</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.12)"><em>list</em></a><em> of </em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.12)"><em>dict</em></a>) – Information about each individual EEG channel. This should be filled with
 <code class="docutils literal notranslate"><span class="pre">info[&quot;chs&quot;]</span></code>. Refer to <a class="reference external" href="https://mne.tools/stable/generated/mne.Info.html#mne.Info" title="(in MNE v1.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">mne.Info</span></code></a> for more details.</p></li>
 <li><p><strong>n_times</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Number of time samples of the input window.</p></li>
-<li><p><strong>in_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Alias for n_chans.</p></li>
-<li><p><strong>n_classes</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Alias for n_outputs.</p></li>
-<li><p><strong>input_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Alias for input_window_seconds.</p></li>
+<li><p><strong>in_chans</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Alias for <cite>n_chans</cite>.</p></li>
+<li><p><strong>n_classes</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Alias for <cite>n_outputs</cite>.</p></li>
+<li><p><strong>input_size_s</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.12)"><em>float</em></a>) – Alias for <cite>input_window_seconds</cite>.</p></li>
 <li><p><strong>add_log_softmax</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.12)"><em>bool</em></a>) – Whether to use log-softmax non-linearity as the output function.
 LogSoftmax final layer will be removed in the future.
 Please adjust your loss function accordingly (e.g. CrossEntropyLoss)!
@@ -670,16 +667,16 @@ <h1>braindecode.models.USleep<a class="headerlink" href="#braindecode-models-usl
 <div role="list" class="citation-list">
 <div class="citation" id="r58a5e8182f0a-1" role="doc-biblioentry">
 <span class="label"><span class="fn-bracket">[</span>1<span class="fn-bracket">]</span></span>
-<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>,<a role="doc-backlink" href="#id5">5</a>,<a role="doc-backlink" href="#id6">6</a>,<a role="doc-backlink" href="#id7">7</a>)</span>
+<span class="backrefs">(<a role="doc-backlink" href="#id1">1</a>,<a role="doc-backlink" href="#id2">2</a>,<a role="doc-backlink" href="#id3">3</a>,<a role="doc-backlink" href="#id4">4</a>,<a role="doc-backlink" href="#id5">5</a>,<a role="doc-backlink" href="#id6">6</a>,<a role="doc-backlink" href="#id7">7</a>,<a role="doc-backlink" href="#id8">8</a>)</span>
 <p>Perslev M, Darkner S, Kempfner L, Nikolic M, Jennum PJ, Igel C.
-U-Sleep: resilient high-frequency sleep staging. npj Digit. Med. 4, 72 (2021).
+U-Sleep: resilient high-frequency sleep staging. <em>npj Digit. Med.</em> 4, 72 (2021).
 <a class="github reference external" href="https://github.com/perslev/U-Time/blob/master/utime/models/usleep.py">perslev/U-Time</a></p>
 </div>
 </div>
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.models.USleep.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/usleep.py#L327-L357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.USleep.forward" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/models/usleep.py#L328-L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.models.USleep.forward" title="Link to this definition">#</a></dt>
 <dd><p>If input x has shape (B, S, C, T), return y_pred of shape (B, n_classes, S).
 If input x has shape (B, C, T), return y_pred of shape (B, n_classes).</p>
 <dl class="field-list simple">
@@ -711,12 +708,12 @@ <h2>Examples using <code class="docutils literal notranslate"><span class="pre">
                   
 <div class="prev-next-area">
     <a class="left-prev"
-       href="braindecode.models.TimeDistributed.html"
+       href="braindecode.models.TIDNet.html"
        title="previous page">
       <i class="fa-solid fa-angle-left"></i>
       <div class="prev-next-info">
         <p class="prev-next-subtitle">previous</p>
-        <p class="prev-next-title">braindecode.models.TimeDistributed</p>
+        <p class="prev-next-title">braindecode.models.TIDNet</p>
       </div>
     </a>
     <a class="right-next"
diff --git a/dev/generated/braindecode.preprocessing.Crop.html b/dev/generated/braindecode.preprocessing.Crop.html
index d3dc87c9..a734dc60 100644
--- a/dev/generated/braindecode.preprocessing.Crop.html
+++ b/dev/generated/braindecode.preprocessing.Crop.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.DropChannels.html b/dev/generated/braindecode.preprocessing.DropChannels.html
index d21153a4..9b1e70d0 100644
--- a/dev/generated/braindecode.preprocessing.DropChannels.html
+++ b/dev/generated/braindecode.preprocessing.DropChannels.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.Filter.html b/dev/generated/braindecode.preprocessing.Filter.html
index 6666cd87..4e535648 100644
--- a/dev/generated/braindecode.preprocessing.Filter.html
+++ b/dev/generated/braindecode.preprocessing.Filter.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.Pick.html b/dev/generated/braindecode.preprocessing.Pick.html
index afe8db4a..9448ae49 100644
--- a/dev/generated/braindecode.preprocessing.Pick.html
+++ b/dev/generated/braindecode.preprocessing.Pick.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.Preprocessor.html b/dev/generated/braindecode.preprocessing.Preprocessor.html
index d2aac3a6..55afc59d 100644
--- a/dev/generated/braindecode.preprocessing.Preprocessor.html
+++ b/dev/generated/braindecode.preprocessing.Preprocessor.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.Resample.html b/dev/generated/braindecode.preprocessing.Resample.html
index e35a279a..54f63145 100644
--- a/dev/generated/braindecode.preprocessing.Resample.html
+++ b/dev/generated/braindecode.preprocessing.Resample.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.SetEEGReference.html b/dev/generated/braindecode.preprocessing.SetEEGReference.html
index 4517d82d..78893054 100644
--- a/dev/generated/braindecode.preprocessing.SetEEGReference.html
+++ b/dev/generated/braindecode.preprocessing.SetEEGReference.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.create_fixed_length_windows.html b/dev/generated/braindecode.preprocessing.create_fixed_length_windows.html
index 2b5db5ef..d34d48ee 100644
--- a/dev/generated/braindecode.preprocessing.create_fixed_length_windows.html
+++ b/dev/generated/braindecode.preprocessing.create_fixed_length_windows.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.create_windows_from_events.html b/dev/generated/braindecode.preprocessing.create_windows_from_events.html
index 67d924d5..ed55bbdf 100644
--- a/dev/generated/braindecode.preprocessing.create_windows_from_events.html
+++ b/dev/generated/braindecode.preprocessing.create_windows_from_events.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.create_windows_from_target_channels.html b/dev/generated/braindecode.preprocessing.create_windows_from_target_channels.html
index 90793d80..a2b0ee33 100644
--- a/dev/generated/braindecode.preprocessing.create_windows_from_target_channels.html
+++ b/dev/generated/braindecode.preprocessing.create_windows_from_target_channels.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.exponential_moving_demean.html b/dev/generated/braindecode.preprocessing.exponential_moving_demean.html
index f12cf348..8550076b 100644
--- a/dev/generated/braindecode.preprocessing.exponential_moving_demean.html
+++ b/dev/generated/braindecode.preprocessing.exponential_moving_demean.html
@@ -447,7 +447,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.exponential_moving_standardize.html b/dev/generated/braindecode.preprocessing.exponential_moving_standardize.html
index ac35070c..3a08a126 100644
--- a/dev/generated/braindecode.preprocessing.exponential_moving_standardize.html
+++ b/dev/generated/braindecode.preprocessing.exponential_moving_standardize.html
@@ -447,7 +447,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.filterbank.html b/dev/generated/braindecode.preprocessing.filterbank.html
index bcb34419..795c9f83 100644
--- a/dev/generated/braindecode.preprocessing.filterbank.html
+++ b/dev/generated/braindecode.preprocessing.filterbank.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.preprocessing.preprocess.html b/dev/generated/braindecode.preprocessing.preprocess.html
index adfa3588..3b1b5dc0 100644
--- a/dev/generated/braindecode.preprocessing.preprocess.html
+++ b/dev/generated/braindecode.preprocessing.preprocess.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.regressor.EEGRegressor.html b/dev/generated/braindecode.regressor.EEGRegressor.html
index 55f9179d..016204f2 100644
--- a/dev/generated/braindecode.regressor.EEGRegressor.html
+++ b/dev/generated/braindecode.regressor.EEGRegressor.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.samplers.BalancedSequenceSampler.html b/dev/generated/braindecode.samplers.BalancedSequenceSampler.html
index 7e3f2e79..8faad5dc 100644
--- a/dev/generated/braindecode.samplers.BalancedSequenceSampler.html
+++ b/dev/generated/braindecode.samplers.BalancedSequenceSampler.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,7 +602,7 @@
 <h1>braindecode.samplers.BalancedSequenceSampler<a class="headerlink" href="#braindecode-samplers-balancedsequencesampler" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.samplers.BalancedSequenceSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.samplers.</span></span><span class="sig-name descname"><span class="pre">BalancedSequenceSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_sequences</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L178-L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.BalancedSequenceSampler" title="Link to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.samplers.</span></span><span class="sig-name descname"><span class="pre">BalancedSequenceSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_sequences</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L184-L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.BalancedSequenceSampler" title="Link to this definition">#</a></dt>
 <dd><p>Balanced sampling of sequences of consecutive windows with categorical
 targets.</p>
 <p>Balanced sampling of sequences inspired by the approach of <a class="reference internal" href="#r3d821f159c06-perslev2021" id="id1">[Perslev2021]</a>:
@@ -635,7 +634,7 @@ <h1>braindecode.samplers.BalancedSequenceSampler<a class="headerlink" href="#bra
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.samplers.BalancedSequenceSampler.sample_class">
-<span class="sig-name descname"><span class="pre">sample_class</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rec_ind</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L215-L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.BalancedSequenceSampler.sample_class" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample_class</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rec_ind</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L221-L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.BalancedSequenceSampler.sample_class" title="Link to this definition">#</a></dt>
 <dd><p>Return a random class.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
diff --git a/dev/generated/braindecode.samplers.RecordingSampler.html b/dev/generated/braindecode.samplers.RecordingSampler.html
index 288a9267..cbd1fe9b 100644
--- a/dev/generated/braindecode.samplers.RecordingSampler.html
+++ b/dev/generated/braindecode.samplers.RecordingSampler.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,24 +602,28 @@
 <h1>braindecode.samplers.RecordingSampler<a class="headerlink" href="#braindecode-samplers-recordingsampler" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.samplers.RecordingSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.samplers.</span></span><span class="sig-name descname"><span class="pre">RecordingSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L15-L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.RecordingSampler" title="Link to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.samplers.</span></span><span class="sig-name descname"><span class="pre">RecordingSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L15-L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.RecordingSampler" title="Link to this definition">#</a></dt>
 <dd><p>Base sampler simplifying sampling from recordings.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
 <dd class="field-odd"><ul class="simple">
-<li><p><strong>metadata</strong> (<em>pd.DataFrame</em>) – <p>DataFrame with at least one of {subject, session, run} columns for each
+<li><p><strong>metadata</strong> (<em>pd.DataFrame</em>) – DataFrame with at least one of {subject, session, run} columns for each
 window in the BaseConcatDataset to sample examples from. Normally
 obtained with <cite>BaseConcatDataset.get_metadata()</cite>. For instance,
-<cite>metadata.head()</cite> might look like this:</p>
-<blockquote>
-<div><p>i_window_in_trial  i_start_in_trial  i_stop_in_trial  target  subject    session    run</p>
-</div></blockquote>
-<p>0                  0                 0              500      -1        4  session_T  run_0
-1                  1               500             1000      -1        4  session_T  run_0
-2                  2              1000             1500      -1        4  session_T  run_0
-3                  3              1500             2000      -1        4  session_T  run_0
-4                  4              2000             2500      -1        4  session_T  run_0</p>
-</p></li>
+<cite>metadata.head()</cite> might look like this:
++——————-+—————–+—————–+——–+———-+———–+——-+
+| i_window_in_trial | i_start_in_trial| i_stop_in_trial | target | subject  | session   | run   |
++===================+=================+=================+========+==========+===========+=======+
+| 0                 | 0               | 500             | -1     | 4        | session_T | run_0 |
++——————-+—————–+—————–+——–+———-+———–+——-+
+| 1                 | 500             | 1000            | -1     | 4        | session_T | run_0 |
++——————-+—————–+—————–+——–+———-+———–+——-+
+| 2                 | 1000            | 1500            | -1     | 4        | session_T | run_0 |
++——————-+—————–+—————–+——–+———-+———–+——-+
+| 3                 | 1500            | 2000            | -1     | 4        | session_T | run_0 |
++——————-+—————–+—————–+——–+———-+———–+——-+
+| 4                 | 2000            | 2500            | -1     | 4        | session_T | run_0 |
++——————-+—————–+—————–+——–+———-+———–+——-+</p></li>
 <li><p><strong>random_state</strong> (<em>np.RandomState</em><em> | </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a><em> | </em><em>None</em>) – Random state.</p></li>
 </ul>
 </dd>
@@ -652,13 +655,13 @@ <h1>braindecode.samplers.RecordingSampler<a class="headerlink" href="#braindecod
 <p class="rubric">Methods</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.samplers.RecordingSampler.sample_recording">
-<span class="sig-name descname"><span class="pre">sample_recording</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L87-L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.RecordingSampler.sample_recording" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample_recording</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L93-L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.RecordingSampler.sample_recording" title="Link to this definition">#</a></dt>
 <dd><p>Return a random recording index.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="braindecode.samplers.RecordingSampler.sample_window">
-<span class="sig-name descname"><span class="pre">sample_window</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rec_ind</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L92-L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.RecordingSampler.sample_window" title="Link to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample_window</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rec_ind</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L98-L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.RecordingSampler.sample_window" title="Link to this definition">#</a></dt>
 <dd><p>Return a specific window.</p>
 </dd></dl>
 
diff --git a/dev/generated/braindecode.samplers.RelativePositioningSampler.html b/dev/generated/braindecode.samplers.RelativePositioningSampler.html
index e16d6633..7e33e808 100644
--- a/dev/generated/braindecode.samplers.RelativePositioningSampler.html
+++ b/dev/generated/braindecode.samplers.RelativePositioningSampler.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.samplers.SequenceSampler.html b/dev/generated/braindecode.samplers.SequenceSampler.html
index 6ba4adb7..1641f067 100644
--- a/dev/generated/braindecode.samplers.SequenceSampler.html
+++ b/dev/generated/braindecode.samplers.SequenceSampler.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
@@ -603,7 +602,7 @@
 <h1>braindecode.samplers.SequenceSampler<a class="headerlink" href="#braindecode-samplers-sequencesampler" title="Link to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="braindecode.samplers.SequenceSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.samplers.</span></span><span class="sig-name descname"><span class="pre">SequenceSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows_stride</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L108-L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.SequenceSampler" title="Link to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">braindecode.samplers.</span></span><span class="sig-name descname"><span class="pre">SequenceSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_windows_stride</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/braindecode/braindecode//blob/master/braindecode/samplers/base.py#L114-L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#braindecode.samplers.SequenceSampler" title="Link to this definition">#</a></dt>
 <dd><p>Sample sequences of consecutive windows.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters<span class="colon">:</span></dt>
diff --git a/dev/generated/braindecode.training.CroppedLoss.html b/dev/generated/braindecode.training.CroppedLoss.html
index 84f91e0e..54fe36a5 100644
--- a/dev/generated/braindecode.training.CroppedLoss.html
+++ b/dev/generated/braindecode.training.CroppedLoss.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.CroppedTimeSeriesEpochScoring.html b/dev/generated/braindecode.training.CroppedTimeSeriesEpochScoring.html
index 8c3c6918..43fc763c 100644
--- a/dev/generated/braindecode.training.CroppedTimeSeriesEpochScoring.html
+++ b/dev/generated/braindecode.training.CroppedTimeSeriesEpochScoring.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.CroppedTrialEpochScoring.html b/dev/generated/braindecode.training.CroppedTrialEpochScoring.html
index 3d02e8c9..3355adf3 100644
--- a/dev/generated/braindecode.training.CroppedTrialEpochScoring.html
+++ b/dev/generated/braindecode.training.CroppedTrialEpochScoring.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.PostEpochTrainScoring.html b/dev/generated/braindecode.training.PostEpochTrainScoring.html
index aac31055..3ab319d7 100644
--- a/dev/generated/braindecode.training.PostEpochTrainScoring.html
+++ b/dev/generated/braindecode.training.PostEpochTrainScoring.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.TimeSeriesLoss.html b/dev/generated/braindecode.training.TimeSeriesLoss.html
index 60915b18..9bcd756b 100644
--- a/dev/generated/braindecode.training.TimeSeriesLoss.html
+++ b/dev/generated/braindecode.training.TimeSeriesLoss.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.mixup_criterion.html b/dev/generated/braindecode.training.mixup_criterion.html
index f0d77875..4d085966 100644
--- a/dev/generated/braindecode.training.mixup_criterion.html
+++ b/dev/generated/braindecode.training.mixup_criterion.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.predict_trials.html b/dev/generated/braindecode.training.predict_trials.html
index 37ad3ab7..3b0863a3 100644
--- a/dev/generated/braindecode.training.predict_trials.html
+++ b/dev/generated/braindecode.training.predict_trials.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.training.trial_preds_from_window_preds.html b/dev/generated/braindecode.training.trial_preds_from_window_preds.html
index 74d0efaa..5b605d8d 100644
--- a/dev/generated/braindecode.training.trial_preds_from_window_preds.html
+++ b/dev/generated/braindecode.training.trial_preds_from_window_preds.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="current nav bd-sidenav">
diff --git a/dev/generated/braindecode.util.set_random_seeds.html b/dev/generated/braindecode.util.set_random_seeds.html
index 76586154..2f065ba9 100644
--- a/dev/generated/braindecode.util.set_random_seeds.html
+++ b/dev/generated/braindecode.util.set_random_seeds.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.visualization.compute_amplitude_gradients.html b/dev/generated/braindecode.visualization.compute_amplitude_gradients.html
index 56f0f1d8..082cf76b 100644
--- a/dev/generated/braindecode.visualization.compute_amplitude_gradients.html
+++ b/dev/generated/braindecode.visualization.compute_amplitude_gradients.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/generated/braindecode.visualization.plot_confusion_matrix.html b/dev/generated/braindecode.visualization.plot_confusion_matrix.html
index 06299139..51f8cea9 100644
--- a/dev/generated/braindecode.visualization.plot_confusion_matrix.html
+++ b/dev/generated/braindecode.visualization.plot_confusion_matrix.html
@@ -446,7 +446,6 @@
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.SyncNet.html">braindecode.models.SyncNet</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TCN.html">braindecode.models.TCN</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.TIDNet.html">braindecode.models.TIDNet</a></li>
-<li class="toctree-l1"><a class="reference internal" href="braindecode.models.TimeDistributed.html">braindecode.models.TimeDistributed</a></li>
 <li class="toctree-l1"><a class="reference internal" href="braindecode.models.USleep.html">braindecode.models.USleep</a></li>
 </ul>
 <ul class="nav bd-sidenav">
diff --git a/dev/genindex.html b/dev/genindex.html
index ac6191cb..ca67ef31 100644
--- a/dev/genindex.html
+++ b/dev/genindex.html
@@ -698,8 +698,6 @@ <h2 id="F">F</h2>
         <li><a href="generated/braindecode.models.TCN.html#braindecode.models.TCN.forward">(braindecode.models.TCN method)</a>
 </li>
         <li><a href="generated/braindecode.models.TIDNet.html#braindecode.models.TIDNet.forward">(braindecode.models.TIDNet method)</a>
-</li>
-        <li><a href="generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed.forward">(braindecode.models.TimeDistributed method)</a>
 </li>
         <li><a href="generated/braindecode.models.USleep.html#braindecode.models.USleep.forward">(braindecode.models.USleep method)</a>
 </li>
@@ -1066,8 +1064,6 @@ <h2 id="T">T</h2>
       <li><a href="generated/braindecode.models.TIDNet.html#braindecode.models.TIDNet">TIDNet (class in braindecode.models)</a>
 </li>
       <li><a href="generated/braindecode.augmentation.functional.time_reverse.html#braindecode.augmentation.functional.time_reverse">time_reverse() (in module braindecode.augmentation.functional)</a>
-</li>
-      <li><a href="generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed">TimeDistributed (class in braindecode.models)</a>
 </li>
       <li><a href="generated/braindecode.augmentation.TimeReverse.html#braindecode.augmentation.TimeReverse">TimeReverse (class in braindecode.augmentation)</a>
 </li>
diff --git a/dev/install/install_source.html b/dev/install/install_source.html
index 51ac0e25..2e5129a3 100644
--- a/dev/install/install_source.html
+++ b/dev/install/install_source.html
@@ -476,7 +476,7 @@
 <p>If you are only trying to install Braindecode, we recommend using the pip installation <a class="reference external" href="https://braindecode.org/braindecode/install/install_pip.html#install-pip">Installation</a> for details on that.</p>
 </div>
 <section id="clone-the-repository-from-github">
-<span id="system-level"></span><h2>Clone the repository from GitHub<a class="headerlink" href="#clone-the-repository-from-github" title="Link to this heading">#</a></h2>
+<h2>Clone the repository from GitHub<a class="headerlink" href="#clone-the-repository-from-github" title="Link to this heading">#</a></h2>
 <p>The first thing you should do is clone the Braindecode repository to your computer and enter inside the repository.</p>
 <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>git<span class="w"> </span>clone<span class="w"> </span>https://github.com/braindecode/braindecode<span class="w"> </span><span class="o">&amp;&amp;</span><span class="w"> </span><span class="nb">cd</span><span class="w"> </span>braindecode
 </pre></div>
@@ -486,7 +486,7 @@
 <section id="installing-braindecode-from-the-source">
 <h2>Installing Braindecode from the source<a class="headerlink" href="#installing-braindecode-from-the-source" title="Link to this heading">#</a></h2>
 <p>If you want to only install Braindecode from source once and not do any development
-work, then the recommended way to build and install is to use <code class="docutils literal notranslate"><span class="pre">pip</span></code>:</p>
+work, then the recommended way to build and install is to use <code class="docutils literal notranslate"><span class="pre">pip</span></code></p>
 <p>For the latest development version, directly from GitHub:</p>
 <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip<span class="w"> </span>install<span class="w"> </span>-U<span class="w"> </span>https://api.github.com/repos/braindecode/braindecode/zipball/master#egg<span class="o">=</span>braindecode
 </pre></div>
diff --git a/dev/objects.inv b/dev/objects.inv
index 17c04906d6cecc29d12c8b0c47cf4c6b1ff9ef1e..7d1850c5ad4bf1850ec37c19517baa57fd5fad41 100644
GIT binary patch
delta 9226
zcmV+lB=y_5NV!Omet+GPoH(++ucshl_F^Vt)l>gJd$VD;?U{}kd%bSYjO`mjfT&_k
zK`l_-uDLp|abE8{$&mz90VPnTpnE1_V%!DFFTWH*KPi#vBs7RT=Efeg4yS+YWA7L;
zYi!X&aI?$y;dl8J@;8f&oJ-jodfe_=l+i4Rqnj7`59Yn18GrpHrXEWKm>beGwI<e<
zMJ%EG_Kz5ZTz#kBmo)OyEIzym!VImlE{xW8vt^lGy>B0ALieexMV9Si?|Ep%2cd!A
zcyh(JI~qkSOkXAOAwFiv>TXEm^$k_w{fQV?xw-25-O=|$W?1KiG+y7(b#6|icbyxk
zKJB@p<YZdug@3q##=)z-2bKO6k5C@(4{?fa<+&6b|HhA#N1AwOi@=KBe7rv<NxbEF
zNMkCJI6XtP8FK>0Ed{AEVgEg{$UWWf0v|gH)rHa82CL+rG|a0StN15+Ow)iy@8SUc
zV%B7_x`wLiek6=58msos<9`O(>0?5pl=n}2WL;m$n}6suH`he{Tbh1-9r5cyv_)E5
z6-8<qs$KP=U|h{urNOu30b8{~28umcWulatS07N#J-ht)!0$(CmK@zuBcd|ffqJnR
zs@k85p78_fNhnI=B>fO))aX&wr1AQOdnkR0^r(JA)t~xR`X{``&;2xh#%ui2PvaMi
z#$X%034a4@*IkMsH1udI2xa>?&UPPzJrm;>)~K2=TH9c6WltLB^^8?4ihf`ZEJ4rL
zE0Q=p=GGxq8cvQev(ighLob1uvVoc@M!7?IrFXjSNk88`YQI27^vX9x@ID)@<4H%N
zW0gkwtdkJSLLEh8YEVibD*iE&(>5A%R{1`I?SG$lY0A5>Hr<W|Xyg@Pw{S?>-em*B
zm`M}NkP7cN_s85x*q=%PW=JKyY%%nwl7hYM6=}b8PI2+VwP(zvfrTWJ*=f~(YtEtq
zgrl%6{6}_FI^K*))S+-Rf};QFMW6)1sowMHj?F6mA!GeDBqWK_gJP~6=yRxuq?J{$
zoqt^UAB?GV;9?2NC5@d_Rzy8m)xnTd_%g)yi?xzDhY|&;T+Yqyj89_ieX+DL=g<Jd
zQITTFW!i5{qY4C|kd?E6wDmLwF+Pp}J@^6R*Lr?|m~Y;L4@=-EUTyai^Sy5H*#acR
ztKD(ZV_O)$84qKr+<+x!yOE$>ULdWOy?;w$ym<%RCWY~9+3h2yTVB9zMHo5tei1R;
zIDu_T0h!hJSqOGBLbHJbBLUg8AcJ_}P4-QoHnh0#iMjt8ykCH#_^BtyPdJjF%vgTz
z$?`Lf<!3XNUwX3qf@Apw%ks(_PYgWddS^e7O^Y*~7<-eUetQ@{rTdwfIfFqy?teNh
zsW0#YK81Y!`ls9TFTKaOO;SAxZY^!QNx<i%0Tmi)mL-8B96V30H9w}EKCjaFz*h^w
zAN(;qt6rCep+nuTsr|fa#h>iCmFBI9FW8?~?a`yQ#||tKz8m|j_nEC1yCTAVn#BoV
zD`Y^eVVtJVr!k0vETAEOmAvPz;D5Z^cwU`{gn5CRJzwn>3hhG@JM{V0@@l1F`mB2W
z;M)_usvgZ~%Chw4<?Wr=HDg&IM&!HSUgbCD`hivpVW|1WiyxyfrjQ-m-W=ZD-c84o
z`FK3R7<`e^;q!lP<H)61K?tLzDT~!5J3wB6R1`r~W^c_YePGY5k=yFAlz)%22jBsQ
zA(bD(AbV<+W-SPf-?t`V3V;6T6~Yi+T7&oYUoT$1#Me+&Orzo5+m8rfURr~9A2N1$
zzdNP8j!~TJf*LI!fBhK&%}eX?UN{k7A<__sTS{s0f9IFt#}xl0>w+jPeOf$9tvuM#
zF(eSvegio6=x7-df>D8xXn%Y9#OOId8dw_}H*ooM0x&xwJ*OtPNm&bBH(^}A?I-cx
z{$#^;`P+mwZMa%`A2FL9Vt1FCYrJ3}6({tupH>c_QMr$)<EZC|1V2gCPCz?Z)CNof
zA2C};-%f4n;glGRr~1*lg-Eo|>SHc}54x=bc#E!745{|vJf^md&40vbaE1*3EyS|p
zu0Dhl_!!<gAL!O~J-ieA_^zEhTyr>PL3ksUeYPtHE!(>^KhR6w2GIVJO9`=5>7`Nu
zpjNr({|nQb7awomL8dmf;s8X%L1zSXmWe}OaU_Ot6zzr}N{fLh7<Di2{`C=Th$yT@
z!xPrR@~K;v(BD6RiGP*?AXGeI9DEih?#@m#KO0!XE8cC+F%7X4(4xv78H-#Bfzk05
z4^|`GesLtW?;!hR3L!8$-Uu@_!hz+xb{hP_o<`N(N6Z5+1+=J<%j8P(^@sN;@QNH*
z$J;w26>skl8jPMdLe*QjeepK<7DO0hDq;u?M#dPb5)C*$W`BocW~V!PV9%vfcE16C
z33wMwvmng^H+>G>a{47yG8?!z)LUg`$NZ^P$#1z>R_v2MwYDs_Jr<?RE;gXV=CLgK
zRLbA6Pnfrl7Y87UU4GX-P_I1h2WAe$H+h>u(AmQTR~=jcf;z{d&UL6CSc)9RatR&o
zeXu`-!iV^P!GFF;!SRirB3uz}#Z?M`P>q=D;eS3kN#J2vpCw?pc-}AtzfgX04`!Vg
z2O!?~!8co+udp9ku-#=gjlBFf+dB-|yCAe;YY7c)`;2DC1T%ucb%?ouTRS}W6dI!A
z-VW&rH7>$6@Tz$_EAHRF_<-shN&yfmzWKo5cQg#+$A333Z|~ouxYy;nb%+(`eMYw|
zc^T5kji=-37_Lbrjn`*Te|;3+?&#i$qv?3EHnFrKZlJN3tp=)Jhx`iT)iW`%^&*Ye
z*UM6<;#1_JUX8pw1k->%0Gv+=z+`z@9TuLX7WD2Frb6@L07L_(dgxzeivg3(ivtkx
zWC74LbAQENQFC8_AiVeO+YBul3vapDb(gwZ-TcJJ@ebKZP%@Lp0NOl4#9+CrcQ~ne
z1aa2bCm>*te%qFVQj;sa-j9jG;ZINw^R7JvrDjif#uW~Ag7T<$`RH5K$_-c1@YIfX
zf_91PeELczjBVYsr&#ShCunE0&N1J{Bq-gbHh)VF?OtSJ;zkCzsr9t>L95@H7<hyA
zZtYe|nP@rJ-g|;_-*;^Yv}rE%Hhe<_<s9mAHv#m{(R$}Pz4H#e->w{k1mRw5_cOL>
z<cqz+*rrp9;JjL$p0YOWsq`qh!lTsU{vvp{l-9S_#wMQ@T)VFb%E8p-5mRd3Nk5Ou
z1Aj$u9->aSmQr<?FW8$tB!XDyx4Wd28q<79Z2OLz9@-by#AIa+Sh=e?$<s)wT<+M8
zT*caQ8LL^76Z5q(*a4s??B+{RTdqZQi)+$ji3?xL>q#@Ys<h>@QnN-T=4(~(f?Q4b
zKoi*`T>GpD%B$4n22*S1>sP6`xu_<Xg@13yDqX3ScYpO&F@dgNTb9>qErBOYYp!ky
zVh!59SXOF0%9eMvL?wuYWc!M@uJMqtLlV0zO+~zn+av}oiLYhUi`RNN5g(_F@q*P+
zm4)bnrioHXLGa%P?pG|jkO5(zf5m7Es<K#JH}r4_PXM<?Kb3rbMa8@ZYg#D>(SLEz
zGC7m;S;F{g0jsJZ4$)Yi91p%R&kk9%&35)<{v846s3;f>L8g$%kF&D}7G*uSD8Njq
zWHgbRPL;l308R~52s!rc5J$q}L_>QYKk!So$M%dy29#Q{42kerN957OE6%m`XHx-$
zP|CxuIyCxfp#CBZQ6;{#xLj$BL4O202x$g41QGRsMNCI5;K+y|2oAs3KFn!{Pz0U&
zph&QzqGq&35V;;=h{+fO7{d^xTE`^PV^D$*fn7{5zYN~>iiv=Cz1m!q^BiJ2>i|xu
z>f{pXP7)ZhvWg%2`GQ(bT>&j+k<o*O(1?m0G=xHI)Sv-$Vj~6(p%NLmXMYHlJ%jcP
zK*0xvGZ;V-GBVHr8u2lD22hHM&oh8NY^a<8Rf5Ch45JehA_t=}p93V~+jZgnWZr!q
zhn3yuH}u1Z4#7-sQ6N7L2dL$qEJXOvL>#Wfo81&eYPu1hFTkGbU@G%)>he<h%&LpW
zde)D5v;*nRSKLpkIHXzdz<=JysSIpj*sR(>jJ1n?<g%!M8*fO&yeGlEyUo&k;m+*9
z!?x^xN)6s(oWde{iKde#{rX4L$k0W!y+0*}ZyT)J?&8#=(%_W^tfVvzLEQxD{d!`1
zs5;?H{9XE;4$S+dh%?#!BCDj-&0AR#e)!N_kqF6q&lfx_eJ!H0+<)_S1j_3R!|B7}
zMjVY2ziqxSGN^-IjKrk2XN5E&3^j{taA;;;4FmG%^*E3`_$!&o;vdBo{9{nco9Hw)
z+=RiU(IR`8x*$r6Nk4;9CxY^_RNZwFe3z!}m%C}SRWUI#8uAod_{bDf_SxYCa@V#A
zYo5UMVjZrjE~`<L7JscAIJ%G_I&*{J4amNI6d*mjJ>1}<p{waCNuQny(KolSl<h`-
z)Lv}v=IhS<3a%-3LaAG39<qsLc0zg4y`3_sR;8p`$wQDHg^MxIav&lJ@`aBrCXzvR
z^q9R(s26~@?7?UdGKVnEM6@dZn94)ll-J=m0~$)43julvtba7~{^7;0Xm9+dyl1_5
ze`lTdtwbq1IqzbL@*#CtSe5vW|3NNg8uHalyQNA6M5P!J#a>h{aF8sv**7`OPk*G|
zgIv_vWh47hRKT~IF%W^m+~TGcv139*{!jK8Ctt0yEQb{pz2*IpmWQly5tz~r9_+cz
zAIg^Z_p*n;uz%}-$vMB_rNpL=AF^+vJ(N0RGZ38lH4&iFy8F$VTd!~9pR6L3AIt<1
zBdwMr8O{C*Atx?a)E;e>>6G?l$=`RHxV!#j3!t3yz5H9$YPMsR!_v%>(YonCW+cUe
z);?TTv}hAlASM0KC+YFP65c!THWG4kqN0twe*Kg67=L6ts}#2?;#&6UmfvOWQP!A9
zW|(4VUrXnFZ)NA1*Q&hS<Z<AgDhE1W(7pW1^2NKK-?PelqD~S<L&AH2(6h?0h&l$U
z_f?L22v)5a>Ng($rYjX*PFRa0N^a#qHj;TOP|*nG$=Bkx;4EIH{Ng3RW*OS?C{7Jn
z)zjfcpMPv%61$w(?qw0HpA$DR=yG`6z>fSxaz7i2Q_ZIQe<k^S%)`izd<o8YgNT#E
zF~!oaOXtMj7YAji<pkTjBNn|_!qWJd@Y%=rB7Ca2aw~;?(9uM7VtQd%A69lOb`byQ
z@M+R+Pm`~9NdGw5On&Sjf^>Bb15kvV&&#rez<-qYEj~fEL~*Mq*uhZK!Cn>3b^cPA
zAQZ*PmPWxJ;-@Ixp)2nO&j!^F62T~RAt-92u0allB8FHPvT`0REl9;lq4J83zk5tG
zzWOMxmjw~@)c{4?lK0A9-g=$i(^1N!zKJln<t+rAYvIcy&TB{H5-EEN24f_S=b6`#
zLVr5v^!D9rY~9Fs+I_gF<O?<;iZ+&yOjU9YbPVTFlPkJ;ne_yzUv#@(kh%%uYuNoU
z%!2%EH-btVL{Tf^f~e!Nh?U<>^Y>2-MfG01gE6N6?v{gf-I~s@(g7B=-2{*y1KG|o
z2tB~kRaLs^#b_G1RvvAzyf0tIa)#ZlH-GOY1;%+wUM32Fl4*x18lU`r_Og)XH7efD
zya<F{F&m!J;uX^_r7<YQ<1QdyDdy9y3ptP)%>n?9QGMJmMP1g&ikIZo^_Z%H-^Gvl
zgR(Qeh?UXVvSY+>99uwgl0V0fRu<<^{O^`1khe&o<;3S_d2{_IgzJefSkJ*cg?|ds
zx<vP2r*7~y$cS9WBDupr3tMW1t-NsFK~)O_Y$?vPb-Gcy<;t!pdWb{WV@W?%&0SSd
zlJ^Px51)R`hvgdp%lx78{|?85*@sge9$Y-%^6yXt_3QRd^aRfB{8)AvG;i;@bF(mu
zH~;sik3y{5Cd{~?6@?8A7?p4x;(vpxElcgOy|5>B@9E=?^1&=(MUs@FBpH(hzxf+W
zWNR4TEN&*&_hQ{i#w#+J|4@Nk+G8N(l8h^m%K~sRCF5lka0LcjalqSSlCUV_fGg|!
z$(V4=X%%e^MqAg=)*Nk8q6Jy4ixa<Vy_GCbX=oRTv)Z%FcYkY_Dzta;{eN49<Hq{l
zV-MpWMn3&-U1-O`^9Q|e5_u>m3s2UI^eZ2z{(a=VDt`#6_5GU{|NdbFNcLR#TbU=u
z2{C8q-C3nV%n<S_#7ID>zU18kU)~&wkDqWX>%tm>^}-Nt<riY&Yq9v4A;~qQHS8Lt
zG4$?tN8hinU+~gEdPQjzy?@i552(q>lwTnZC0G;(G2~ruoT4i(m(uacOF?M7`FPL!
zh<HmgER~9+hEAm<h*I7Oxu^SG;A0zpU06q~Rv5zVCwk<w9vZ!i1N5`2$!eI@%0h_U
zi7$hK?8Ij?Q7Qt9A<13IYY1MIhmd?r)32|iVl{!|R~6Mzs}=>Z5`PC}uyllsj)y1%
zA#l$wKg2oRD9w_i+uR841*D<cE(qfvrE!veh_82V@zPqRwbBTBpZf9pgd_OLfZ^wU
z3_s%-el}qEr60pDIEG(P41;a-CJeAIaw(=`R1^a-*~f9V6X(iAPlV-D6V|b+6^3vV
zWk0Y7zOurOUKL3VtA9#K5GBJA3p!GvMyT@46Af>iV#;p&CaZ&XAPwDiK_ve&G>YvR
ztspv(;1)C`O-(qkWPe1@P&<$eOeiExO-PLvN*zcBCZzBMR7Kn`XUSY1KOt`if*a5f
z#PZMV)NqZ{f`VXPkwVhm7E1s-GFWT0;=rlb<&flqVtHUryMIK06D}o?RQG)7w3*qe
zqzwj6x+aEYZm@7^iX)gpmopWaw6d;{UosmnZD62qYdS#CHp<DWotRCHJCHEe)FrVd
z@Y${H<0sE52n6X;1j|;=dgV5Ty~oe6JCG3E8<I#9q+DV&4{t$%Q?E+3(7vQrl9B2!
ziI%if+a#~)wSScyX)=q8?echkV3|BPeD_<iXFk_+(?VR6)QV`?zPr7fjwkc+c!D8#
zk?P`fDW#>s|GAY3$zNTc^TEn?QEHZj5Hq6$BLk%I^G~l3>Urr7wfwG5ojj+7H@hm<
zL7-Yp$K>7Hj|c+1bcbGkSEo)M>Ajrzg=?-0c95tS)PM02=f2=1c<Bz!{4PM<3nz+`
zef_8oT&i1rSxQIa_dJj)z5&(+JIK@v>iCrLZ^id|pX?KYP(!kVQKKY=k~sW%eOAo~
z07&p6faRIc#~viPG=d>7-9b-&94U|Tx^h5JoiN2qtLe3s*3pxPjE(6jq&w&-N{;~9
zy!3polYf6%t+z+0%w2HZs+3<Apx{WGKMTy^oNUW#xj6!5&I0SJrP{JO3XDLhv%q?5
zxwfp10wZw3ER^nAmMu$DXar7`1?F&-U(3=I8i7(kVf0^eMp+#NMwqNzDD};3UY5Sx
z2$7A;h)a>g%hDDbArkgsm^AbJS=wSFK-MY@gMTu~mDPHC1j-7A(^;kwvpNcZ^v<z*
z=Q_Rf5iCC!MsX#hm(^8b1W(F^QQt`AW$8+dKzX?^47!K;vcL$ImJ6)7p2*AUDlr0N
z<^t=jB=WLaZ;wE!j=(x=xsj}n0wYWYFt~a}<}gcNZiLVD1*g=SC(MGD9vNiyGU3-u
z3V&vSi;wV0yi5o-Qh-^|(j!P-EjXb{9xki>{z#Wz3#_nA#bv4QjR3i|;JPlUxUAOO
zBS3B~u*OO%F01wS2%6bMueK!{iq&0agw14vC32Mo#e$U`!Sk44DYc!>SCtw;GnimW
zoU@)--DO7DTo`B~%{&?wtn3JrP6bP<mVbuD(w7?<<WIqJQl($9z{N*BvwmUO>Jo@q
zMxvvB`N9m1Xv;iinMjTXN-s8qEvk%VRxgNAuS{iFo4Qk;Sq6fm{<+NtFrt|$%`%l9
z;c}&6sW-B$S&)(=TuLV_rA9I+3sQ1~$;6>2)RDo%(w7^Vg@D)70tJz`FcKqVEPr?e
zM`aj!3siJu9CIDTuQPDFg%ld$Lf9jS!XGm1;VNSnYw5JcMYeRMMtwr<;)!*H?6vT6
zBg1gJ2E3IKdo7g6$Ryw{f@*ufUJG7+gbH_!V5f+aZ2=07a3QY|gjB(@El9}`DmFHP
zks_$J1t>V`6CfEuPakO6!pn^iaetQeT-(DlTiRlyo`IM3>~JxhEhEv9aolDs|MuX|
z7E(xXzC@`yN2w^U=9qWl&yk2+Q6+kgWTB5^aTN!v8tSSN1?J~?&kl6UxB#E&hvARK
zzje{tt&*Yqk)OtHl&}x=lh%scH4xGBi+9C(e|mp+1y)3&?7+)Qs3G%v>3^t6?OgF~
z<i0B|5Fyb;v`VlQwL<X>T*zq{U(VdOftSHeYL8?uKDfAQWrq_fZxpfP<aTk<-YR!B
zV((AcPQ)LpN+;v#gwo||z1b{0GP!ErCNVQ)Wc6e`U#{k}6`jt<Yr>a(4?!sR48{;0
zsO)9Qc;Pa4Gnp+MXJ%l7@_$R^0+}w>bnQ<zbC((*H=|LMpuX!d-}795Yyf&4u|WYl
zeHz%=aIpSnz46&<&L*DGGwTd0kn5OE*KEBIXVK@bfezhAFolw}vzV@_OE-&|h%wGV
z>DTFavV!PqJHk{zGuLxgGjB<q4UGTwu{#CQv=7p3<<3{ji8p7PDSrw{bw)@5=`fas
z!^5VOKh-_u^E_x5q{pZ0*~}aB8g*CwTG!>9HwE%^P-JgCo%oZ*#vL!ofp@SWdpPeI
zL;GZHiq?d8`O~rIFX()_=`pBO<3ts}^Z9bj=$I|n)V!zvr0D7A-h}$I&6rMBjHK=^
zNRmAZQof!-zRUGPDSrhxo4T{vYVA3bwE=BKP%j1UbVyu(#v37}llgR5z7^a7`7Wls
zYjfALiMN~+{+4G!#9Q?Y)6c063%7#HS@=NUbiQ1yecz`&JCUnT!3za*&-a%Tx}gi;
ztEkV_RR^681-e{L7QEl{+~tg%#FuvwLq5gpvvA$e$miG!zkj9+ww|n~{+Oc1>B<R>
z0%^0^cysD6sk`hm8?Q!)E0FmFfNho&J`0!=AsM*59uB+~76`)C6FLgqFhF*e*LchE
zl1-P+Z0)n9<cVwo=M(n|xD$=Gec}AI$H!0KTaO82+eqON03F9|g~K<=2IOSS`&iEz
zZ(N6b<?TU40Dpx5UVTqj;7u3KoQ@~H<F9&+i}ho&1^CRJEymONV(l{2i_?B|O#wW8
zD&R(9m4P(yUUj`*F8RX9WbX8~G2^SjP5Z++-g3Rz(1}mi<`Xc*{A<Z(yo+`h3%=Cs
zHxMd9izrk~pI*i6NmQ)XY(<w#cjYa862^RL!C%D1(|;_WS3X;;CjNXm9gq1EDx~`W
z+MTFAOvypld^yf%fRs^hGobsU20MKk*x7)veA+kT0~4Q=z$yWi*DzUcCcLX!FzPHR
zY38&-cT~;u%Y_bSGUZLtnS1m306kR=u76Lp_Qw9wT}<7DL;H0os!(YP9n+`M!TVaa
z@ZI&&Gk@=KzbLxg&4f?>HXG(mXC`jbtKg>v>U=h(lMP=UOeei24608K3Kc6lo6Ok8
zn|iZBeb$=|AKWL7yYv^!er-k>oi0~GXWrOhQ*SldID<Mz=xV|{71vp=HY<~<bM50%
z1!OUOp7e!um+oZlZ5*TSU+q$-bT->e*UQOfzJDR2L2{n+p;|O$>m~0=*@8~ku!}O@
z{ks#oa`@aD_-@0(#gyob@t0)7m!_0B^$%>&LqOvbn?eI${rT>a(Yeov!-DJqGdHMw
zMx}r&8t{BD!2bjk-Y!}Z*Npf0(-nVk{oI7LFQyA@htY-WFXxMm$-a;xNUH*OIv}pM
zT7S=0Y`XGRe!hCm=Gdic`N3v^=uf@nYB^gk*5jTVHmV?63MJDgQsVNSXufvnYE64@
zJ#`0`EA;VY`pjF?8J&*_@4n*DPg5~t!)|so_j}yglJV!v7XkhPwM18Zhg~3Urjv>1
zIn(K4HP9fNUXA3g!)6|xE*Dd8UbIbo(|@ck%XvrQGuN3+ctsDyx*GMhP~y9EN%{J2
zIvo>-2FMwE`8it-=J93Ql1=B{bTJ)tsqQV^vCn*Wwh(KJGNJ+AaaE6)pupx0c#B_e
zDq-FE+IM`)VVxnn)*9}BT`QY!mYb!waHea=d_L0|2((bNntL8!j84|>hGc<<dw)+V
z-!$fM{+jXS#MocEbZRmMt$pRJfc#H@_TXMaRx+fYA+D31TkpjQtL}VO@C;VzVfW46
zhKXHEfn{H%1h2Ew<qy9c?)gqAAY1_vGNhCtr3^VMcu`zwCQqv{5Oui?5Ug!g=I%1b
z;NgTbstXHcDiKITAd%pK@L_->k$(b-a8}KH;$><@KwfcN#fV9}U3)W)>f{>6pgIHy
zse*`_5N25~Di>Q)K=w4-F5a?XthX!gZ0}0Qu|!?uZ@+l_A_uD@@;Ay1+jQvaNs6Ow
z_Th52&8%vaNCwqX;*bhXUL~O~jyAF6AxQZPB9lH=a&O9nkfpFy5r)@DOMgELu7{SM
z7+wMCmYe}dP5|DEH*%tPQg7x@2lU~&$oYcxBEMjrFK~hhqaooPdFYi%sKIoVy?35=
zRnr`m8S9lm82gm{wuDjj+C6$}Wj&<A=OMnJ+=_Ntah)4gMmrk5MkE#~u&Pdd`HmK$
zA>>U_7ozvdFJ3~Mmf-}CGJnx~HK<833+Pi-m)+0-YKk?sMtfA$1<J6VD&bCgRL@cV
z9H43npuW|T!x&b{uOz>3)NDjzbiO3FU76S1s74wP_`2W#!Yx2@08tC?i?5BT<pkS&
z$QNT<!ip3B-`CTz{{XfbIkYwH#g1%EbNdWzm1OZ<oU1wI^}|_NntyOmkrlPf*&Zib
z8U=rdpP~qWlkM;o?QTz#uXafPIN3}%s_ihx)U>NA=S~=)DdY@71PGBJqyQ1^>t%Ug
z7%1;bt3_d}C<ZY(A7amh8y~cTP40w&nw*c*XS-`4S0>l)=2J$ISv(9`xv4GdBV}Ts
zFRp+q#66~2yf3ep1%I*i(Sm}ijvS-BUKSL!aVzhXlM?H7eg|x#j3g}M^`7^Dkme~6
zP^JlaBIGZ(I0Nwt=TDB`IS&&IX`Kk&-1F(FAW-&k0M&DQ`|h>zL)*vHae5o31i_gm
zAe6?5u>8j6rQ+kxbC_wQS#@EQIa2g&j+nxT3&v)M*@PFQZhyiuX77(-7UVH)uokuA
zpo|k!lM;ngP~_thKSeaFvVfJ}OY;s@Ox)_z6i6N5CMZ>_k#m!(sePs;(z9zj#~}1H
zF4KBRz~n><kTdj4ng*^VFIwk|qO&Xg1~7`ns4c)QE{`Jkes>#d7|?+Ox2hPo1<J+$
zk)z0WNgi>(_<w`NC!@RzEJFWd>@6GtQ(AOkFpsd(<Tfa@)rD7KN{c?R;twvOVpy*f
z9tFLZ4^#sXuL{V1y;lWf{n@LMH+1=tdCh*&lf3GfjjOEQ#gBRGv@@1wHh*1s&loWS
zv)hocc5|G(r4xZeI1Ujw!tkHtM=Oi-*8X=(+|J)`et+9K@s(fx^8XWM|LMRIF}L0G
z4muHx#Vyf6+o>CT<s+ALpqkVN5E)%RHC&S85`jyqxU#-#MXkJOKKfLPV(P1if~DUV
zQB_Gr7;E)KRKERj^bm)~e8050Id&;p3<mrUpMK5fyEhnP^XAO|I~)^cA5K}ExI5Xh
z%fG{5yMN07n*plYz@THRD}RCbe*&8nc=BB;|2|`j`utdqAG8*`BCkH)%e+5*6hgqd
z!_83|RfC+SG>q>vQ^C<j^28DI;>Sp?0RNhMxh1{6o4Ul*;%C~V#o4LctsTz9=h%?#
zYw%@f*4XZ6-D$<y+qUHju=P*h#cQ(^wVh{b=zpKHO@}hMbH8pFyPs#zt%ue1&9`BU
ze%hV19>!j_)JzS1>a8)9ao2lfdb9rA-I*5iFxxaZ6Q6%K24JFYTgJe|XWU<b8rZ(k
zVqo7hY_34<Qtz@D*z_!0Dp0Fh_Et>Hdaf-MuxV|3D+b0r*@g<#n5&%?10$Y!I|XW5
z*MGi>-pW7Qq2FR9%Cm21<+Ho-F}8O2^9M5bNqzQxOhv4r{t9k-gsC0=dP7_PVlH`1
zUBG?wW_9y4?stTRbw9kB5r0*;I-(ko{`E>d>AcKZzcR>^{J5ihaE@3lm;3o*{^8T_
g{OAAu&;O<tztRvmv#E=GCw~%AswVvZrvq}$Mx&E82><{9

delta 9226
zcmV+lB=y_5NV!Omet%n&oH(+6=T{Ih`!Ex+>Z$u>UpDNvJ>!VA*X#D~*nS~YAi7vn
zPzzMIYo5;EIDhZ_lA{Y$L6tz6g6`RfiE$Swzx+}NT~Z=*lhG&%n4bpB-5>w5OM^qq
z+>uN7(apBl#XqPk<WDYfHs`W8^l-mpNkNM!O>SPOA1ru93xE2zlm;vlV17*V+#S33
zEMXbtw|~YUDD|CsU(zJVi*)}ciVL*LrZ8ID%{?o;`h9OtGrG%VEwW;p2G2ty-3tx;
z#*-_)-O?msasDbx_vxWPR`-Q8Uf)m^-k*qdmD{Vn+aAI&W|nncO5^nnUFY^hde^yy
z>f??p%8s^`UVn;PXdJxSdr;|L@d)MVZlC7pR<5Mr_%~siJ<=>dTLf10=F{CF%hG#}
zhcu=piPJMwo3STg-BOS$GxnbYOZ?;AHVUz$P*WJKZLmu2NyEOXv5J48hdhsH@;;5w
zFJ?m)t81vL?nlD9qOoe<2K>*cIDX1#lJov)hpg)>d4C(7_U78Ce@F9guM>VfO74-?
z)<uz;hH6)RC|FlBR%!J8u*X)dkbz<kR+%WJ_SFYebH~m<KJxoXUStQq(uk<ccA#D?
zhN||bqG$bpdJ;<VG|NAx1+{uq4Qaf-;T}p~B0Z|#QuXJ4mHrv8@k>9AU+@~g_S5(k
zqcOTq-hadqw(G9M5E^>46@;=~niktn(T<7n3u{zE7_Duvx3VV<`+CMI7DYd@2bQ7d
z>orN79((JMDlI3+m|5w$tfiO0PT4@s6r+4Yd8K!{?nyu2J!-$eMD)rxMDRWvqvOd$
zqGOdt`mB=>%R&=HYidwRAS&S@k<&IBb5?4f!G8-+yEN5ZSetIg0yOfPuwObPz2Llo
zVa?<c%#sT4H+Ki+B<xS61hb@)pSKwLQ^~>J_L_89Ij6XI>Dseqa)E^;Qh0gYe{0X8
z285$<U;2-{q;kAjlW0QWXhdcI(~Cd_f>XWY(;bi1{6p6I8%RhJl?TOMInd`&6Ul3<
zV1F;W@;_Kp>A=MjluH^ftF4H7uxf%Ksqkfp7nW-!dkz%}Qn{R)dj+4wdb@IIW6$9N
z3`a$ZW#?(XHH|tDfI?Bt2J+U^7{vNG0`%Yqj9=^d1!BK>4?Zk`qj<I5Pwe-)!DkDQ
z6t8y2Nsnz|_+~terFH|B*zHDwc6oucT7UK~iS_0kbej~$uVuH7*lu|Nw-sUJ^!r7`
za^nQHEd^xO+-D)!%?QH=4vYk3(}E1*g}2!^f!fgG!YB6rYw&&nisI*<96#eoezs%z
zr6<cTIF?`RSbpuv@+*$zS1ijbZ#=Q^kei+TKsGJTbYksIhWhPc{Iu?8V&@D7`G2^Z
zw4}Z$jQAAt_3K}5Pru9_<2FhCB)GM-=VuY0lSWi%q(zZM8{y!2YOU&+cK*Cd(>-4;
zM8EUL@T_`$8pj*zf6Kk+RV)5v&#hFoCca>QUbTmSdI8(BMEGvJlip{xUhIkp`)QG8
zfUS@LwZ>_lKcB`ZiHeBE{8b8`w||0FxAD9>_ZbT!zj(gdEfsqEEZxxOSIeuF#`&}A
z4WsW*^r{B5pgAk@o0qq5#jY7EA~7Pr{nsmXV`d&`jS!ZaZ-VqOiBk&MvF**_{q5Vy
zXgnK@#u$UoQYL)<&uyCcv?vK-v|P$!b;%BpS0EKdP?gzRb50-FGi&6w27fH)<Ln-I
zfMH1G`#36|TBThJLgV+XNtnW4e|d#4gqJqpz5Dx%moM=(R2MU7c>nGb0+^RJ;N8WH
z?LTafIj>_B=cb@R%cp<-ih$;&&3G?1311=77>8R)8SsDOm(s@^|0J7&C@p<jJW8!R
z*wHa05ZitOIQE!mSrUR#fq#%_d-}xcIY1g%8yi3J`E&v>J0d-&Cb&si3tc~BT)!7)
z>CXG?!FKuEgbi)DUV4`>kL^=`o7-zVV;~i0^s%2-4q#BZOX+5#pCc0dB+)nl?PSpy
zFbRCbY#n_&wdsdbVlkeYN9z_M$*yRQxdcAwwhrJex^gk3di&Fu+J81S6RW`)GW@p?
zD-PS{5KiD@c<X$iTi5mQPVnQqaqe)<;ZQ{Jjac@1z8ti?;N1K`FL@h4`%5k*#8Rb~
zN)3Qs<&OU^&Tn3Px_u9s+BAv-5D^ER5zs{;4t=GG7{XDsF9cCqEKI?ud-?Y7pTLHQ
z!bUVaVIwS`x)mAy?SCVfXe9tb#S_NC7is2iy}SsEfi=A1-R2C_5Gw&As_c=m$dwQn
z9bfTaHNx$eCSv;zvQMTF0;A)Nuu~%(SfTIb(eLbORK5L#dEk|R5jF9dTuHwE_yGl8
zlLPB`_tr|qySE4pR?i!u>Yd!aco%(-5{xl5F@y#yV=PsP27jC$iv6MR@-5x7=h7*=
z--y2iybGp9loyeoKZkBP{Sqpf2izO#t+KXb{?w}Ew_L0!_sO4HTakJJOLFFw8&G2N
zSeAS$<?q>N%-hF{0}#b7zwhm7P#yOJGY8_^yv-o!;$e)d4lV#eoncXDCe)8CM-F33
z!i0Ml?e?+oA%8w#u+LI(e5<DjSA<(}RRSPXE9PeSUyqwC3NWls5-?mmZ<vC=QGRg;
zX03_?5O2chyC=?9c#kZ)-xeNC0`;5iHVoOjAhcp@2@UOqj24FsGlIc&h`E5@I6U_h
z8j{1#i|G+HF2XhNs(Csq?moQui0T|F0T3#_`M}_}G=GlM$2Tu;?>?ZoH|4r@h!y8u
zLGM}iGNy^2PDYavT$4^3ug{|X`Y68L(%mLaCZqAn#?qR&g~ndCTBv><^DB&3&)CM+
zvou~`FH50{kBN_ZHB@;BrUiWfIG+-L$?~!$EIdgg=-XGA3RT4ch!#u%(9w>);>%uj
zW-frUZhy*QbXeGdQ1(yx3V`iU#Q}(T)&OW)_+s<xa-)MFwj<j2O<FXT?tgKNK<aMY
zw;)zK36QN3Ei-wpq0PlbEY|O451O7wlol5o9|XKb(YA-8)#OVz{$r-u!62v|fUZpu
zt>!?u`ZYTQ1hqxbwdv5RR_-8+hNs_2AZQ=IX@8SK%Y?Ce|K$4CZwC;x_uRD8(8eUH
z{J$Q{_U&$QV&fMF_}$I4c2TP%omjZH&3^h;N`+`S*V_>UwI9*7!_lU>)O+FVA}DWH
zm;Vf)cZSwGGwGdm=>2}>=_Ck$VY}nBO(S2umd0Ls=?KnE*XjCe)1FHgnJ-*qE&e=$
z_kXh)orP^|)U@E*A4gCgvo05(R`XUmu5>Onf^&Iw`suW)W95Okbczv#<D%Wirqx((
zhqTXtiOsAOFvZrg$(6^!3pakgZ}(de8^;B}F{0-r4}0ZuHR)}nlfaW+0)xwg*t;IU
z{uMJ}U#;{#xzsoLE=Ug#0^C(%Ce7rc-G7s-c7qFo*t-J2{ti9iJ<VkQbnOx(D5qVQ
zmr<|zm?*`UJ_~~JD|9$Pv|4#*+;ln+sDq%zd!g471;VsT=K(=1@!Ne7T8#(U@~#%l
z1hK4bUw=0>?lZQ}QlI6y2uE_8rGN$cwTyl#-7F`<4^<&_usZ6p5M9tLTskQT{(pza
z|As{uG9c{JuM}-TT^6hBhVJ+A5#U7Wr;^Y1sF-D8O{?S}I__8@=anJL7+<?!Rb7Zf
zG*$=mqwg&6VwT(&TklbQrU5#M3r0hbDJ9g`0_=e$MGr0-Fk31G&E%e5tuGjW(*-Jo
z9Q(dc6XE}&vA0Vf_$4o3J4O==N`I|bmPGihBME30l*b19v#9|>D5<En8=8ExP=6MN
zs1hHtoUdGrK?FMp83s255&eKgY)35M$cP{aj&9gK%o&GJ1fAxfNU)=#VYEdMxgKJO
z%@_k1!w{re$0X8YP=XJET};ovEZ+5+iGX*#-dwcv9AZ1`08Xfy<TB~p5`P%7vdSOk
z`GQ_fUjZ#;k-?dU(1;4mG=xHIP^JNNVgoV_p%NJvX$X})V<HVeAp}K>7(fv+@X`Pp
z@ga}~P>KqFG=M&AB%%RTf};=(qZ1Q>2%}NW0WuL9KzKh{aHqoDvO9IdJdBtS?DUoe
z)Nw;VE%#(0qN`@&>?+>uOMg+MrW^5f2<*8Ircy<#mzVNqR$V^UlYY#j9Z0uYaX+cz
zm=@6k`;g``ZiHpCY6G#>F8Y!4q5^KbB@z3c1o!S<mgWn0=0yRvW%pBR@fPD0mcd~R
zoiyp!KcYs4E~4%IDY1OpVBK~Xryi9CuPk6C<#`P1CP?qs6Wc>I34a&j@5=AAXTjgf
zFrM8nvQA3hytO6aM<MMMiCyzMzTjc`YZ3J3j<+LF+GH3`9}YL-pqBXU@r98^9rR)(
zCbc~)<PySCv#5p*E$pjdKpwpw2a*SWB@0>nlemI^3|e^`oz{liFgQ0_WDnC6L}{_<
zXHe=y%wv}8yH0}d(tnKoayN~(DkfG&L!M#_ADO|+J2{*{?%FnC!xOk(tiv@mWetk*
zvXuiz7cxX=ZZW(8*|(1Zq-VE>8+;6O4P7Pa(^Db(<`$N+-N={$<>szhcd9G6rq~Ik
zZ<#707Aw4r@}fI0XHczLNxhPXC_e}nqe>zn0yXl5k0&OQQGam=n0KGiAOdgMgV7*l
z_HkN>U|``Pmq*Mgufy*aG_*Kp0(2j_c@g|2NPW@X_)mGyeevO~d)l`WrM&F4izUj(
zbi?Ah#1H%raxQZrUr%IQsnkH!iV;!lMePCyDN>Jpm(%?GXBs@nMV(hQvY$l-d~X;7
z5h%?qZ@LLPWPdc~{}hjD_RX!za#&H(_q;zc@{lzy;(mJ3gE#Z|L%HYuz3d?{>^fi+
z=Qq5R*whJQ_Fc4xN{4I)f-}D+;(xkt|K-ly*SF~}ZW$>NW`YPo*GNH)W`BjChzk~t
zM_Xq)p*>mh_nl_`wm;btNO8WCe~Vfzw#?nIyl`bObbmUK8CkiY_4el#E!qSfNJT#m
zNq*R~jQ0+_jl|rXq--OvU;pAhM#a{x#NC>>k$ry8?=t@&YfR*d%rUgDr4`>>*?Fp3
zm6tDh?0Kikfle1pFTb{Y`R=QGZgo%8NycbQcn=T<ZWVRX#6b7H%5e|Dsue^3#^c{~
zt-|vOYkzS>$*&#AMlx>&DjT6Z`C8r<oW-l8E}r9;R*^Fg;?#g!KOJ87$rdKD^NH<V
z7P00zaT|lqhsQ1KP$!c6*-)Npw&nj%qV8iJMseUvaK;-%n(YrcmVQ%O5&uvgl%eh>
zx>p^s=*2RYr-zKsK7JI@X~mUWDfE+xCaM!N3xC7<u&QJ6qV(qtpC)a0H2dbo^!KC3
z<i`#o23qGZ07X!IUREUpro8X+39>7SyJf)+hK3IIs;JWWx6%ZmD9!F^68$cIiqajr
zR5y4ssBw@8MxhHqQyWbUaxfGj+Txg1^Jr;7E=~$nS4{l<LtgOJM|r&}h@h_rDBG62
zSAX^L?rU|=L`enJ6H$h%TL?PW!skb<YDc7Msd@_rV<e8}+1HRpT5)>!{x!C4WVrG^
zTy*j!8xf=&%SUE{ImMBN^JvJG-MmaHgVZm&-5|>SjPW(>?hqG|I@^t)(gso1int)^
zxGLhRySaM*#8A}i#XA^d`tNQzSl4an41a4KU|HLj0P<rXZ*z#^0I+n`l`eZRnn%8?
zf;m?A<;z&ju)FoDZc<>JrsP!~1}K?!h_dm?uX)c4X<nn^?Nmh|?8@2jgqE+EaVd>K
zDIa$U`ARdNZe7TM)EE{3aE$unektm*K~}sZudc^b9sD+ZR1eB4_###Yzbg(2!+&vX
z0Z}A>O&{GNRZslSt|*{dq|kEY^E1_4{|e!H<O|kQtW=>wv@X#-c)1^aiwYvwu}JPP
z(9)JhVOJGa9aOzAz?Sk%Tc;bPTdwMwl7}>wJ(l!SHQZG-C8|&0e}wd#8kTPWEY(Bh
z|LqSM^Y%v-eO)}?>hD;@Ozief^nV0ac7Ccl4653@a&DGp@#g>G_(_O$+k_bxjH0li
z0izPGLwrzm&vI|%&AoBcd-}Mgd@xH`nS-V*Nk(MOZ~lvAvNeou<~L*aN3rfCqa_*7
zeyTw(yb%y`K}I#mMF}{bkkO(JxC8?(IpFOf%UDuyz@_`+ctkknq>i=%qkpX$Xe*93
zuF#^Q(Zz}1jowNYs5P{+#7XT*=7&GEOO@KY`2MNJaqa#Xu!qr4PDuaL6xy=*^g-{N
zOdiT9;-mW_|HcQZe;jzP${#}R{`ls_KYnrmxwK1vD+|OpA?ED7JF8WQ9fGPtj0A-0
zOWrN;<;}kQ_zB0dDQqCvEPo8)R(&BRz7|Ul1(Mu_w1M44X$-x)?I8@C>leH<kX~6D
zMen%d18R1(<yVSB36{k{40+d^=IDx3QYJpC6okf`Pj|eJNbhNZrBahL(5aOKQBs|d
zf4tj9A-3T+g-yg7g(2L2p$9(ep~?F+LO;8PtbtjhEQHuw@nuj{9Dn(2CdoyZGbFhy
zc>}?#@(_~mX#VYWQm!U&{OY0xYW1QZR^p%xmX44y@epMo1n$`Rhd8I3<VAMyFE>Ja
z0U4;a3&Qv(d79-P)9c+^ytI*Nqcnov=YIS?;|PAXVECmU!!J07Uo04Y?Z@ydj^S4n
z!{|PF6Gzw=xe_xmDu0WCnC#ND*ot#yq9?-gX$YHGH3~zxiLxKr17BHTN3WWsfmN*}
zh?3=q1s$nSBUE+fiN-gZa?0+7HmienAOqcYK_vewG>R8ktspv(;1*m;+M2Lu+3tXz
zp>`lym{3aEnvh#9lsb?sOvvF2sG4|K&62r1enQ?31UKM95P!?R@N&yFP74Zxc})sQ
z`@UQPc!|YYqZJ2Ey(xzzAC=1kd)gHOoNy(9q`Konr^oD8C2cTp(hV^zbBl$`r8t5q
zbU9O#$!qHh`6aXU(gp?!x26LGZKIs5dYRqSxC04eO;ZwU0-xP_A%60#gFuk3M6hh-
ztXFPhcsu+IyMF@-!TmxKX@Zo?tmfe@C~)d^sTSJj%vCaO{yC48k!qXdHNCcyjv;Zo
z*e*|ZdsfJU!*Bmp?wQZb+>8*{B#k0Qw(oD>PDbO|Xf(zUJWF+PI+rri;Q!ppeDANW
z&-q|wyC_|jg%Go&1S12a@#`<I5bAm94z>KQNu4~Wg?~4@F4jSyUd+Vg{ku;H0=#sG
zUVhi4P9Et!pZJAqZVGmgXcjc_5$C?(BzWl#&HOGv-HT0<X1nH59k^7t`l^(P#&0T+
zD!u_W1v|(z3!3;;@o&ZVdY`=`g3yIz2cwIU7)s*s=k-}ND*zzDvjCQ7Mjv~S<kAR+
zymSXW`G0YwJj(0K0YP`d6fdo(*H+p@PaZP1rl*napr<MA0CJ0&`CO+Wb6amas61kD
z-MR#1E})=e%;p8=a7z8<w%l|;dAz{-8i~K$jsgxSkr!BRBlDNrQNRJG??UNr<ot3C
zg&c6=E-;6yY+tUSkON9ch0%Y`VC8lca4<Q-P=D$#bBnp=at<Olm=%{YrI>3h<{;7s
zVwhZJ9dwPw96$~&41+4=mfL#U0p%#e>8z5Pxg7;SdS_U@Gn3w#1IreMQC!O}=602E
z;3>i|>Ms(Dxu#MMC`%ZILH96U6>wll!oZ4~X~o>G5)L3w7+7yDt(e<-+X1CI0_$w#
zMt^cU3OJYyU~u)C%wev%oP*Ew1*g=SC(MPGb}X`b+3>qe3g&`~JNP7CHUuwHfVt4p
z4kWJ@oKP(fm)m~dF{Rf6E38s+x%zt!Ah#A=*EtoJ+j`r<q!fg!)}$hI&E*_GqAxIq
zT3#@>^|k{|vtm};lA6WsF5_U+s$hv+rGI2`VPze7QWY$vwoe6gr5tEF6)cHU3KqA!
zjDt<gfhKa9)We09buhVIu%sF}VO(=L$0C^vmXj_Qj0-OA^h`m9Woyc2=30q5{gRhi
z8qt;p&9#wq2Fi6dge|)CX>KnFr&roEtWDkd*IWxhr+=cg0gSjz+veIzJGjJcSbypl
zDc@X3Ne7o-3QOrCGnES|>0r`=m<e^H6LHPu9J_e*W?G<#_AW-kK?bHraMZ@McR@uR
z>j3a5ew|U|U8InMi>Hqu3V+D3hpP>wY^2i~q}er<a{9#m#S`m@AME1g9Lw0h7QD6L
zgI$z}V-x)sLA5=4unRBmpki+$*neq)cDsOr4le#Sf{-q9w+kuhpaOLx7-=GWyMTgD
zpJ>epdgiFlE?&+-1bsGhZI2c08jCqSqd=S4;Q~s#R-%q|5NRy`_DIw&Qb=$<hs-*K
z%&4v^%(voCM}*O+6Fr61FbCDR3d&WFyHyKG^J}_edwS2f0H5i{@z3SIO@GnGt%{-i
zp^k=Ml<@Y=W8a$F4G_`ui+9ESaQyK03aku^*@34@=pog;+_|K7s`xf?Ka>}Ukmw>>
zC)kQwqj&-?<qV9^9{{w0SCLj4k7Osl{<vyo`y;7tl!5Hz-gVjDYIhA{ACARV1VgJ!
zXQRoO(#3MMUe5zEzG~h!0e?JXnD=ZnTP$bOC7sMhE5et34^b>PFh&p^s8nj%XznwA
zJ)X`to2i8j+Rvs-WIA8bRXASHd}@Jw85*Mk4gG+HLEwiY3()KE5gORZ)4)!LgALcK
zb;y=8HV&+wS!aX;rDHN#vDI80jGy@yI!s^WluA~c`D8_Xx}Hx(z<+ZNO217;<0V92
z+j*)In)$(IISm$cvxf1%J_D#hn)E@MF8$eZF%D*IJwYMq4lHRPbIPlKNBM*d+E<wI
z>1sL+M%;9N*{>O#zm(G;PX<K}R+Di!p0EAUg6w%u7_*1dPBXOgG$wY<c;7r31>u~|
zChH!(e?7WX2|SxEMt_Ws*kVQPyX4QBE_oJ=X*gYv=y=IU?r)<k+p#F;3m@c5*F4Hn
zg0qP~oi10wX1ubXtqBFD!JQ0=8%}v6q;x!+49mBMJ0Rcrg!e)IYB~-UGs55UB1(9x
zo?<#A-4Wwfa5-Hb2%OFq^Hmszv}Y%B^#OUQU>1boVocX`4u5<V%^AL$pp&6M7mM+n
z_j`fAn3ALTUN2$Dr+9sWu7qCEIa`falW;^)BVO&SLy5FruY(y47t~+$nb+0>zm>>*
zC}r!#n2)D3A|xZ9*TJ6Gz#Kuie(*+v8%N0A>>6(|TCmAtGhKyjA$cO7(di()2JT3c
z`@V4DD&PZL7=Nrrgt7ZXv$h7EvTcP!zWdjZ;}P!!gUx8|Z^$>^9z<YI2;kLcawXnm
zzM0X{INXHGUISP2^lJ$|^{4aEWHw*<4E5r)pGeaHPo4_+B45ft8hE$2S}hiQiD5Ij
zd3P}-YrswV!)=1aYQCo9kgn`!NSX=Kf=zk%?9b<X(SO!&q|!tT(Wsa_y^86Rs93Jp
zk}ekhGFXI9wFF&;Y`z?av&CdI;%l3j?jmS6qWjK7fv)(1mQT$nqrrMW2SNjO@-(p1
z0b%)kY{~~DJ`sUc0xC^mwpx#Q7d2;ev!LWMMHRY(x;&0t>e!4Yya{e*!E81_57mI{
z-$Si}QGdAb=M#Uvq5V1%UF0*3j>%K$;C(EchyH32*!Q$wHC^p`%qM;8H47$F8^_~S
zEYlKoHl5J%n$O!O<6aX5-4_I<iY1+nr)(Weg6W`M-}Rag>f?>S2<MA_ZAKexPAQ?&
zV6<VAU^!lI2K8Fd<(PLW{${aUFKwpGjc-9UkbmX0dE6J$U-;u$u-;g8|9Yo1Wvd16
z?AV-+*|6&+-b4Fiy4>(-FYxt)1!$?z8RPAE%~y?-Y?`06pnK_yk6KC%d|?*)3r1%l
zBO4YK518S*_TiESu54qo!2tgqsV3GBam9G2JX!Jw*U!b)_(r+J-Y`1%!^LdAw%Pp9
zgnvcV;7$g_4VJ6vl1-MuGE@u8VuoE+R-Z_gh~XqyEEm(&d^PI1E1?TprBO0@A|?KK
zJ)5mIbh)Cv_gA_@xt03(3VIr>=#<Vzs6}q$bIB5Gx?ud#@~L?^$6{T6>|7$QC*yGt
zY$lWWa-g9vzZzft4VwmZvY1bTS=k)%t$(q;NalS<$o$QC%<Fa_*7eY;rIOI63(8kp
zlgWr|XoQ?cSKo{&uz)Y77Hl#LCiBUl3+G_rk3tsu)47=OS78J2Zlq>d0u6Sa%07BB
z0IWY-g`1Fa*v*i=X#;n_-jpq8LBLmT<CVWAMHJwgZ|!?N1sARupL>tOl}{%&^MAF*
z7rq+Ee@AFH=QU(4JNOCWI?=cLK^*Am&gBHp-jwgR-@W@d^BU=&ysLEBO;+&q^*;y&
zgexFIhEy`7k|8Grm^}AT)?Qbp`u!1Slqu^y*i<5rh(IFI1L3_hM<OK>;jAumX;*0l
z0XemC6?2tW-mXrrVJxacfRH+fsDBAzmixk-$G)f8Uip>{W4%{<XM0zI!V-0%-hT1;
zMgGx^$XzJ2OVgpNCo4}<dHeHGD!Z!DB3V>Rg+ppMs!HNeoTOpdLzMFuL?%3}<(-tt
z5G!G~CJe8UmVOpo4=p`0yaMujasnWV0K6B!$Oqm@{W5nrpbu9frwi^2b$`J<UEl;W
zMq|P|@;ImxFoWr8dvBF;)X*HY+1j;082hySwuI63+C6$}Z9U||`yf8pyBF=U=4ZC5
zjCM49jYup~V%0t1@*OQB5y+dOE=2F8E}p}BR-yC`GRb*8phr0i=u=haEyDq7ie2m<
z_Nb^clx02DLVfh8o`d{3K!4SgKz*x4!B|$wKZ&|;)oeskaK2LZe3{eRszxp#@O8lf
z#A=-=08tAc%8y&AyNT}AkT1rzjFkt>e{7~A{|Rg}a%j7>7dx_Dn%ie!t0hYB;#|+C
zZXV96(u9MGjG$G%@-(}rN%Xt;DT)9%c^j7a+a1lmc`^O{=rQ3k_J3l9X=qn<&Ydto
zQ^*N~2oNGcNC_g^*URd@Fi_r=R*S-JSqx&b8e&g`FTS4!o7@QlHCc_*C%YRUS0*>^
zswtz$svXCy+5wjJkux#Smsh|Q;ve!N-Bs7Cg4p_KK|xiA!l<rS1x0P#$~)Dh#C@&q
zfK8N9bY-mC({2pXJbw)W$}}NQg#7syXCPi-_2l@S(=fr1)`_siJ)fQq0%acu&^@<z
z?_XO#v|UO!o8E?LL2#xC2(57<B)zqHx%igw6k-`^R#O;djubtaBc?Fog0&f9HW5U*
zpRs~@yF*+=DufEwqE;M~abjvxp^zGid|cwE2%c0GaMitBb$_U0;?|s|K<WTDL8)7f
zoSW25?K3Tro?UNqh~mKDGHsRwOirW#IYGaqdE~qDqI<e1I=jkm0Haur+5+tC@+bq(
zcek+%13GZvR+ZznKsozA6pDP8<T>!OKUjRB$h*KY>^;Wb(h)GBWfunX2y0DlgF;(f
zdKD(L>=SGL;D0g*gZoP3Q80V?Ks5mIs(|b_dsRTzpS&unq04WY8}^Hy<W<LPTxaz*
zeN?T}D_CB5{B_|yW5O)VZbQP_&2dyqCjy6X93pUp;lHMjZjq|i{%2R*R_`~z?H>8c
zPrdwqMcIGcvrNowcf5nn1Y>babkJVzN8k9!B^{_X^?w0GM%PaRmnd8!a7i6k)>osb
ztBR`8r(P6OUuDoG^S+3#N@~JbtIwkH?N5`3G(M=k^UKY#bJ21z;D3blo0{+5V2oAG
zng6#xWX#(ii!}4MvSn9)$I<<^0Bi>6Y6F9gtuFNf@&5!iDe>gHRQ-Lz7WMh58b4?w
zRD!BL-haz{IDQgBz`DcDQ7)<mIZe4RzRyerM;pl#M=VGm6S)HX@7&9+==I&yCAJnn
z(<Uv>PVH{(a3(&-hHPJh&pWf$c0cP*E6(1wEmwf8fA}t5o297jJX=Hmm~A?g$({Rk
z!`S^idu~0fZf?E}WAxMRr1dcNyrpJq=u>Zvp?{3K-Xk-c^~dhcw3vt4roox`{JSv#
z6HVJP7A8L9{tDE<_Kg+``<`KQ1!|Xmm&L-SXW3GLTGg_*Vq?~GZK;4wYuj6~Fz(4V
zRG`LO?W|ZB@yy#PP}92hRm@iY(GL9<D^Z?(ODmt<jgPUl!=FEpxlih|?_(-r4fWsP
zrhiA6+TpLawDrHtC6B2KxNqLBZl1>dj<B%lhqp80ztydds0O5ey;e^qFSF6F4D%!(
z^MdVoYkOcZJWTJO+}k)!m^_-m7b3#Tm1aj3qxYAn`1P=H9=DW_`Uz_!NIzXvUsV0Z
gfBxV9{BQ2^D;EMM8cmTO<WC|>HH7~kbOWs(U+)qWa{vGU

diff --git a/dev/searchindex.js b/dev/searchindex.js
index fe221fdf..748069ce 100644
--- a/dev/searchindex.js
+++ b/dev/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"API Reference": [[0, null]], "API changes": [[154, "api-changes"], [154, "id13"], [154, "id16"], [154, "id19"], [154, "id22"]], "Advanced neural network training strategies": [[1, null], [24, "advanced-neural-network-training-strategies"]], "Analysing the best fit": [[4, "analysing-the-best-fit"]], "Applied examples on real-world datasets": [[7, null], [24, "applied-examples-on-real-world-datasets"]], "Augmentation": [[0, "augmentation"]], "Authors": [[154, "authors"]], "Basic Brain Decoding on EEG Data": [[28, null]], "Basic model building and training": [[24, "basic-model-building-and-training"], [25, null]], "Benchmarking eager and lazy loading": [[14, null]], "Benchmarking preprocessing with parallelization and serialization": [[16, null]], "Braindecode Homepage": [[149, null]], "Bugs": [[154, "bugs"], [154, "id12"], [154, "id15"], [154, "id18"], [154, "id21"]], "By description information": [[21, "by-description-information"]], "By row index": [[21, "by-row-index"]], "Choosing between GPU and CPU processors": [[31, "choosing-between-gpu-and-cpu-processors"]], "Citing other algorithms": [[35, "citing-other-algorithms"]], "Citing the Braindecode": [[35, "citing-the-braindecode"]], "Citing the MNE": [[35, "citing-the-mne"]], "Classifier": [[0, "classifier"]], "Clone the repository from GitHub": [[152, "clone-the-repository-from-github"]], "Combining preprocessing steps": [[12, "combining-preprocessing-steps"]], "Computation times": [[6, null], [13, null], [23, null], [33, null], [34, null], [153, null]], "Conclusion": [[5, "conclusion"]], "Convolutional neural network regression model on fake data.": [[31, null]], "Create Pytorch model": [[32, "create-pytorch-model"]], "Create an EEGClassifier with the desired augmentation": [[3, "create-an-eegclassifier-with-the-desired-augmentation"], [4, "create-an-eegclassifier-with-the-desired-augmentation"]], "Create model": [[2, "create-model"], [3, "create-model"], [4, "create-model"], [8, "create-model"], [9, "create-model"], [10, "create-model"], [11, "create-model"], [29, "create-model"], [30, "create-model"]], "Create model and compute windowing parameters": [[27, "create-model-and-compute-windowing-parameters"]], "Create sequence samplers": [[9, "create-sequence-samplers"], [10, "create-sequence-samplers"], [11, "create-sequence-samplers"]], "Creating Temple University Hospital (TUH) EEG Corpus Dataset": [[22, "creating-temple-university-hospital-tuh-eeg-corpus-dataset"]], "Creating Windows": [[22, "creating-windows"]], "Creating a model": [[28, "creating-a-model"]], "Creating samplers": [[5, "creating-samplers"]], "Creating the dataset using TUHMock": [[12, "creating-the-dataset-using-tuhmock"]], "Creating the model": [[5, "creating-the-model"]], "Cropped Decoding on BCIC IV 2a Dataset": [[27, null]], "Current 0.7 (10-2022)": [[154, "current-0-7-10-2022"]], "Current 0.8 (11-2022)": [[154, "current-0-8-11-2022"]], "Current 0.9 (dev0)": [[154, "current-0-9-dev0"]], "Custom Dataset Example": [[17, null]], "Cut Compute Windows": [[2, "cut-compute-windows"], [8, "cut-compute-windows"], [12, "cut-compute-windows"], [32, "cut-compute-windows"]], "Cut the data into windows": [[27, "cut-the-data-into-windows"]], "Data Augmentation": [[4, null]], "Data Augmentation on BCIC IV 2a Dataset": [[3, null]], "Data Utils": [[0, "data-utils"]], "Data windowing": [[31, "data-windowing"]], "DataLoader for Model Training": [[22, "dataloader-for-model-training"]], "Dataset summary": [[74, null], [77, null]], "Datasets": [[0, "datasets"]], "Defining a CNN regression model": [[31, "defining-a-cnn-regression-model"]], "Defining a Transform": [[3, "defining-a-transform"]], "Defining a list of transforms": [[4, "defining-a-list-of-transforms"]], "Enhancements": [[154, "enhancements"], [154, "id7"], [154, "id14"], [154, "id17"], [154, "id20"]], "Examining the model": [[26, "examining-the-model"]], "Examples": [[24, null]], "Examples using braindecode.augmentation.AugmentedDataLoader": [[36, "examples-using-braindecode-augmentation-augmenteddataloader"]], "Examples using braindecode.augmentation.ChannelsDropout": [[38, "examples-using-braindecode-augmentation-channelsdropout"]], "Examples using braindecode.augmentation.Compose": [[41, "examples-using-braindecode-augmentation-compose"]], "Examples using braindecode.augmentation.FTSurrogate": [[42, "examples-using-braindecode-augmentation-ftsurrogate"]], "Examples using braindecode.augmentation.FrequencyShift": [[43, "examples-using-braindecode-augmentation-frequencyshift"]], "Examples using braindecode.augmentation.SignFlip": [[53, "examples-using-braindecode-augmentation-signflip"]], "Examples using braindecode.augmentation.SmoothTimeMask": [[54, "examples-using-braindecode-augmentation-smoothtimemask"]], "Examples using braindecode.augmentation.Transform": [[56, "examples-using-braindecode-augmentation-transform"]], "Examples using braindecode.datasets.BCICompetitionIVDataset4": [[73, "examples-using-braindecode-datasets-bcicompetitionivdataset4"]], "Examples using braindecode.datasets.BaseConcatDataset": [[75, "examples-using-braindecode-datasets-baseconcatdataset"]], "Examples using braindecode.datasets.BaseDataset": [[76, "examples-using-braindecode-datasets-basedataset"]], "Examples using braindecode.datasets.MOABBDataset": [[78, "examples-using-braindecode-datasets-moabbdataset"]], "Examples using braindecode.datasets.SleepPhysionet": [[80, "examples-using-braindecode-datasets-sleepphysionet"]], "Examples using braindecode.datasets.TUH": [[81, "examples-using-braindecode-datasets-tuh"]], "Examples using braindecode.datasets.TUHAbnormal": [[82, "examples-using-braindecode-datasets-tuhabnormal"]], "Examples using braindecode.datasets.create_from_X_y": [[84, "examples-using-braindecode-datasets-create-from-x-y"]], "Examples using braindecode.datasets.create_from_mne_epochs": [[85, "examples-using-braindecode-datasets-create-from-mne-epochs"]], "Examples using braindecode.datasets.create_from_mne_raw": [[86, "examples-using-braindecode-datasets-create-from-mne-raw"]], "Examples using braindecode.datautil.load_concat_dataset": [[87, "examples-using-braindecode-datautil-load-concat-dataset"]], "Examples using braindecode.models.Deep4Net": [[93, "examples-using-braindecode-models-deep4net"]], "Examples using braindecode.models.EEGModuleMixin": [[99, "examples-using-braindecode-models-eegmodulemixin"]], "Examples using braindecode.models.ShallowFBCSPNet": [[109, "examples-using-braindecode-models-shallowfbcspnet"]], "Examples using braindecode.models.SleepStagerChambon2018": [[111, "examples-using-braindecode-models-sleepstagerchambon2018"]], "Examples using braindecode.models.SleepStagerEldele2021": [[112, "examples-using-braindecode-models-sleepstagereldele2021"]], "Examples using braindecode.models.TimeDistributed": [[116, "examples-using-braindecode-models-timedistributed"]], "Examples using braindecode.models.USleep": [[117, "examples-using-braindecode-models-usleep"]], "Examples using braindecode.preprocessing.Preprocessor": [[122, "examples-using-braindecode-preprocessing-preprocessor"]], "Examples using braindecode.preprocessing.create_fixed_length_windows": [[125, "examples-using-braindecode-preprocessing-create-fixed-length-windows"]], "Examples using braindecode.preprocessing.create_windows_from_events": [[126, "examples-using-braindecode-preprocessing-create-windows-from-events"]], "Examples using braindecode.preprocessing.create_windows_from_target_channels": [[127, "examples-using-braindecode-preprocessing-create-windows-from-target-channels"]], "Examples using braindecode.preprocessing.exponential_moving_standardize": [[129, "examples-using-braindecode-preprocessing-exponential-moving-standardize"]], "Examples using braindecode.preprocessing.preprocess": [[131, "examples-using-braindecode-preprocessing-preprocess"]], "Examples using braindecode.samplers.RecordingSampler": [[134, "examples-using-braindecode-samplers-recordingsampler"]], "Examples using braindecode.samplers.RelativePositioningSampler": [[135, "examples-using-braindecode-samplers-relativepositioningsampler"]], "Examples using braindecode.samplers.SequenceSampler": [[136, "examples-using-braindecode-samplers-sequencesampler"]], "Examples using braindecode.training.CroppedLoss": [[137, "examples-using-braindecode-training-croppedloss"]], "Examples using braindecode.training.CroppedTimeSeriesEpochScoring": [[138, "examples-using-braindecode-training-croppedtimeseriesepochscoring"]], "Examples using braindecode.training.CroppedTrialEpochScoring": [[139, "examples-using-braindecode-training-croppedtrialepochscoring"]], "Examples using braindecode.training.TimeSeriesLoss": [[141, "examples-using-braindecode-training-timeseriesloss"]], "Examples using braindecode.util.set_random_seeds": [[145, "examples-using-braindecode-util-set-random-seeds"]], "Examples using braindecode.visualization.plot_confusion_matrix": [[147, "examples-using-braindecode-visualization-plot-confusion-matrix"]], "Exploring Data": [[22, "exploring-data"]], "Exploring DataLoader": [[22, "exploring-dataloader"]], "Exploring Windows": [[22, "exploring-windows"]], "Exploring the braindecode online documentation": [[26, "exploring-the-braindecode-online-documentation"]], "Extract windows": [[9, "extract-windows"], [10, "extract-windows"], [11, "extract-windows"]], "Extracting Compute Windows": [[28, "extracting-compute-windows"]], "Extracting windows": [[3, "extracting-windows"], [4, "extracting-windows"], [5, "extracting-windows"]], "Extraction of the Compute Windows": [[30, "extraction-of-the-compute-windows"]], "Extraction of the Windows": [[29, "extraction-of-the-windows"], [30, "extraction-of-the-windows"]], "Fake regression data": [[31, "fake-regression-data"]], "Finding the model you want": [[26, "finding-the-model-you-want"]], "Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset": [[2, null]], "Fingers flexion decoding on BCIC IV 4 ECoG Dataset": [[8, null]], "Frequently Asked Questions (FAQ)": [[148, null]], "Generating fake regression dataset": [[31, "generating-fake-regression-dataset"]], "Get the best hyperparameters": [[30, "get-the-best-hyperparameters"]], "Help! I can\u2019t get Python and Braindecode working!": [[148, "help-i-can-t-get-python-and-braindecode-working"]], "How do I cite Braindecode?": [[148, "how-do-i-cite-braindecode"]], "How to cite Braindecode": [[35, null]], "How to train and evaluate your model": [[29, "how-to-train-and-evaluate-your-model"], [32, "how-to-train-and-evaluate-your-model"]], "How to train, test and tune your model?": [[29, null]], "How to tune your hyperparameters": [[29, "how-to-tune-your-hyperparameters"]], "Hyperparameter tuning with scikit-learn": [[30, null]], "I still can\u2019t get it to work!": [[148, "i-still-can-t-get-it-to-work"]], "I think I found a bug, what do I do?": [[148, "i-think-i-found-a-bug-what-do-i-do"]], "Inspecting pretext task performance": [[5, "inspecting-pretext-task-performance"]], "Installation": [[150, null]], "Installing Braindecode from the source": [[152, "installing-braindecode-from-the-source"]], "Installing from PyPI": [[151, null]], "Installing from sources": [[152, null]], "Let\u2019s visualize the first option with a util function.": [[29, "let-s-visualize-the-first-option-with-a-util-function"]], "Let\u2019s visualize the second option with a util function.": [[29, "let-s-visualize-the-second-option-with-a-util-function"]], "Let\u2019s visualize the third option with a util function.": [[29, "let-s-visualize-the-third-option-with-a-util-function"]], "Load and save dataset example": [[18, null]], "Loading": [[2, "loading"], [3, "loading"], [4, "loading"], [8, "loading"], [9, "loading"], [10, "loading"], [11, "loading"], [30, "loading"]], "Loading and organizing data": [[15, null], [24, "loading-and-organizing-data"]], "Loading and preparing the data": [[28, "loading-and-preparing-the-data"]], "Loading and preparing the dataset": [[2, "loading-and-preparing-the-dataset"], [8, "loading-and-preparing-the-dataset"]], "Loading and preprocessing of data, defining a model, etc.": [[29, "loading-and-preprocessing-of-data-defining-a-model-etc"]], "Loading and preprocessing the dataset": [[3, "loading-and-preprocessing-the-dataset"], [4, "loading-and-preprocessing-the-dataset"], [5, "loading-and-preprocessing-the-dataset"], [9, "loading-and-preprocessing-the-dataset"], [10, "loading-and-preprocessing-the-dataset"], [11, "loading-and-preprocessing-the-dataset"], [27, "loading-and-preprocessing-the-dataset"], [30, "loading-and-preprocessing-the-dataset"]], "Loading data": [[29, "loading-data"]], "Loading the Dataset Structure": [[32, "loading-the-dataset-structure"]], "Loading the dataset": [[21, "loading-the-dataset"], [28, "loading-the-dataset"]], "Loading the raw recordings": [[5, "loading-the-raw-recordings"]], "Loading your own data with MNE": [[26, "loading-your-own-data-with-mne"]], "Loading, preprocessing, defining a model, etc.": [[32, "loading-preprocessing-defining-a-model-etc"]], "MNE Dataset Example": [[19, null]], "MOABB Dataset Example": [[20, null]], "Manipulating one session and visualizing the transformed data": [[3, "manipulating-one-session-and-visualizing-the-transformed-data"]], "Manually composing Transforms": [[3, "manually-composing-transforms"]], "Model Training": [[28, "model-training"]], "Model evaluation": [[31, "model-evaluation"]], "Model testing": [[31, "model-testing"]], "Model training": [[31, "model-training"]], "Models": [[0, "models"]], "Multiple discrete targets with the TUH EEG Corpus": [[22, null]], "Observation": [[21, "observation"]], "Option 1: Pure PyTorch training loop": [[32, "option-1-pure-pytorch-training-loop"]], "Option 1: Simple Train-Test Split": [[29, "option-1-simple-train-test-split"]], "Option 1: Train-Val-Test Split": [[29, "option-1-train-val-test-split"]], "Option 2: Train it with PyTorch Lightning": [[32, "option-2-train-it-with-pytorch-lightning"]], "Option 2: Train-Val-Test Split": [[29, "option-2-train-val-test-split"]], "Option 2: k-Fold Cross Validation": [[29, "option-2-k-fold-cross-validation"]], "Option 3: k-Fold Cross Validation": [[29, "option-3-k-fold-cross-validation"]], "Plot Confusion Matrix": [[27, "plot-confusion-matrix"]], "Plot Results": [[2, "plot-results"], [8, "plot-results"], [27, "plot-results"]], "Plot results": [[4, "plot-results"], [9, "plot-results"], [10, "plot-results"], [11, "plot-results"]], "Plotting Results": [[28, "plotting-results"]], "Plotting a  Confusion Matrix": [[28, "plotting-a-confusion-matrix"]], "Plotting the results": [[30, "plotting-the-results"]], "Preprocessing": [[0, "preprocessing"], [2, "preprocessing"], [3, "preprocessing"], [4, "preprocessing"], [5, "preprocessing"], [8, "preprocessing"], [9, "preprocessing"], [10, "preprocessing"], [11, "preprocessing"], [12, "preprocessing"], [28, "preprocessing"], [30, "preprocessing"]], "Preprocessing data": [[29, "preprocessing-data"]], "Preprocessing windows": [[5, "preprocessing-windows"]], "Preprocessing, the offline transformation of the raw dataset": [[32, "preprocessing-the-offline-transformation-of-the-raw-dataset"]], "Process a big data EEG resource (TUH EEG Corpus)": [[12, null]], "References": [[4, "references"], [5, "references"], [9, "references"], [10, "references"], [11, "references"], [26, "references"], [27, "references"], [28, "references"], [29, "references"], [30, "references"], [31, "references"], [148, "references"]], "Regressor": [[0, "regressor"]], "Samplers": [[0, "samplers"]], "Searching the best data augmentation on BCIC IV 2a Dataset": [[4, null]], "Selecting recordings": [[12, "selecting-recordings"]], "Self-supervised learning": [[5, null]], "Self-supervised learning on EEG with relative positioning": [[5, null]], "Setting the data augmentation at the Dataset level": [[3, "setting-the-data-augmentation-at-the-dataset-level"]], "Simple training on MNE epochs": [[26, null]], "Sleep staging on the Sleep Physionet dataset using Chambon2018 network": [[9, null]], "Sleep staging on the Sleep Physionet dataset using Eldele2021": [[10, null]], "Sleep staging on the Sleep Physionet dataset using U-Sleep network": [[11, null]], "Split Dataset Example": [[21, null]], "Split dataset into train and test": [[2, "split-dataset-into-train-and-test"], [29, "split-dataset-into-train-and-test"], [32, "split-dataset-into-train-and-test"]], "Split dataset into train and valid": [[3, "split-dataset-into-train-and-valid"], [4, "split-dataset-into-train-and-valid"], [9, "split-dataset-into-train-and-valid"], [10, "split-dataset-into-train-and-valid"], [11, "split-dataset-into-train-and-valid"], [30, "split-dataset-into-train-and-valid"]], "Split dataset into train, valid, and test": [[8, "split-dataset-into-train-valid-and-test"]], "Split the dataset": [[27, "split-the-dataset"]], "Splitting": [[21, "splitting"]], "Splitting dataset into train, valid and test sets": [[5, "splitting-dataset-into-train-valid-and-test-sets"]], "Splitting the dataset into training and validation sets": [[28, "splitting-the-dataset-into-training-and-validation-sets"]], "Testing if your installation is working": [[152, "testing-if-your-installation-is-working"]], "This example covers:": [[3, "this-example-covers"], [4, "this-example-covers"], [5, "this-example-covers"], [12, "this-example-covers"], [21, "this-example-covers"], [26, "this-example-covers"], [27, "this-example-covers"], [28, "this-example-covers"], [29, "this-example-covers"], [30, "this-example-covers"], [32, "this-example-covers"]], "Training": [[0, "training"], [2, "training"], [5, "training"], [8, "training"], [9, "training"], [10, "training"], [11, "training"], [27, "training"], [30, "training"]], "Training a Braindecode model in PyTorch": [[32, null]], "Training a model with data augmentation": [[3, "training-a-model-with-data-augmentation"], [4, "training-a-model-with-data-augmentation"]], "Training your model (scikit-learn compatible)": [[26, "training-your-model-scikit-learn-compatible"]], "Using the learned representation for sleep staging": [[5, "using-the-learned-representation-for-sleep-staging"]], "Utils": [[0, "utils"]], "Version 0.5.1 (2021-07-14)": [[154, "version-0-5-1-2021-07-14"]], "Version 0.6 (2021-12-06)": [[154, "version-0-6-2021-12-06"]], "Visualization": [[0, "visualization"]], "Visualizing the results": [[5, "visualizing-the-results"]], "What\u2019s new": [[154, null]], "Why do you need to tune the neural networks model?": [[30, null]], "Why should I care about model evaluation?": [[29, "why-should-i-care-about-model-evaluation"], [32, "why-should-i-care-about-model-evaluation"]], "Window preprocessing": [[9, "window-preprocessing"], [10, "window-preprocessing"]], "braindecode.augmentation.AugmentedDataLoader": [[36, null]], "braindecode.augmentation.BandstopFilter": [[37, null]], "braindecode.augmentation.ChannelsDropout": [[38, null]], "braindecode.augmentation.ChannelsShuffle": [[39, null]], "braindecode.augmentation.ChannelsSymmetry": [[40, null]], "braindecode.augmentation.Compose": [[41, null]], "braindecode.augmentation.FTSurrogate": [[42, null]], "braindecode.augmentation.FrequencyShift": [[43, null]], "braindecode.augmentation.GaussianNoise": [[44, null]], "braindecode.augmentation.IdentityTransform": [[45, null]], "braindecode.augmentation.MaskEncoding": [[46, null]], "braindecode.augmentation.Mixup": [[47, null]], "braindecode.augmentation.SegmentationReconstruction": [[48, null]], "braindecode.augmentation.SensorsRotation": [[49, null]], "braindecode.augmentation.SensorsXRotation": [[50, null]], "braindecode.augmentation.SensorsYRotation": [[51, null]], "braindecode.augmentation.SensorsZRotation": [[52, null]], "braindecode.augmentation.SignFlip": [[53, null]], "braindecode.augmentation.SmoothTimeMask": [[54, null]], "braindecode.augmentation.TimeReverse": [[55, null]], "braindecode.augmentation.Transform": [[56, null]], "braindecode.augmentation.functional.bandstop_filter": [[57, null]], "braindecode.augmentation.functional.channels_dropout": [[58, null]], "braindecode.augmentation.functional.channels_permute": [[59, null]], "braindecode.augmentation.functional.channels_shuffle": [[60, null]], "braindecode.augmentation.functional.frequency_shift": [[61, null]], "braindecode.augmentation.functional.ft_surrogate": [[62, null]], "braindecode.augmentation.functional.gaussian_noise": [[63, null]], "braindecode.augmentation.functional.identity": [[64, null]], "braindecode.augmentation.functional.mask_encoding": [[65, null]], "braindecode.augmentation.functional.mixup": [[66, null]], "braindecode.augmentation.functional.segmentation_reconstruction": [[67, null]], "braindecode.augmentation.functional.sensors_rotation": [[68, null]], "braindecode.augmentation.functional.sign_flip": [[69, null]], "braindecode.augmentation.functional.smooth_time_mask": [[70, null]], "braindecode.augmentation.functional.time_reverse": [[71, null]], "braindecode.classifier.EEGClassifier": [[72, null]], "braindecode.datasets.BCICompetitionIVDataset4": [[73, null]], "braindecode.datasets.BNCI2014001": [[74, null]], "braindecode.datasets.BaseConcatDataset": [[75, null]], "braindecode.datasets.BaseDataset": [[76, null]], "braindecode.datasets.HGD": [[77, null]], "braindecode.datasets.MOABBDataset": [[78, null]], "braindecode.datasets.NMT": [[79, null]], "braindecode.datasets.SleepPhysionet": [[80, null]], "braindecode.datasets.TUH": [[81, null]], "braindecode.datasets.TUHAbnormal": [[82, null]], "braindecode.datasets.WindowsDataset": [[83, null]], "braindecode.datasets.create_from_X_y": [[84, null]], "braindecode.datasets.create_from_mne_epochs": [[85, null]], "braindecode.datasets.create_from_mne_raw": [[86, null]], "braindecode.datautil.load_concat_dataset": [[87, null]], "braindecode.datautil.save_concat_dataset": [[88, null]], "braindecode.models.ATCNet": [[89, null]], "braindecode.models.AttentionBaseNet": [[90, null]], "braindecode.models.BIOT": [[91, null]], "braindecode.models.ContraWR": [[92, null]], "braindecode.models.Deep4Net": [[93, null]], "braindecode.models.DeepSleepNet": [[94, null]], "braindecode.models.EEGConformer": [[95, null]], "braindecode.models.EEGITNet": [[96, null]], "braindecode.models.EEGInceptionERP": [[97, null]], "braindecode.models.EEGInceptionMI": [[98, null]], "braindecode.models.EEGModuleMixin": [[99, null]], "braindecode.models.EEGNeX": [[100, null]], "braindecode.models.EEGNetv1": [[101, null]], "braindecode.models.EEGNetv4": [[102, null]], "braindecode.models.EEGResNet": [[103, null]], "braindecode.models.EEGSimpleConv": [[104, null]], "braindecode.models.EEGTCNet": [[105, null]], "braindecode.models.HybridNet": [[106, null]], "braindecode.models.Labram": [[107, null]], "braindecode.models.SPARCNet": [[108, null]], "braindecode.models.ShallowFBCSPNet": [[109, null]], "braindecode.models.SleepStagerBlanco2020": [[110, null]], "braindecode.models.SleepStagerChambon2018": [[111, null]], "braindecode.models.SleepStagerEldele2021": [[112, null]], "braindecode.models.SyncNet": [[113, null]], "braindecode.models.TCN": [[114, null]], "braindecode.models.TIDNet": [[115, null]], "braindecode.models.TimeDistributed": [[116, null]], "braindecode.models.USleep": [[117, null]], "braindecode.preprocessing.Crop": [[118, null]], "braindecode.preprocessing.DropChannels": [[119, null]], "braindecode.preprocessing.Filter": [[120, null]], "braindecode.preprocessing.Pick": [[121, null]], "braindecode.preprocessing.Preprocessor": [[122, null]], "braindecode.preprocessing.Resample": [[123, null]], "braindecode.preprocessing.SetEEGReference": [[124, null]], "braindecode.preprocessing.create_fixed_length_windows": [[125, null]], "braindecode.preprocessing.create_windows_from_events": [[126, null]], "braindecode.preprocessing.create_windows_from_target_channels": [[127, null]], "braindecode.preprocessing.exponential_moving_demean": [[128, null]], "braindecode.preprocessing.exponential_moving_standardize": [[129, null]], "braindecode.preprocessing.filterbank": [[130, null]], "braindecode.preprocessing.preprocess": [[131, null]], "braindecode.regressor.EEGRegressor": [[132, null]], "braindecode.samplers.BalancedSequenceSampler": [[133, null]], "braindecode.samplers.RecordingSampler": [[134, null]], "braindecode.samplers.RelativePositioningSampler": [[135, null]], "braindecode.samplers.SequenceSampler": [[136, null]], "braindecode.training.CroppedLoss": [[137, null]], "braindecode.training.CroppedTimeSeriesEpochScoring": [[138, null]], "braindecode.training.CroppedTrialEpochScoring": [[139, null]], "braindecode.training.PostEpochTrainScoring": [[140, null]], "braindecode.training.TimeSeriesLoss": [[141, null]], "braindecode.training.mixup_criterion": [[142, null]], "braindecode.training.predict_trials": [[143, null]], "braindecode.training.trial_preds_from_window_preds": [[144, null]], "braindecode.util.set_random_seeds": [[145, null]], "braindecode.visualization.compute_amplitude_gradients": [[146, null]], "braindecode.visualization.plot_confusion_matrix": [[147, null]]}, "docnames": ["api", "auto_examples/advanced_training/index", "auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped", "auto_examples/advanced_training/plot_data_augmentation", "auto_examples/advanced_training/plot_data_augmentation_search", "auto_examples/advanced_training/plot_relative_positioning", "auto_examples/advanced_training/sg_execution_times", "auto_examples/applied_examples/index", "auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial", "auto_examples/applied_examples/plot_sleep_staging_chambon2018", "auto_examples/applied_examples/plot_sleep_staging_eldele2021", "auto_examples/applied_examples/plot_sleep_staging_usleep", "auto_examples/applied_examples/plot_tuh_eeg_corpus", "auto_examples/applied_examples/sg_execution_times", "auto_examples/datasets_io/benchmark_lazy_eager_loading", "auto_examples/datasets_io/index", "auto_examples/datasets_io/plot_benchmark_preprocessing", "auto_examples/datasets_io/plot_custom_dataset_example", "auto_examples/datasets_io/plot_load_save_datasets", "auto_examples/datasets_io/plot_mne_dataset_example", "auto_examples/datasets_io/plot_moabb_dataset_example", "auto_examples/datasets_io/plot_split_dataset", "auto_examples/datasets_io/plot_tuh_discrete_multitarget", "auto_examples/datasets_io/sg_execution_times", "auto_examples/index", "auto_examples/model_building/index", "auto_examples/model_building/plot_basic_training_epochs", "auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped", "auto_examples/model_building/plot_bcic_iv_2a_moabb_trial", "auto_examples/model_building/plot_how_train_test_and_tune", "auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn", "auto_examples/model_building/plot_regression", "auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning", "auto_examples/model_building/sg_execution_times", "auto_examples/sg_execution_times", "cite", "generated/braindecode.augmentation.AugmentedDataLoader", "generated/braindecode.augmentation.BandstopFilter", "generated/braindecode.augmentation.ChannelsDropout", "generated/braindecode.augmentation.ChannelsShuffle", "generated/braindecode.augmentation.ChannelsSymmetry", "generated/braindecode.augmentation.Compose", "generated/braindecode.augmentation.FTSurrogate", "generated/braindecode.augmentation.FrequencyShift", "generated/braindecode.augmentation.GaussianNoise", "generated/braindecode.augmentation.IdentityTransform", "generated/braindecode.augmentation.MaskEncoding", "generated/braindecode.augmentation.Mixup", "generated/braindecode.augmentation.SegmentationReconstruction", "generated/braindecode.augmentation.SensorsRotation", "generated/braindecode.augmentation.SensorsXRotation", "generated/braindecode.augmentation.SensorsYRotation", "generated/braindecode.augmentation.SensorsZRotation", "generated/braindecode.augmentation.SignFlip", "generated/braindecode.augmentation.SmoothTimeMask", "generated/braindecode.augmentation.TimeReverse", "generated/braindecode.augmentation.Transform", "generated/braindecode.augmentation.functional.bandstop_filter", "generated/braindecode.augmentation.functional.channels_dropout", "generated/braindecode.augmentation.functional.channels_permute", "generated/braindecode.augmentation.functional.channels_shuffle", "generated/braindecode.augmentation.functional.frequency_shift", "generated/braindecode.augmentation.functional.ft_surrogate", "generated/braindecode.augmentation.functional.gaussian_noise", "generated/braindecode.augmentation.functional.identity", "generated/braindecode.augmentation.functional.mask_encoding", "generated/braindecode.augmentation.functional.mixup", "generated/braindecode.augmentation.functional.segmentation_reconstruction", "generated/braindecode.augmentation.functional.sensors_rotation", "generated/braindecode.augmentation.functional.sign_flip", "generated/braindecode.augmentation.functional.smooth_time_mask", "generated/braindecode.augmentation.functional.time_reverse", "generated/braindecode.classifier.EEGClassifier", "generated/braindecode.datasets.BCICompetitionIVDataset4", "generated/braindecode.datasets.BNCI2014001", "generated/braindecode.datasets.BaseConcatDataset", "generated/braindecode.datasets.BaseDataset", "generated/braindecode.datasets.HGD", "generated/braindecode.datasets.MOABBDataset", "generated/braindecode.datasets.NMT", "generated/braindecode.datasets.SleepPhysionet", "generated/braindecode.datasets.TUH", "generated/braindecode.datasets.TUHAbnormal", "generated/braindecode.datasets.WindowsDataset", "generated/braindecode.datasets.create_from_X_y", "generated/braindecode.datasets.create_from_mne_epochs", "generated/braindecode.datasets.create_from_mne_raw", "generated/braindecode.datautil.load_concat_dataset", "generated/braindecode.datautil.save_concat_dataset", "generated/braindecode.models.ATCNet", "generated/braindecode.models.AttentionBaseNet", "generated/braindecode.models.BIOT", "generated/braindecode.models.ContraWR", "generated/braindecode.models.Deep4Net", "generated/braindecode.models.DeepSleepNet", "generated/braindecode.models.EEGConformer", "generated/braindecode.models.EEGITNet", "generated/braindecode.models.EEGInceptionERP", "generated/braindecode.models.EEGInceptionMI", "generated/braindecode.models.EEGModuleMixin", "generated/braindecode.models.EEGNeX", "generated/braindecode.models.EEGNetv1", "generated/braindecode.models.EEGNetv4", "generated/braindecode.models.EEGResNet", "generated/braindecode.models.EEGSimpleConv", "generated/braindecode.models.EEGTCNet", "generated/braindecode.models.HybridNet", "generated/braindecode.models.Labram", "generated/braindecode.models.SPARCNet", "generated/braindecode.models.ShallowFBCSPNet", "generated/braindecode.models.SleepStagerBlanco2020", "generated/braindecode.models.SleepStagerChambon2018", "generated/braindecode.models.SleepStagerEldele2021", "generated/braindecode.models.SyncNet", "generated/braindecode.models.TCN", "generated/braindecode.models.TIDNet", "generated/braindecode.models.TimeDistributed", "generated/braindecode.models.USleep", "generated/braindecode.preprocessing.Crop", "generated/braindecode.preprocessing.DropChannels", "generated/braindecode.preprocessing.Filter", "generated/braindecode.preprocessing.Pick", "generated/braindecode.preprocessing.Preprocessor", "generated/braindecode.preprocessing.Resample", "generated/braindecode.preprocessing.SetEEGReference", "generated/braindecode.preprocessing.create_fixed_length_windows", "generated/braindecode.preprocessing.create_windows_from_events", "generated/braindecode.preprocessing.create_windows_from_target_channels", "generated/braindecode.preprocessing.exponential_moving_demean", "generated/braindecode.preprocessing.exponential_moving_standardize", "generated/braindecode.preprocessing.filterbank", "generated/braindecode.preprocessing.preprocess", "generated/braindecode.regressor.EEGRegressor", "generated/braindecode.samplers.BalancedSequenceSampler", "generated/braindecode.samplers.RecordingSampler", "generated/braindecode.samplers.RelativePositioningSampler", "generated/braindecode.samplers.SequenceSampler", "generated/braindecode.training.CroppedLoss", "generated/braindecode.training.CroppedTimeSeriesEpochScoring", "generated/braindecode.training.CroppedTrialEpochScoring", "generated/braindecode.training.PostEpochTrainScoring", "generated/braindecode.training.TimeSeriesLoss", "generated/braindecode.training.mixup_criterion", "generated/braindecode.training.predict_trials", "generated/braindecode.training.trial_preds_from_window_preds", "generated/braindecode.util.set_random_seeds", "generated/braindecode.visualization.compute_amplitude_gradients", "generated/braindecode.visualization.plot_confusion_matrix", "help", "index", "install/install", "install/install_pip", "install/install_source", "sg_execution_times", "whats_new"], "envversion": {"sphinx": 62, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.todo": 2}, "filenames": ["api.rst", "auto_examples/advanced_training/index.rst", "auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.rst", "auto_examples/advanced_training/plot_data_augmentation.rst", "auto_examples/advanced_training/plot_data_augmentation_search.rst", "auto_examples/advanced_training/plot_relative_positioning.rst", "auto_examples/advanced_training/sg_execution_times.rst", "auto_examples/applied_examples/index.rst", "auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.rst", "auto_examples/applied_examples/plot_sleep_staging_chambon2018.rst", "auto_examples/applied_examples/plot_sleep_staging_eldele2021.rst", "auto_examples/applied_examples/plot_sleep_staging_usleep.rst", "auto_examples/applied_examples/plot_tuh_eeg_corpus.rst", "auto_examples/applied_examples/sg_execution_times.rst", "auto_examples/datasets_io/benchmark_lazy_eager_loading.rst", "auto_examples/datasets_io/index.rst", "auto_examples/datasets_io/plot_benchmark_preprocessing.rst", "auto_examples/datasets_io/plot_custom_dataset_example.rst", "auto_examples/datasets_io/plot_load_save_datasets.rst", "auto_examples/datasets_io/plot_mne_dataset_example.rst", "auto_examples/datasets_io/plot_moabb_dataset_example.rst", "auto_examples/datasets_io/plot_split_dataset.rst", "auto_examples/datasets_io/plot_tuh_discrete_multitarget.rst", "auto_examples/datasets_io/sg_execution_times.rst", "auto_examples/index.rst", "auto_examples/model_building/index.rst", "auto_examples/model_building/plot_basic_training_epochs.rst", "auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.rst", "auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.rst", "auto_examples/model_building/plot_how_train_test_and_tune.rst", "auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.rst", "auto_examples/model_building/plot_regression.rst", "auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.rst", "auto_examples/model_building/sg_execution_times.rst", "auto_examples/sg_execution_times.rst", "cite.rst", "generated/braindecode.augmentation.AugmentedDataLoader.rst", "generated/braindecode.augmentation.BandstopFilter.rst", "generated/braindecode.augmentation.ChannelsDropout.rst", "generated/braindecode.augmentation.ChannelsShuffle.rst", "generated/braindecode.augmentation.ChannelsSymmetry.rst", "generated/braindecode.augmentation.Compose.rst", "generated/braindecode.augmentation.FTSurrogate.rst", "generated/braindecode.augmentation.FrequencyShift.rst", "generated/braindecode.augmentation.GaussianNoise.rst", "generated/braindecode.augmentation.IdentityTransform.rst", "generated/braindecode.augmentation.MaskEncoding.rst", "generated/braindecode.augmentation.Mixup.rst", "generated/braindecode.augmentation.SegmentationReconstruction.rst", "generated/braindecode.augmentation.SensorsRotation.rst", "generated/braindecode.augmentation.SensorsXRotation.rst", "generated/braindecode.augmentation.SensorsYRotation.rst", "generated/braindecode.augmentation.SensorsZRotation.rst", "generated/braindecode.augmentation.SignFlip.rst", "generated/braindecode.augmentation.SmoothTimeMask.rst", "generated/braindecode.augmentation.TimeReverse.rst", "generated/braindecode.augmentation.Transform.rst", "generated/braindecode.augmentation.functional.bandstop_filter.rst", "generated/braindecode.augmentation.functional.channels_dropout.rst", "generated/braindecode.augmentation.functional.channels_permute.rst", "generated/braindecode.augmentation.functional.channels_shuffle.rst", "generated/braindecode.augmentation.functional.frequency_shift.rst", "generated/braindecode.augmentation.functional.ft_surrogate.rst", "generated/braindecode.augmentation.functional.gaussian_noise.rst", "generated/braindecode.augmentation.functional.identity.rst", "generated/braindecode.augmentation.functional.mask_encoding.rst", "generated/braindecode.augmentation.functional.mixup.rst", "generated/braindecode.augmentation.functional.segmentation_reconstruction.rst", "generated/braindecode.augmentation.functional.sensors_rotation.rst", "generated/braindecode.augmentation.functional.sign_flip.rst", "generated/braindecode.augmentation.functional.smooth_time_mask.rst", "generated/braindecode.augmentation.functional.time_reverse.rst", "generated/braindecode.classifier.EEGClassifier.rst", "generated/braindecode.datasets.BCICompetitionIVDataset4.rst", "generated/braindecode.datasets.BNCI2014001.rst", "generated/braindecode.datasets.BaseConcatDataset.rst", "generated/braindecode.datasets.BaseDataset.rst", "generated/braindecode.datasets.HGD.rst", "generated/braindecode.datasets.MOABBDataset.rst", "generated/braindecode.datasets.NMT.rst", "generated/braindecode.datasets.SleepPhysionet.rst", "generated/braindecode.datasets.TUH.rst", "generated/braindecode.datasets.TUHAbnormal.rst", "generated/braindecode.datasets.WindowsDataset.rst", "generated/braindecode.datasets.create_from_X_y.rst", "generated/braindecode.datasets.create_from_mne_epochs.rst", "generated/braindecode.datasets.create_from_mne_raw.rst", "generated/braindecode.datautil.load_concat_dataset.rst", "generated/braindecode.datautil.save_concat_dataset.rst", "generated/braindecode.models.ATCNet.rst", "generated/braindecode.models.AttentionBaseNet.rst", "generated/braindecode.models.BIOT.rst", "generated/braindecode.models.ContraWR.rst", "generated/braindecode.models.Deep4Net.rst", "generated/braindecode.models.DeepSleepNet.rst", "generated/braindecode.models.EEGConformer.rst", "generated/braindecode.models.EEGITNet.rst", "generated/braindecode.models.EEGInceptionERP.rst", "generated/braindecode.models.EEGInceptionMI.rst", "generated/braindecode.models.EEGModuleMixin.rst", "generated/braindecode.models.EEGNeX.rst", "generated/braindecode.models.EEGNetv1.rst", "generated/braindecode.models.EEGNetv4.rst", "generated/braindecode.models.EEGResNet.rst", "generated/braindecode.models.EEGSimpleConv.rst", "generated/braindecode.models.EEGTCNet.rst", "generated/braindecode.models.HybridNet.rst", "generated/braindecode.models.Labram.rst", "generated/braindecode.models.SPARCNet.rst", "generated/braindecode.models.ShallowFBCSPNet.rst", "generated/braindecode.models.SleepStagerBlanco2020.rst", "generated/braindecode.models.SleepStagerChambon2018.rst", "generated/braindecode.models.SleepStagerEldele2021.rst", "generated/braindecode.models.SyncNet.rst", "generated/braindecode.models.TCN.rst", "generated/braindecode.models.TIDNet.rst", "generated/braindecode.models.TimeDistributed.rst", "generated/braindecode.models.USleep.rst", "generated/braindecode.preprocessing.Crop.rst", "generated/braindecode.preprocessing.DropChannels.rst", "generated/braindecode.preprocessing.Filter.rst", "generated/braindecode.preprocessing.Pick.rst", "generated/braindecode.preprocessing.Preprocessor.rst", "generated/braindecode.preprocessing.Resample.rst", "generated/braindecode.preprocessing.SetEEGReference.rst", "generated/braindecode.preprocessing.create_fixed_length_windows.rst", "generated/braindecode.preprocessing.create_windows_from_events.rst", "generated/braindecode.preprocessing.create_windows_from_target_channels.rst", "generated/braindecode.preprocessing.exponential_moving_demean.rst", "generated/braindecode.preprocessing.exponential_moving_standardize.rst", "generated/braindecode.preprocessing.filterbank.rst", "generated/braindecode.preprocessing.preprocess.rst", "generated/braindecode.regressor.EEGRegressor.rst", "generated/braindecode.samplers.BalancedSequenceSampler.rst", "generated/braindecode.samplers.RecordingSampler.rst", "generated/braindecode.samplers.RelativePositioningSampler.rst", "generated/braindecode.samplers.SequenceSampler.rst", "generated/braindecode.training.CroppedLoss.rst", "generated/braindecode.training.CroppedTimeSeriesEpochScoring.rst", "generated/braindecode.training.CroppedTrialEpochScoring.rst", "generated/braindecode.training.PostEpochTrainScoring.rst", "generated/braindecode.training.TimeSeriesLoss.rst", "generated/braindecode.training.mixup_criterion.rst", "generated/braindecode.training.predict_trials.rst", "generated/braindecode.training.trial_preds_from_window_preds.rst", "generated/braindecode.util.set_random_seeds.rst", "generated/braindecode.visualization.compute_amplitude_gradients.rst", "generated/braindecode.visualization.plot_confusion_matrix.rst", "help.rst", "index.rst", "install/install.rst", "install/install_pip.rst", "install/install_source.rst", "sg_execution_times.rst", "whats_new.rst"], "indexentries": {"_criteria (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier._criteria", false]], "_criteria (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor._criteria", false]], "_modules (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier._modules", false]], "_modules (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor._modules", false]], "_optimizers (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier._optimizers", false]], "_optimizers (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor._optimizers", false]], "apply() (braindecode.preprocessing.preprocessor method)": [[122, "braindecode.preprocessing.Preprocessor.apply", false]], "atcnet (class in braindecode.models)": [[89, "braindecode.models.ATCNet", false]], "attentionbasenet (class in braindecode.models)": [[90, "braindecode.models.AttentionBaseNet", false]], "augmenteddataloader (class in braindecode.augmentation)": [[36, "braindecode.augmentation.AugmentedDataLoader", false]], "balancedsequencesampler (class in braindecode.samplers)": [[133, "braindecode.samplers.BalancedSequenceSampler", false]], "bandstop_filter() (in module braindecode.augmentation.functional)": [[57, "braindecode.augmentation.functional.bandstop_filter", false]], "bandstopfilter (class in braindecode.augmentation)": [[37, "braindecode.augmentation.BandstopFilter", false]], "baseconcatdataset (class in braindecode.datasets)": [[75, "braindecode.datasets.BaseConcatDataset", false]], "basedataset (class in braindecode.datasets)": [[76, "braindecode.datasets.BaseDataset", false]], "bcicompetitionivdataset4 (class in braindecode.datasets)": [[73, "braindecode.datasets.BCICompetitionIVDataset4", false]], "biot (class in braindecode.models)": [[91, "braindecode.models.BIOT", false]], "bnci2014001 (class in braindecode.datasets)": [[74, "braindecode.datasets.BNCI2014001", false]], "braindecode": [[0, "module-braindecode", false]], "calc_padding() (braindecode.models.eegnex static method)": [[100, "braindecode.models.EEGNeX.calc_padding", false]], "callbacks_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.callbacks_", false]], "callbacks_ (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor.callbacks_", false]], "channels_dropout() (in module braindecode.augmentation.functional)": [[58, "braindecode.augmentation.functional.channels_dropout", false]], "channels_permute() (in module braindecode.augmentation.functional)": [[59, "braindecode.augmentation.functional.channels_permute", false]], "channels_shuffle() (in module braindecode.augmentation.functional)": [[60, "braindecode.augmentation.functional.channels_shuffle", false]], "channelsdropout (class in braindecode.augmentation)": [[38, "braindecode.augmentation.ChannelsDropout", false]], "channelsshuffle (class in braindecode.augmentation)": [[39, "braindecode.augmentation.ChannelsShuffle", false]], "channelssymmetry (class in braindecode.augmentation)": [[40, "braindecode.augmentation.ChannelsSymmetry", false]], "classes_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.classes_", false]], "compose (class in braindecode.augmentation)": [[41, "braindecode.augmentation.Compose", false]], "compute_amplitude_gradients() (in module braindecode.visualization)": [[146, "braindecode.visualization.compute_amplitude_gradients", false]], "contrawr (class in braindecode.models)": [[92, "braindecode.models.ContraWR", false]], "create_fixed_length_windows() (in module braindecode.preprocessing)": [[125, "braindecode.preprocessing.create_fixed_length_windows", false]], "create_from_mne_epochs() (in module braindecode.datasets)": [[85, "braindecode.datasets.create_from_mne_epochs", false]], "create_from_mne_raw() (in module braindecode.datasets)": [[86, "braindecode.datasets.create_from_mne_raw", false]], "create_from_x_y() (in module braindecode.datasets)": [[84, "braindecode.datasets.create_from_X_y", false]], "create_windows_from_events() (in module braindecode.preprocessing)": [[126, "braindecode.preprocessing.create_windows_from_events", false]], "create_windows_from_target_channels() (in module braindecode.preprocessing)": [[127, "braindecode.preprocessing.create_windows_from_target_channels", false]], "criterion_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.criterion_", false]], "criterion_ (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor.criterion_", false]], "crop (class in braindecode.preprocessing)": [[118, "braindecode.preprocessing.Crop", false]], "croppedloss (class in braindecode.training)": [[137, "braindecode.training.CroppedLoss", false]], "croppedtimeseriesepochscoring (class in braindecode.training)": [[138, "braindecode.training.CroppedTimeSeriesEpochScoring", false]], "croppedtrialepochscoring (class in braindecode.training)": [[139, "braindecode.training.CroppedTrialEpochScoring", false]], "cuda_dependent_attributes_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.cuda_dependent_attributes_", false]], "cuda_dependent_attributes_ (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor.cuda_dependent_attributes_", false]], "deep4net (class in braindecode.models)": [[93, "braindecode.models.Deep4Net", false]], "deepsleepnet (class in braindecode.models)": [[94, "braindecode.models.DeepSleepNet", false]], "download() (braindecode.datasets.bcicompetitionivdataset4 static method)": [[73, "braindecode.datasets.BCICompetitionIVDataset4.download", false]], "dropchannels (class in braindecode.preprocessing)": [[119, "braindecode.preprocessing.DropChannels", false]], "eegclassifier (class in braindecode.classifier)": [[72, "braindecode.classifier.EEGClassifier", false]], "eegconformer (class in braindecode.models)": [[95, "braindecode.models.EEGConformer", false]], "eeginceptionerp (class in braindecode.models)": [[97, "braindecode.models.EEGInceptionERP", false]], "eeginceptionmi (class in braindecode.models)": [[98, "braindecode.models.EEGInceptionMI", false]], "eegitnet (class in braindecode.models)": [[96, "braindecode.models.EEGITNet", false]], "eegmodulemixin (class in braindecode.models)": [[99, "braindecode.models.EEGModuleMixin", false]], "eegnetv1 (class in braindecode.models)": [[101, "braindecode.models.EEGNetv1", false]], "eegnetv4 (class in braindecode.models)": [[102, "braindecode.models.EEGNetv4", false]], "eegnex (class in braindecode.models)": [[100, "braindecode.models.EEGNeX", false]], "eegregressor (class in braindecode.regressor)": [[132, "braindecode.regressor.EEGRegressor", false]], "eegresnet (class in braindecode.models)": [[103, "braindecode.models.EEGResNet", false]], "eegsimpleconv (class in braindecode.models)": [[104, "braindecode.models.EEGSimpleConv", false]], "eegtcnet (class in braindecode.models)": [[105, "braindecode.models.EEGTCNet", false]], "exponential_moving_demean() (in module braindecode.preprocessing)": [[128, "braindecode.preprocessing.exponential_moving_demean", false]], "exponential_moving_standardize() (in module braindecode.preprocessing)": [[129, "braindecode.preprocessing.exponential_moving_standardize", false]], "file_ids (braindecode.samplers.sequencesampler attribute)": [[136, "braindecode.samplers.SequenceSampler.file_ids", false]], "filter (class in braindecode.preprocessing)": [[120, "braindecode.preprocessing.Filter", false]], "filterbank() (in module braindecode.preprocessing)": [[130, "braindecode.preprocessing.filterbank", false]], "fit() (braindecode.regressor.eegregressor method)": [[132, "braindecode.regressor.EEGRegressor.fit", false]], "fix_init_weight_and_init_embedding() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.fix_init_weight_and_init_embedding", false]], "forward() (braindecode.augmentation.compose method)": [[41, "braindecode.augmentation.Compose.forward", false]], "forward() (braindecode.augmentation.transform method)": [[56, "braindecode.augmentation.Transform.forward", false]], "forward() (braindecode.models.atcnet method)": [[89, "braindecode.models.ATCNet.forward", false]], "forward() (braindecode.models.attentionbasenet method)": [[90, "braindecode.models.AttentionBaseNet.forward", false]], "forward() (braindecode.models.biot method)": [[91, "braindecode.models.BIOT.forward", false]], "forward() (braindecode.models.contrawr method)": [[92, "braindecode.models.ContraWR.forward", false]], "forward() (braindecode.models.deepsleepnet method)": [[94, "braindecode.models.DeepSleepNet.forward", false]], "forward() (braindecode.models.eegconformer method)": [[95, "braindecode.models.EEGConformer.forward", false]], "forward() (braindecode.models.eeginceptionmi method)": [[98, "braindecode.models.EEGInceptionMI.forward", false]], "forward() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.forward", false]], "forward() (braindecode.models.eegnex method)": [[100, "braindecode.models.EEGNeX.forward", false]], "forward() (braindecode.models.eegsimpleconv method)": [[104, "braindecode.models.EEGSimpleConv.forward", false]], "forward() (braindecode.models.eegtcnet method)": [[105, "braindecode.models.EEGTCNet.forward", false]], "forward() (braindecode.models.hybridnet method)": [[106, "braindecode.models.HybridNet.forward", false]], "forward() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.forward", false]], "forward() (braindecode.models.sleepstagerblanco2020 method)": [[110, "braindecode.models.SleepStagerBlanco2020.forward", false]], "forward() (braindecode.models.sleepstagerchambon2018 method)": [[111, "braindecode.models.SleepStagerChambon2018.forward", false]], "forward() (braindecode.models.sleepstagereldele2021 method)": [[112, "braindecode.models.SleepStagerEldele2021.forward", false]], "forward() (braindecode.models.sparcnet method)": [[108, "braindecode.models.SPARCNet.forward", false]], "forward() (braindecode.models.syncnet method)": [[113, "braindecode.models.SyncNet.forward", false]], "forward() (braindecode.models.tcn method)": [[114, "braindecode.models.TCN.forward", false]], "forward() (braindecode.models.tidnet method)": [[115, "braindecode.models.TIDNet.forward", false]], "forward() (braindecode.models.timedistributed method)": [[116, "braindecode.models.TimeDistributed.forward", false]], "forward() (braindecode.models.usleep method)": [[117, "braindecode.models.USleep.forward", false]], "forward() (braindecode.training.croppedloss method)": [[137, "braindecode.training.CroppedLoss.forward", false]], "forward() (braindecode.training.timeseriesloss method)": [[141, "braindecode.training.TimeSeriesLoss.forward", false]], "forward_features() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.forward_features", false]], "frequency_shift() (in module braindecode.augmentation.functional)": [[61, "braindecode.augmentation.functional.frequency_shift", false]], "frequencyshift (class in braindecode.augmentation)": [[43, "braindecode.augmentation.FrequencyShift", false]], "ft_surrogate() (in module braindecode.augmentation.functional)": [[62, "braindecode.augmentation.functional.ft_surrogate", false]], "ftsurrogate (class in braindecode.augmentation)": [[42, "braindecode.augmentation.FTSurrogate", false]], "gaussian_noise() (in module braindecode.augmentation.functional)": [[63, "braindecode.augmentation.functional.gaussian_noise", false]], "gaussiannoise (class in braindecode.augmentation)": [[44, "braindecode.augmentation.GaussianNoise", false]], "get_augmentation_params() (braindecode.augmentation.bandstopfilter method)": [[37, "braindecode.augmentation.BandstopFilter.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.channelsdropout method)": [[38, "braindecode.augmentation.ChannelsDropout.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.channelsshuffle method)": [[39, "braindecode.augmentation.ChannelsShuffle.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.channelssymmetry method)": [[40, "braindecode.augmentation.ChannelsSymmetry.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.frequencyshift method)": [[43, "braindecode.augmentation.FrequencyShift.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.ftsurrogate method)": [[42, "braindecode.augmentation.FTSurrogate.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.gaussiannoise method)": [[44, "braindecode.augmentation.GaussianNoise.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.maskencoding method)": [[46, "braindecode.augmentation.MaskEncoding.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.mixup method)": [[47, "braindecode.augmentation.Mixup.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.segmentationreconstruction method)": [[48, "braindecode.augmentation.SegmentationReconstruction.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.sensorsrotation method)": [[49, "braindecode.augmentation.SensorsRotation.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.smoothtimemask method)": [[54, "braindecode.augmentation.SmoothTimeMask.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.transform method)": [[56, "braindecode.augmentation.Transform.get_augmentation_params", false]], "get_classifier() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.get_classifier", false]], "get_fc_size() (braindecode.models.eegconformer method)": [[95, "braindecode.models.EEGConformer.get_fc_size", false]], "get_iterator() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.get_iterator", false]], "get_iterator() (braindecode.regressor.eegregressor method)": [[132, "braindecode.regressor.EEGRegressor.get_iterator", false]], "get_loss() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.get_loss", false]], "get_metadata() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.get_metadata", false]], "get_num_layers() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.get_num_layers", false]], "get_output_shape() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.get_output_shape", false]], "get_torchinfo_statistics() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.get_torchinfo_statistics", false]], "hgd (class in braindecode.datasets)": [[77, "braindecode.datasets.HGD", false]], "hybridnet (class in braindecode.models)": [[106, "braindecode.models.HybridNet", false]], "identity() (in module braindecode.augmentation.functional)": [[64, "braindecode.augmentation.functional.identity", false]], "identitytransform (class in braindecode.augmentation)": [[45, "braindecode.augmentation.IdentityTransform", false]], "info (braindecode.samplers.recordingsampler attribute)": [[134, "braindecode.samplers.RecordingSampler.info", false]], "info (braindecode.samplers.sequencesampler attribute)": [[136, "braindecode.samplers.SequenceSampler.info", false]], "initialized_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.initialized_", false]], "initialized_ (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor.initialized_", false]], "labram (class in braindecode.models)": [[107, "braindecode.models.Labram", false]], "load_concat_dataset() (in module braindecode.datautil)": [[87, "braindecode.datautil.load_concat_dataset", false]], "load_state_dict() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.load_state_dict", false]], "mask_encoding() (in module braindecode.augmentation.functional)": [[65, "braindecode.augmentation.functional.mask_encoding", false]], "maskencoding (class in braindecode.augmentation)": [[46, "braindecode.augmentation.MaskEncoding", false]], "mixup (class in braindecode.augmentation)": [[47, "braindecode.augmentation.Mixup", false]], "mixup() (in module braindecode.augmentation.functional)": [[66, "braindecode.augmentation.functional.mixup", false]], "mixup_criterion() (in module braindecode.training)": [[142, "braindecode.training.mixup_criterion", false]], "moabbdataset (class in braindecode.datasets)": [[78, "braindecode.datasets.MOABBDataset", false]], "module": [[0, "module-braindecode", false]], "module_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.module_", false]], "module_ (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor.module_", false]], "modules() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.modules", false]], "n_recordings (braindecode.samplers.recordingsampler attribute)": [[134, "braindecode.samplers.RecordingSampler.n_recordings", false]], "nmt (class in braindecode.datasets)": [[79, "braindecode.datasets.NMT", false]], "on_batch_end() (braindecode.training.croppedtrialepochscoring method)": [[139, "braindecode.training.CroppedTrialEpochScoring.on_batch_end", false]], "on_epoch_end() (braindecode.training.croppedtimeseriesepochscoring method)": [[138, "braindecode.training.CroppedTimeSeriesEpochScoring.on_epoch_end", false]], "on_epoch_end() (braindecode.training.croppedtrialepochscoring method)": [[139, "braindecode.training.CroppedTrialEpochScoring.on_epoch_end", false]], "on_epoch_end() (braindecode.training.postepochtrainscoring method)": [[140, "braindecode.training.PostEpochTrainScoring.on_epoch_end", false]], "operation() (braindecode.augmentation.bandstopfilter static method)": [[37, "braindecode.augmentation.BandstopFilter.operation", false]], "operation() (braindecode.augmentation.channelsdropout static method)": [[38, "braindecode.augmentation.ChannelsDropout.operation", false]], "operation() (braindecode.augmentation.channelsshuffle static method)": [[39, "braindecode.augmentation.ChannelsShuffle.operation", false]], "operation() (braindecode.augmentation.channelssymmetry static method)": [[40, "braindecode.augmentation.ChannelsSymmetry.operation", false]], "operation() (braindecode.augmentation.frequencyshift static method)": [[43, "braindecode.augmentation.FrequencyShift.operation", false]], "operation() (braindecode.augmentation.ftsurrogate static method)": [[42, "braindecode.augmentation.FTSurrogate.operation", false]], "operation() (braindecode.augmentation.gaussiannoise static method)": [[44, "braindecode.augmentation.GaussianNoise.operation", false]], "operation() (braindecode.augmentation.identitytransform static method)": [[45, "braindecode.augmentation.IdentityTransform.operation", false]], "operation() (braindecode.augmentation.maskencoding static method)": [[46, "braindecode.augmentation.MaskEncoding.operation", false]], "operation() (braindecode.augmentation.mixup static method)": [[47, "braindecode.augmentation.Mixup.operation", false]], "operation() (braindecode.augmentation.segmentationreconstruction static method)": [[48, "braindecode.augmentation.SegmentationReconstruction.operation", false]], "operation() (braindecode.augmentation.sensorsrotation static method)": [[49, "braindecode.augmentation.SensorsRotation.operation", false]], "operation() (braindecode.augmentation.signflip static method)": [[53, "braindecode.augmentation.SignFlip.operation", false]], "operation() (braindecode.augmentation.smoothtimemask static method)": [[54, "braindecode.augmentation.SmoothTimeMask.operation", false]], "operation() (braindecode.augmentation.timereverse static method)": [[55, "braindecode.augmentation.TimeReverse.operation", false]], "parameters() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.parameters", false]], "pick (class in braindecode.preprocessing)": [[121, "braindecode.preprocessing.Pick", false]], "plot_confusion_matrix() (in module braindecode.visualization)": [[147, "braindecode.visualization.plot_confusion_matrix", false]], "postepochtrainscoring (class in braindecode.training)": [[140, "braindecode.training.PostEpochTrainScoring", false]], "predict() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.predict", false]], "predict_proba() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.predict_proba", false]], "predict_proba() (braindecode.regressor.eegregressor method)": [[132, "braindecode.regressor.EEGRegressor.predict_proba", false]], "predict_trials() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.predict_trials", false]], "predict_trials() (braindecode.regressor.eegregressor method)": [[132, "braindecode.regressor.EEGRegressor.predict_trials", false]], "predict_trials() (in module braindecode.training)": [[143, "braindecode.training.predict_trials", false]], "prefixes_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.prefixes_", false]], "prefixes_ (braindecode.regressor.eegregressor attribute)": [[132, "braindecode.regressor.EEGRegressor.prefixes_", false]], "preprocess() (in module braindecode.preprocessing)": [[131, "braindecode.preprocessing.preprocess", false]], "preprocessor (class in braindecode.preprocessing)": [[122, "braindecode.preprocessing.Preprocessor", false]], "presample() (braindecode.samplers.relativepositioningsampler method)": [[135, "braindecode.samplers.RelativePositioningSampler.presample", false]], "recordingsampler (class in braindecode.samplers)": [[134, "braindecode.samplers.RecordingSampler", false]], "relativepositioningsampler (class in braindecode.samplers)": [[135, "braindecode.samplers.RelativePositioningSampler", false]], "resample (class in braindecode.preprocessing)": [[123, "braindecode.preprocessing.Resample", false]], "reset_classifier() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.reset_classifier", false]], "sample_class() (braindecode.samplers.balancedsequencesampler method)": [[133, "braindecode.samplers.BalancedSequenceSampler.sample_class", false]], "sample_recording() (braindecode.samplers.recordingsampler method)": [[134, "braindecode.samplers.RecordingSampler.sample_recording", false]], "sample_window() (braindecode.samplers.recordingsampler method)": [[134, "braindecode.samplers.RecordingSampler.sample_window", false]], "save() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.save", false]], "save_concat_dataset() (in module braindecode.datautil)": [[88, "braindecode.datautil.save_concat_dataset", false]], "segmentation_reconstruction() (in module braindecode.augmentation.functional)": [[67, "braindecode.augmentation.functional.segmentation_reconstruction", false]], "segmentationreconstruction (class in braindecode.augmentation)": [[48, "braindecode.augmentation.SegmentationReconstruction", false]], "sensors_rotation() (in module braindecode.augmentation.functional)": [[68, "braindecode.augmentation.functional.sensors_rotation", false]], "sensorsrotation (class in braindecode.augmentation)": [[49, "braindecode.augmentation.SensorsRotation", false]], "sensorsxrotation (class in braindecode.augmentation)": [[50, "braindecode.augmentation.SensorsXRotation", false]], "sensorsyrotation (class in braindecode.augmentation)": [[51, "braindecode.augmentation.SensorsYRotation", false]], "sensorszrotation (class in braindecode.augmentation)": [[52, "braindecode.augmentation.SensorsZRotation", false]], "sequencesampler (class in braindecode.samplers)": [[136, "braindecode.samplers.SequenceSampler", false]], "set_description() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.set_description", false]], "set_description() (braindecode.datasets.basedataset method)": [[76, "braindecode.datasets.BaseDataset.set_description", false]], "set_description() (braindecode.datasets.windowsdataset method)": [[83, "braindecode.datasets.WindowsDataset.set_description", false]], "set_random_seeds() (in module braindecode.util)": [[145, "braindecode.util.set_random_seeds", false]], "seteegreference (class in braindecode.preprocessing)": [[124, "braindecode.preprocessing.SetEEGReference", false]], "shallowfbcspnet (class in braindecode.models)": [[109, "braindecode.models.ShallowFBCSPNet", false]], "sign_flip() (in module braindecode.augmentation.functional)": [[69, "braindecode.augmentation.functional.sign_flip", false]], "signflip (class in braindecode.augmentation)": [[53, "braindecode.augmentation.SignFlip", false]], "sleepphysionet (class in braindecode.datasets)": [[80, "braindecode.datasets.SleepPhysionet", false]], "sleepstagerblanco2020 (class in braindecode.models)": [[110, "braindecode.models.SleepStagerBlanco2020", false]], "sleepstagerchambon2018 (class in braindecode.models)": [[111, "braindecode.models.SleepStagerChambon2018", false]], "sleepstagereldele2021 (class in braindecode.models)": [[112, "braindecode.models.SleepStagerEldele2021", false]], "smooth_time_mask() (in module braindecode.augmentation.functional)": [[70, "braindecode.augmentation.functional.smooth_time_mask", false]], "smoothtimemask (class in braindecode.augmentation)": [[54, "braindecode.augmentation.SmoothTimeMask", false]], "sparcnet (class in braindecode.models)": [[108, "braindecode.models.SPARCNet", false]], "split() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.split", false]], "syncnet (class in braindecode.models)": [[113, "braindecode.models.SyncNet", false]], "tcn (class in braindecode.models)": [[114, "braindecode.models.TCN", false]], "tidnet (class in braindecode.models)": [[115, "braindecode.models.TIDNet", false]], "time_reverse() (in module braindecode.augmentation.functional)": [[71, "braindecode.augmentation.functional.time_reverse", false]], "timedistributed (class in braindecode.models)": [[116, "braindecode.models.TimeDistributed", false]], "timereverse (class in braindecode.augmentation)": [[55, "braindecode.augmentation.TimeReverse", false]], "timeseriesloss (class in braindecode.training)": [[141, "braindecode.training.TimeSeriesLoss", false]], "to_dense_prediction_model() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.to_dense_prediction_model", false]], "torch_stft() (braindecode.models.contrawr method)": [[92, "braindecode.models.ContraWR.torch_stft", false]], "transform (class in braindecode.augmentation)": [[56, "braindecode.augmentation.Transform", false]], "trial_preds_from_window_preds() (in module braindecode.training)": [[144, "braindecode.training.trial_preds_from_window_preds", false]], "tuh (class in braindecode.datasets)": [[81, "braindecode.datasets.TUH", false]], "tuhabnormal (class in braindecode.datasets)": [[82, "braindecode.datasets.TUHAbnormal", false]], "usleep (class in braindecode.models)": [[117, "braindecode.models.USleep", false]], "windowsdataset (class in braindecode.datasets)": [[83, "braindecode.datasets.WindowsDataset", false]]}, "objects": {"": [[0, 0, 0, "-", "braindecode"]], "braindecode.augmentation": [[36, 1, 1, "", "AugmentedDataLoader"], [37, 1, 1, "", "BandstopFilter"], [38, 1, 1, "", "ChannelsDropout"], [39, 1, 1, "", "ChannelsShuffle"], [40, 1, 1, "", "ChannelsSymmetry"], [41, 1, 1, "", "Compose"], [42, 1, 1, "", "FTSurrogate"], [43, 1, 1, "", "FrequencyShift"], [44, 1, 1, "", "GaussianNoise"], [45, 1, 1, "", "IdentityTransform"], [46, 1, 1, "", "MaskEncoding"], [47, 1, 1, "", "Mixup"], [48, 1, 1, "", "SegmentationReconstruction"], [49, 1, 1, "", "SensorsRotation"], [50, 1, 1, "", "SensorsXRotation"], [51, 1, 1, "", "SensorsYRotation"], [52, 1, 1, "", "SensorsZRotation"], [53, 1, 1, "", "SignFlip"], [54, 1, 1, "", "SmoothTimeMask"], [55, 1, 1, "", "TimeReverse"], [56, 1, 1, "", "Transform"]], "braindecode.augmentation.BandstopFilter": [[37, 2, 1, "", "get_augmentation_params"], [37, 2, 1, "", "operation"]], "braindecode.augmentation.ChannelsDropout": [[38, 2, 1, "", "get_augmentation_params"], [38, 2, 1, "", "operation"]], "braindecode.augmentation.ChannelsShuffle": [[39, 2, 1, "", "get_augmentation_params"], [39, 2, 1, "", "operation"]], "braindecode.augmentation.ChannelsSymmetry": [[40, 2, 1, "", "get_augmentation_params"], [40, 2, 1, "", "operation"]], "braindecode.augmentation.Compose": [[41, 2, 1, "", "forward"]], "braindecode.augmentation.FTSurrogate": [[42, 2, 1, "", "get_augmentation_params"], [42, 2, 1, "", "operation"]], "braindecode.augmentation.FrequencyShift": [[43, 2, 1, "", "get_augmentation_params"], [43, 2, 1, "", "operation"]], "braindecode.augmentation.GaussianNoise": [[44, 2, 1, "", "get_augmentation_params"], [44, 2, 1, "", "operation"]], "braindecode.augmentation.IdentityTransform": [[45, 2, 1, "", "operation"]], "braindecode.augmentation.MaskEncoding": [[46, 2, 1, "", "get_augmentation_params"], [46, 2, 1, "", "operation"]], "braindecode.augmentation.Mixup": [[47, 2, 1, "", "get_augmentation_params"], [47, 2, 1, "", "operation"]], "braindecode.augmentation.SegmentationReconstruction": [[48, 2, 1, "", "get_augmentation_params"], [48, 2, 1, "", "operation"]], "braindecode.augmentation.SensorsRotation": [[49, 2, 1, "", "get_augmentation_params"], [49, 2, 1, "", "operation"]], "braindecode.augmentation.SignFlip": [[53, 2, 1, "", "operation"]], "braindecode.augmentation.SmoothTimeMask": [[54, 2, 1, "", "get_augmentation_params"], [54, 2, 1, "", "operation"]], "braindecode.augmentation.TimeReverse": [[55, 2, 1, "", "operation"]], "braindecode.augmentation.Transform": [[56, 2, 1, "", "forward"], [56, 2, 1, "", "get_augmentation_params"]], "braindecode.augmentation.functional": [[57, 3, 1, "", "bandstop_filter"], [58, 3, 1, "", "channels_dropout"], [59, 3, 1, "", "channels_permute"], [60, 3, 1, "", "channels_shuffle"], [61, 3, 1, "", "frequency_shift"], [62, 3, 1, "", "ft_surrogate"], [63, 3, 1, "", "gaussian_noise"], [64, 3, 1, "", "identity"], [65, 3, 1, "", "mask_encoding"], [66, 3, 1, "", "mixup"], [67, 3, 1, "", "segmentation_reconstruction"], [68, 3, 1, "", "sensors_rotation"], [69, 3, 1, "", "sign_flip"], [70, 3, 1, "", "smooth_time_mask"], [71, 3, 1, "", "time_reverse"]], "braindecode.classifier": [[72, 1, 1, "", "EEGClassifier"]], "braindecode.classifier.EEGClassifier": [[72, 4, 1, "", "_criteria"], [72, 4, 1, "", "_modules"], [72, 4, 1, "", "_optimizers"], [72, 4, 1, "", "callbacks_"], [72, 4, 1, "", "classes_"], [72, 4, 1, "", "criterion_"], [72, 4, 1, "", "cuda_dependent_attributes_"], [72, 2, 1, "", "get_iterator"], [72, 2, 1, "", "get_loss"], [72, 4, 1, "", "initialized_"], [72, 4, 1, "", "module_"], [72, 2, 1, "", "predict"], [72, 2, 1, "", "predict_proba"], [72, 2, 1, "", "predict_trials"], [72, 4, 1, "", "prefixes_"]], "braindecode.datasets": [[73, 1, 1, "", "BCICompetitionIVDataset4"], [74, 1, 1, "", "BNCI2014001"], [75, 1, 1, "", "BaseConcatDataset"], [76, 1, 1, "", "BaseDataset"], [77, 1, 1, "", "HGD"], [78, 1, 1, "", "MOABBDataset"], [79, 1, 1, "", "NMT"], [80, 1, 1, "", "SleepPhysionet"], [81, 1, 1, "", "TUH"], [82, 1, 1, "", "TUHAbnormal"], [83, 1, 1, "", "WindowsDataset"], [84, 3, 1, "", "create_from_X_y"], [85, 3, 1, "", "create_from_mne_epochs"], [86, 3, 1, "", "create_from_mne_raw"]], "braindecode.datasets.BCICompetitionIVDataset4": [[73, 2, 1, "", "download"]], "braindecode.datasets.BaseConcatDataset": [[75, 2, 1, "", "get_metadata"], [75, 2, 1, "", "save"], [75, 2, 1, "", "set_description"], [75, 2, 1, "", "split"]], "braindecode.datasets.BaseDataset": [[76, 2, 1, "", "set_description"]], "braindecode.datasets.WindowsDataset": [[83, 2, 1, "", "set_description"]], "braindecode.datautil": [[87, 3, 1, "", "load_concat_dataset"], [88, 3, 1, "", "save_concat_dataset"]], "braindecode.models": [[89, 1, 1, "", "ATCNet"], [90, 1, 1, "", "AttentionBaseNet"], [91, 1, 1, "", "BIOT"], [92, 1, 1, "", "ContraWR"], [93, 1, 1, "", "Deep4Net"], [94, 1, 1, "", "DeepSleepNet"], [95, 1, 1, "", "EEGConformer"], [96, 1, 1, "", "EEGITNet"], [97, 1, 1, "", "EEGInceptionERP"], [98, 1, 1, "", "EEGInceptionMI"], [99, 1, 1, "", "EEGModuleMixin"], [100, 1, 1, "", "EEGNeX"], [101, 1, 1, "", "EEGNetv1"], [102, 1, 1, "", "EEGNetv4"], [103, 1, 1, "", "EEGResNet"], [104, 1, 1, "", "EEGSimpleConv"], [105, 1, 1, "", "EEGTCNet"], [106, 1, 1, "", "HybridNet"], [107, 1, 1, "", "Labram"], [108, 1, 1, "", "SPARCNet"], [109, 1, 1, "", "ShallowFBCSPNet"], [110, 1, 1, "", "SleepStagerBlanco2020"], [111, 1, 1, "", "SleepStagerChambon2018"], [112, 1, 1, "", "SleepStagerEldele2021"], [113, 1, 1, "", "SyncNet"], [114, 1, 1, "", "TCN"], [115, 1, 1, "", "TIDNet"], [116, 1, 1, "", "TimeDistributed"], [117, 1, 1, "", "USleep"]], "braindecode.models.ATCNet": [[89, 2, 1, "", "forward"]], "braindecode.models.AttentionBaseNet": [[90, 2, 1, "", "forward"]], "braindecode.models.BIOT": [[91, 2, 1, "", "forward"]], "braindecode.models.ContraWR": [[92, 2, 1, "", "forward"], [92, 2, 1, "", "torch_stft"]], "braindecode.models.DeepSleepNet": [[94, 2, 1, "", "forward"]], "braindecode.models.EEGConformer": [[95, 2, 1, "", "forward"], [95, 2, 1, "", "get_fc_size"]], "braindecode.models.EEGInceptionMI": [[98, 2, 1, "", "forward"]], "braindecode.models.EEGModuleMixin": [[99, 2, 1, "", "forward"], [99, 2, 1, "", "get_output_shape"], [99, 2, 1, "", "get_torchinfo_statistics"], [99, 2, 1, "", "load_state_dict"], [99, 2, 1, "", "modules"], [99, 2, 1, "", "parameters"], [99, 2, 1, "", "to_dense_prediction_model"]], "braindecode.models.EEGNeX": [[100, 2, 1, "", "calc_padding"], [100, 2, 1, "", "forward"]], "braindecode.models.EEGSimpleConv": [[104, 2, 1, "", "forward"]], "braindecode.models.EEGTCNet": [[105, 2, 1, "", "forward"]], "braindecode.models.HybridNet": [[106, 2, 1, "", "forward"]], "braindecode.models.Labram": [[107, 2, 1, "", "fix_init_weight_and_init_embedding"], [107, 2, 1, "", "forward"], [107, 2, 1, "", "forward_features"], [107, 2, 1, "", "get_classifier"], [107, 2, 1, "", "get_num_layers"], [107, 2, 1, "", "reset_classifier"]], "braindecode.models.SPARCNet": [[108, 2, 1, "", "forward"]], "braindecode.models.SleepStagerBlanco2020": [[110, 2, 1, "", "forward"]], "braindecode.models.SleepStagerChambon2018": [[111, 2, 1, "", "forward"]], "braindecode.models.SleepStagerEldele2021": [[112, 2, 1, "", "forward"]], "braindecode.models.SyncNet": [[113, 2, 1, "", "forward"]], "braindecode.models.TCN": [[114, 2, 1, "", "forward"]], "braindecode.models.TIDNet": [[115, 2, 1, "", "forward"]], "braindecode.models.TimeDistributed": [[116, 2, 1, "", "forward"]], "braindecode.models.USleep": [[117, 2, 1, "", "forward"]], "braindecode.preprocessing": [[118, 1, 1, "", "Crop"], [119, 1, 1, "", "DropChannels"], [120, 1, 1, "", "Filter"], [121, 1, 1, "", "Pick"], [122, 1, 1, "", "Preprocessor"], [123, 1, 1, "", "Resample"], [124, 1, 1, "", "SetEEGReference"], [125, 3, 1, "", "create_fixed_length_windows"], [126, 3, 1, "", "create_windows_from_events"], [127, 3, 1, "", "create_windows_from_target_channels"], [128, 3, 1, "", "exponential_moving_demean"], [129, 3, 1, "", "exponential_moving_standardize"], [130, 3, 1, "", "filterbank"], [131, 3, 1, "", "preprocess"]], "braindecode.preprocessing.Preprocessor": [[122, 2, 1, "", "apply"]], "braindecode.regressor": [[132, 1, 1, "", "EEGRegressor"]], "braindecode.regressor.EEGRegressor": [[132, 4, 1, "", "_criteria"], [132, 4, 1, "", "_modules"], [132, 4, 1, "", "_optimizers"], [132, 4, 1, "", "callbacks_"], [132, 4, 1, "", "criterion_"], [132, 4, 1, "", "cuda_dependent_attributes_"], [132, 2, 1, "", "fit"], [132, 2, 1, "", "get_iterator"], [132, 4, 1, "", "initialized_"], [132, 4, 1, "", "module_"], [132, 2, 1, "", "predict_proba"], [132, 2, 1, "", "predict_trials"], [132, 4, 1, "", "prefixes_"]], "braindecode.samplers": [[133, 1, 1, "", "BalancedSequenceSampler"], [134, 1, 1, "", "RecordingSampler"], [135, 1, 1, "", "RelativePositioningSampler"], [136, 1, 1, "", "SequenceSampler"]], "braindecode.samplers.BalancedSequenceSampler": [[133, 2, 1, "", "sample_class"]], "braindecode.samplers.RecordingSampler": [[134, 4, 1, "", "info"], [134, 4, 1, "", "n_recordings"], [134, 2, 1, "", "sample_recording"], [134, 2, 1, "", "sample_window"]], "braindecode.samplers.RelativePositioningSampler": [[135, 2, 1, "", "presample"]], "braindecode.samplers.SequenceSampler": [[136, 4, 1, "", "file_ids"], [136, 4, 1, "", "info"]], "braindecode.training": [[137, 1, 1, "", "CroppedLoss"], [138, 1, 1, "", "CroppedTimeSeriesEpochScoring"], [139, 1, 1, "", "CroppedTrialEpochScoring"], [140, 1, 1, "", "PostEpochTrainScoring"], [141, 1, 1, "", "TimeSeriesLoss"], [142, 3, 1, "", "mixup_criterion"], [143, 3, 1, "", "predict_trials"], [144, 3, 1, "", "trial_preds_from_window_preds"]], "braindecode.training.CroppedLoss": [[137, 2, 1, "", "forward"]], "braindecode.training.CroppedTimeSeriesEpochScoring": [[138, 2, 1, "", "on_epoch_end"]], "braindecode.training.CroppedTrialEpochScoring": [[139, 2, 1, "", "on_batch_end"], [139, 2, 1, "", "on_epoch_end"]], "braindecode.training.PostEpochTrainScoring": [[140, 2, 1, "", "on_epoch_end"]], "braindecode.training.TimeSeriesLoss": [[141, 2, 1, "", "forward"]], "braindecode.util": [[145, 3, 1, "", "set_random_seeds"]], "braindecode.visualization": [[146, 3, 1, "", "compute_amplitude_gradients"], [147, 3, 1, "", "plot_confusion_matrix"]]}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "method", "Python method"], "3": ["py", "function", "Python function"], "4": ["py", "attribute", "Python attribute"]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:method", "3": "py:function", "4": "py:attribute"}, "terms": {"": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 21, 22, 26, 27, 28, 30, 31, 32, 40, 42, 44, 48, 49, 50, 51, 52, 59, 62, 63, 68, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 89, 97, 98, 101, 102, 107, 108, 111, 114, 117, 119, 120, 122, 124, 132, 133, 137, 140, 141], "0": [2, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 34, 37, 38, 39, 42, 44, 45, 46, 47, 56, 58, 60, 62, 66, 72, 74, 75, 79, 80, 81, 82, 86, 89, 90, 91, 92, 93, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 123, 124, 125, 126, 128, 129, 131, 132, 134, 143, 147, 153], "00": [6, 10, 13, 16, 23, 26, 27, 32, 33, 34, 153], "000": [5, 16, 17, 18, 19, 22, 23, 31, 34, 153], "0000": [2, 3, 8, 27, 28, 29, 30, 31], "00000000": 22, "00000058": 22, "0000625": 30, "00009932": 22, "0001": [2, 30, 103, 129], "00012331": 22, "00014928": 22, "0002": [2, 3, 28], "0004": 2, "0005": [2, 3, 22, 28, 31], "000525": 22, "0006": [2, 3, 8, 27, 28, 29], "000625": 29, "001": [3, 4, 18, 20, 21, 27, 28, 29, 30, 31, 74, 107, 128, 129], "0010": 31, "0014": 30, "0019": 29, "00267": 35, "004": 11, "0040": 5, "00622": 105, "00625": [29, 30], "0063": [29, 30], "0080": 26, "0081": 26, "0082": 26, "0084": 26, "0094": 26, "00it": 32, "00m": 16, "01": [2, 3, 4, 6, 8, 16, 23, 26, 27, 28, 29, 32, 33, 72, 97, 132, 153], "011": 11, "01271": 114, "0158": 26, "0165": 22, "0168": [22, 29], "0177": 30, "019": [2, 8, 73, 110], "0193": 35, "0194": 16, "01_tcp_ar": 22, "01m39": 16, "02": [6, 11, 16, 23, 26, 27, 33, 91, 92, 107, 108, 153], "0260": 22, "0261": 8, "0273": 22, "02736802": 22, "0280": 22, "0285": 29, "02_tcp_le": 22, "02m": 16, "03": [9, 10, 11, 13, 16, 27, 90, 107, 153], "0308": 22, "0308012": 22, "0311": 22, "0312": 29, "033339": 32, "0364": 29, "0374": 29, "0381": 8, "03_tcp_ar_a": 22, "03m": 16, "04": [3, 4, 6, 11, 13, 16, 23, 26, 27, 28, 29, 32, 153], "0408": 22, "04174": 110, "0419": 22, "04194231": 22, "0426": 22, "044": [3, 4, 28, 29, 32], "0448": 22, "046014": 98, "046020": 4, "0461": 8, "0467": 31, "04871": [37, 44, 54, 57, 63, 70], "04m": 16, "05": [6, 10, 11, 12, 16, 27, 30, 81, 82, 113, 115], "0506": 22, "0508": 22, "0517": 29, "0537782": 22, "0538": 22, "05458383": 22, "0546": 22, "0555": 29, "056008": 115, "059": [8, 13, 153], "0593": 22, "05it": 32, "05m": 16, "06": [2, 8, 10, 11, 16, 27], "060": 11, "060518": 32, "0613": 31, "0625": [2, 3, 4, 8, 27, 28, 29, 32], "063": [4, 6, 153], "06366": 107, "066011": [28, 29, 30], "0678": [2, 8, 73], "0679": 30, "0690": 30, "06it": 32, "06m": 16, "07": [10, 13, 16, 27, 29, 33, 153], "0702": 28, "0703125": 117, "07159": 104, "0748": 29, "0764": 29, "07it": 32, "08": [16, 27], "08024": [101, 102], "0806": 8, "0815": 30, "0847": 29, "08675": [42, 62], "0888": 9, "08it": 32, "08m": 16, "09": [16, 27], "090": [5, 6, 153], "09237": 31, "0925": 31, "0927": 2, "09412": [47, 66, 142], "0944": 8, "0966": 9, "0967": 9, "09702": [40, 59], "0981": 29, "099": 22, "09m": 16, "0kb": 27, "0m": [16, 27], "0mb": 27, "0test": 29, "0train": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32], "0x7f9f72dcf250": 21, "0x7f9f7b4c6fb0": 11, "0x7f9f81a78580": 30, "0x7f9f81a8ff40": 27, "0x7f9f81ad4ee0": 18, "0x7f9f81aff220": 16, "0x7f9f81ec4280": 16, "0x7f9f820894e0": [4, 16], "0x7f9f82089570": 9, "0x7f9f8f339570": 10, "0x7f9f8f33b460": 10, "0x7fa044128b80": 21, "0x7fa044129510": 21, "0x7fa044129690": 21, "0x7fa04412a530": 16, "0x7fa044ed1a20": 3, "0x7fa044ed28c0": 5, "0x7fa044ee1bd0": 9, "0x7fa044ef5600": 9, "0x7fa044ef7760": 5, "0x7fa04530aad0": 8, "0x7fa045570ca0": 2, "0x7fa04674ad70": 32, "0x7fa046758040": 21, "0x7fa04675acb0": 21, "0x7fa04675b130": 21, "0x7fa04675b2e0": 21, "0x7fa04675b370": 21, "0x7fa04675b3a0": 21, "0x7fa04675b6d0": 21, "0x7fa04675b760": 21, "0x7fa04675b820": 21, "0x7fa04675b850": 21, "0x7fa04675ba30": 21, "0x7fa04675bb20": 21, "0x7fa04675bbb0": 21, "0x7fa04735e8c0": 21, "0x7fa04735f700": 21, "0x7fa0473916c0": 5, "0x7fa0473e24a0": 28, "0x7fa05c159780": 31, "0x7fa05c1fa770": 29, "0x7fa05c1fba60": 5, "1": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 30, 31, 33, 37, 38, 39, 40, 42, 44, 45, 46, 47, 48, 49, 50, 51, 52, 54, 56, 57, 58, 59, 60, 62, 63, 65, 66, 67, 68, 70, 72, 73, 74, 75, 77, 79, 80, 81, 82, 87, 89, 90, 92, 93, 97, 98, 99, 100, 103, 104, 105, 107, 109, 110, 112, 113, 115, 117, 120, 123, 124, 125, 126, 127, 128, 129, 132, 133, 134, 142, 143, 144, 147, 153], "10": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 35, 40, 49, 50, 51, 52, 68, 72, 73, 81, 82, 89, 93, 95, 96, 97, 103, 105, 106, 107, 109, 110, 112, 115, 120, 124, 132, 133, 147], "100": [3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 20, 26, 27, 28, 29, 30, 31, 32, 37, 54, 74, 91, 93, 104, 108, 117, 123], "1000": [2, 3, 4, 8, 12, 22, 26, 27, 28, 29, 30, 32, 77, 97, 134], "1002": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 147], "1007": 110, "100hz": 112, "101": [5, 9, 10, 11, 12], "102": 11, "1020": [32, 33, 153], "1022": [3, 6, 153], "1024": 26, "1027": 2, "103": [48, 67], "1031": 11, "1038": [2, 8, 73], "103kb": 27, "105": 5, "105475": 100, "1064": 27, "107": [5, 26], "1074": [33, 153], "1075": 29, "108": 11, "1088": [5, 115], "109": [5, 27, 33, 153], "1097": 35, "10m": 16, "11": [2, 3, 4, 5, 8, 10, 11, 12, 13, 16, 17, 18, 19, 20, 21, 27, 28, 29, 31, 32, 33, 73, 94, 153], "110": 11, "1101": [3, 4, 28, 29, 32], "1108": 27, "1109": [10, 89, 96, 97, 112], "1119": 31, "11198": 90, "1121": 2, "1125": [3, 4, 28, 29, 32, 33, 153], "1126": 28, "1145": 22, "1149": 9, "115": 11, "1175": 22, "11754766": 22, "1185": [5, 9, 10, 11, 22], "1194": [5, 9, 10, 11], "11m": 16, "12": [4, 5, 6, 11, 16, 17, 18, 19, 27, 28, 29, 30, 32, 33, 74, 104, 105, 107, 117, 147, 153], "120": [10, 77, 112], "1209": 22, "1209397": 22, "121": [5, 12], "122": 12, "1225": [2, 8, 73], "123": 22, "1231": 27, "1235": [2, 8, 73], "124": [17, 19, 27], "1247": 5, "1249": 22, "12493701": 22, "125": [97, 111], "1251": 22, "1255": 2, "125hz": 112, "126": 11, "1276": 29, "128": [5, 10, 11, 72, 77, 92, 97, 104, 111, 117, 132], "1281": 22, "129": [5, 11], "12m": 16, "13": [5, 9, 10, 11, 13, 16, 17, 19, 26, 27, 32, 77, 80, 91, 92, 108, 120, 130, 153], "1315": 30, "1319": 22, "1322": 22, "133": [10, 11], "1343": [6, 153], "1344": 2, "13440": 77, "1350": 22, "13578887": 22, "1358": 5, "1360": 22, "13694": [38, 39, 58, 60], "1379": 30, "138": 154, "1381": 27, "1387": 30, "13it": 32, "13m": 16, "14": [2, 5, 8, 9, 11, 16, 17, 19, 27, 28, 32, 77, 120, 145], "1409": 22, "1412": 31, "1415": 8, "142": [5, 154], "1422": 22, "1427": 29, "14345092": 22, "144": [4, 74, 104], "1445": 2, "14483": 4, "145": 32, "146": 154, "147": 154, "1471": 10, "1477": [33, 153], "1478": 27, "148": 154, "14827406": 22, "1483": 22, "1486": 22, "1486133": 22, "1487": 29, "149": 22, "15": [5, 9, 10, 11, 12, 14, 16, 26, 27, 28, 29, 30, 49, 50, 51, 52, 79, 90, 95, 109, 115, 120, 123], "150": [9, 10, 11, 77], "1500": [11, 115, 134], "1508": 22, "151": [30, 33, 153], "1512": 2, "152": [11, 154], "1529": 29, "1531": 10, "1535": 22, "15352039": 22, "154": 11, "15447331": 22, "15447332": 22, "1545": 22, "1547": 10, "155": 154, "156": 11, "1564": 29, "15756383": 22, "158": 154, "159": [10, 13, 153, 154], "1594": 11, "15m": 16, "15mb": 27, "16": [5, 9, 10, 11, 16, 27, 30, 89, 90, 100, 102, 108, 111, 120], "160": [11, 77], "16017832": 22, "1602": 22, "1607": 22, "161": [11, 154], "16104": [5, 135], "1611": [101, 102], "163": 11, "164": 154, "166": 154, "1662": 35, "167": [16, 23, 153, 154], "1671": 3, "1677": 22, "169": 154, "16m": 16, "17": [3, 5, 6, 11, 16, 27, 104, 108, 115, 153], "170": [5, 154], "1707": 11, "171": 154, "1710": [47, 66, 142], "1716": 2, "172": [31, 33, 153], "1729": 22, "1741": 115, "174715": 32, "1749": 29, "1753": 31, "1755": 2, "176": [10, 19], "176596": 32, "1768": 22, "178": 154, "1792846": 22, "1793": 22, "1795": 10, "17m": 16, "18": [4, 5, 11, 12, 16, 27, 98, 154], "180": 11, "1803": [40, 59, 114], "1806": [42, 62], "1807": 22, "1811": 10, "1829": 28, "185": 154, "1853": 11, "188": 11, "1882": 22, "1885": 10, "189": 32, "18m": 16, "19": [5, 9, 10, 11, 16, 27, 118, 124], "1904": 31, "1915": 29, "192104": 32, "194": 9, "1941": 3, "195": 11, "1955": 10, "1963": 29, "197": [11, 154], "19750": 16, "1975000": 16, "198": 154, "199": 154, "1990": 2, "1998": 94, "19999": [17, 19], "19it": 32, "19k": 27, "19m": 16, "1_": 89, "1d": [98, 104], "1e": [2, 3, 4, 8, 9, 10, 11, 27, 28, 29, 30, 32], "1e6": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32], "1f": [12, 32], "1hz": 37, "1m": [16, 27], "1mb": 27, "1test": [3, 4, 20, 21, 27, 28, 29, 30, 32], "2": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 30, 31, 37, 38, 39, 42, 43, 44, 47, 54, 57, 62, 63, 66, 70, 72, 74, 77, 79, 80, 89, 92, 93, 97, 99, 100, 101, 102, 103, 104, 105, 110, 112, 113, 115, 117, 120, 124, 129, 132, 133, 134, 142, 143], "20": [5, 9, 10, 11, 12, 16, 26, 27, 29, 31, 32, 40, 49, 50, 51, 52, 68, 92, 103, 110, 124], "200": [2, 8, 10, 11, 14, 91, 93, 107], "2000": [5, 9, 10, 11, 22, 134], "20000": 17, "2004": 77, "2006": 105, "2007": [5, 37, 44, 54, 57, 63, 70, 135], "2008": [77, 94], "2010": [38, 39, 58, 60, 77], "2012": [27, 28, 29, 30], "2013": 35, "2014": [31, 74], "2015": [48, 67], "2016": 101, "2017": [26, 27, 28, 29, 30, 31, 35, 49, 50, 51, 52, 68, 77, 93, 94, 103, 106, 109, 113, 147], "2018": [5, 9, 10, 28, 29, 30, 40, 42, 44, 47, 59, 62, 63, 66, 102, 111, 114], "2019": [2, 8, 31, 73], "202": 26, "2020": [5, 37, 38, 39, 44, 54, 57, 58, 60, 63, 70, 97, 105, 110, 115, 135], "20200220": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "2021": [4, 10, 11, 97, 98, 112, 117, 133], "2022": [4, 30, 79, 89, 95, 96, 97], "2023": [90, 91, 92, 104, 108], "2024": [46, 90, 91, 92, 100, 107, 108], "2025": 113, "2031": 22, "2036": 9, "2037": 22, "2040": 11, "2058": 2, "2069": 30, "206k": 16, "209k": 27, "20m": 16, "21": [5, 9, 10, 11, 16, 23, 27, 31, 124, 153], "2102": 9, "2126": 9, "2136": 9, "2137": 22, "214": 11, "21543634": 22, "216": 11, "2186": 10, "2196f3": 29, "22": [3, 4, 5, 9, 11, 16, 17, 19, 27, 28, 29, 32, 33, 74], "2206": 4, "2208": 107, "22222222222223": [9, 10, 11], "2224": 11, "223": 154, "22477157": 22, "2247716": 22, "2248": 22, "2249": 22, "224gb": 16, "224kb": 27, "225": 11, "228": 11, "2295": 10, "22m": 16, "23": [2, 5, 9, 10, 11, 16, 27, 119], "2309": 104, "2310": 90, "232164": 20, "2324": 9, "2331": 10, "2348": 30, "236566": 32, "237": 11, "23730": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 147], "2374": 22, "238": [37, 44, 54, 57, 63, 70], "2396": 28, "23it": 32, "23m": 16, "24": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31, 32, 110, 115, 121, 153], "240": [3, 4, 17, 26, 27, 28, 29, 32], "2402": 27, "2414": 30, "2435": 30, "243gb": 27, "244": [5, 9, 16], "246258": 32, "2465": 9, "24m": 16, "25": [2, 5, 8, 9, 11, 12, 14, 16, 27, 29, 31, 32, 74, 89, 90, 93, 94, 95, 97, 101, 102, 105, 109, 111, 120], "250": [5, 20, 27, 74, 89, 95, 98, 103], "2500": [22, 28, 29, 134], "25070": 16, "2507000": 16, "250hz": 74, "2511": 29, "25153176": 22, "2522": 22, "2526": 22, "253": [37, 44, 54, 57, 63, 70], "254": 154, "2548": 29, "2552": 115, "256": [14, 26, 91, 92, 154], "2569": 27, "256hz": 26, "25829056": 22, "2583": 22, "2586": 30, "25878426": 22, "2588": 22, "25e": 30, "25m": 16, "26": [5, 8, 9, 10, 11, 13, 16, 20, 27, 111, 153], "260": 77, "2600": 22, "2609": 30, "261": 154, "2625": 2, "2626": 5, "263": 154, "2639": 3, "2657": 22, "267": 35, "267gb": 27, "269": 154, "2696": 30, "26m": 16, "27": [2, 9, 11, 16, 77], "2731": 2, "274": 154, "2742": 22, "2743": 28, "274k": 16, "2759": 30, "2768": 9, "277": 154, "2778": 29, "2781": 10, "2783": 30, "2790": 2, "27it": 32, "27m": [16, 27], "28": [4, 9, 11, 16, 27, 30, 32, 90, 97], "2818": 8, "282": 154, "28417889": 22, "2847": 27, "287": 154, "2870": 30, "288": [74, 154], "28840": 16, "2884000": 16, "2885": 22, "2888": 9, "2896": 27, "29": [4, 10, 11, 16, 31, 112], "2919": 22, "292": 154, "294": 154, "2944": 28, "295": 154, "2952": 9, "2957": 30, "2975": 22, "298": 32, "2985": 29, "2986": 3, "2997": 22, "2997373": 22, "2999": 31, "29it": 32, "29m": 16, "2a": [1, 6, 20, 21, 24, 25, 26, 28, 29, 30, 32, 33, 36, 38, 41, 42, 43, 53, 54, 56, 75, 78, 89, 98, 99, 109, 122, 126, 129, 131, 137, 145, 147, 153, 154], "2d": [5, 147], "2darrai": 144, "2f": [4, 29, 30, 32], "2k": 16, "2m": [16, 27], "2mb": 27, "2x2": 117, "2\u03c0": 4, "3": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 30, 31, 32, 44, 47, 49, 63, 66, 68, 72, 73, 74, 77, 80, 89, 93, 97, 98, 99, 103, 110, 114, 115, 132, 133, 134, 143, 150, 153, 154], "30": [2, 4, 5, 8, 9, 10, 11, 16, 27, 30, 31, 33, 80, 112, 113, 114, 117, 153], "3000": [11, 22, 31], "3002": 10, "30167542": 22, "302": 11, "3025": 3, "3036": 22, "30362263": 22, "304": [11, 154], "3043": 30, "3048106": 97, "305": 19, "3056": 28, "3076234": [10, 112], "3083": 31, "30m": 16, "31": [5, 9, 10, 11, 16, 26, 27, 95], "3119": 3, "312": 154, "3122": 26, "3125": 32, "313": [19, 23, 153], "314": [21, 23, 153], "3161489": 96, "31628": 145, "3169": 22, "3174": 30, "318": 154, "3194": 3, "3197419": 89, "31m": 16, "32": [4, 5, 9, 10, 11, 16, 26, 27, 46, 89, 92, 100, 101, 115], "3220": 30, "3224": 8, "323": 11, "324": 11, "3259": 3, "32600": 16, "3260000": 16, "327": 154, "3299": 3, "3299779": 22, "33": [4, 6, 9, 11, 16, 27, 29, 33, 153], "3300": 22, "3304": 30, "3315": 11, "3319": 29, "333": 154, "3333": 3, "3359": 8, "337": [11, 13, 153], "338": 11, "3389": 35, "33m": 16, "34": [9, 11, 16], "3406": 22, "3407": 9, "341": 154, "3427": 9, "343kb": 16, "3446": 9, "3448": [9, 30], "3450": 9, "3459": 10, "3464": 11, "347": 154, "349": 154, "34it": 32, "35": [3, 4, 11, 16, 27, 28, 29, 31, 32], "350": 5, "3500": 26, "3513": 31, "353": 154, "3533": 9, "354kb": 16, "3557": 30, "3566": 9, "357355": 32, "3581": 9, "35it": 32, "35m": 16, "36": [3, 4, 9, 11, 16, 27, 28, 29, 32], "3600": [22, 80], "3613": 22, "3615": 9, "3621": 29, "363": 11, "363kb": 16, "364": [3, 4, 28, 29, 32], "3644": 29, "3646": 28, "3648": 22, "365": 154, "3654": 2, "365749": 32, "3662": 9, "367": 154, "368": 11, "3689": 9, "36m": 16, "37": [9, 11, 16, 22, 26, 27, 29], "371": 154, "372": 9, "3730": 22, "373041": 22, "3739": 30, "373kb": 16, "374445": 32, "375": 11, "376": 11, "3762": 30, "377": 11, "3777": 30, "377k": 16, "378": 154, "3793": 30, "3796": 22, "379kb": 16, "37m": 16, "37mb": 27, "38": [3, 4, 11, 16, 27, 28, 29, 30, 31, 32], "381kb": 16, "3829": 22, "382kb": 16, "383": 9, "3830": 30, "3850": 31, "3854": 28, "386": 18, "38658058": 22, "3865806": 22, "3866": [22, 30], "3868": 18, "386kb": 16, "3878": 22, "388": 154, "389": 154, "389kb": 16, "38it": 32, "38m": 16, "39": [11, 16, 22, 27], "390": 154, "391": 154, "3912": 22, "3913": 30, "392kb": 27, "3930": 8, "3931": 28, "3948": 3, "3957": 29, "395kb": 16, "396kb": 16, "397": 154, "3977": 30, "3986": 22, "398kb": 16, "399": 11, "3993": 9, "3996": 22, "399kb": 16, "39it": 32, "39m": 16, "39th": [49, 50, 51, 52, 68], "3a6190": 29, "3d": [49, 68, 154], "3f": 30, "3h": 80, "3k": [16, 27], "3m": [16, 27], "3mb": 27, "4": [1, 3, 4, 5, 6, 7, 9, 10, 11, 13, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 73, 74, 75, 77, 89, 90, 91, 93, 95, 96, 97, 98, 99, 100, 101, 102, 104, 105, 107, 108, 109, 111, 115, 117, 122, 125, 127, 129, 130, 131, 133, 134, 138, 139, 141, 145, 153], "40": [3, 4, 11, 13, 14, 16, 23, 26, 27, 28, 29, 31, 32, 90, 95, 109, 113], "400": [10, 11, 154], "400k": 91, "4013": 9, "402": 154, "4033": 9, "405": 11, "4058": 30, "406": 154, "4067": 110, "4076": 9, "4079": 110, "407kb": 16, "4087": 29, "409": 154, "41": [5, 11, 16, 27], "4101": 30, "4107": 30, "411": 154, "4121": [28, 29], "4122": 22, "413": 154, "4138": 30, "415": 154, "415kb": 16, "417": [79, 154], "417750": 32, "418kb": 16, "4190": 31, "419kb": 16, "41it": 32, "41m": 16, "42": [9, 11, 13, 16, 27, 30, 153], "4217": 29, "421kb": 16, "4221": 30, "423kb": 16, "424": 32, "424kb": 16, "426kb": 16, "427kb": 16, "428": [11, 154], "429": 154, "4298": 9, "42m": 16, "43": [5, 10, 11, 16], "430kb": 16, "431": 154, "4310": 29, "431kb": 16, "4326": 30, "432k": 27, "432kb": 16, "4333": 30, "435kb": 16, "4360": 30, "436kb": 16, "437836": 32, "438274": 32, "4383": 2, "438kb": 16, "4398": 22, "439kb": 16, "44": [11, 16, 27, 77], "4418": 22, "441kb": 16, "442362": 32, "442473": 32, "4425": 30, "4429": 22, "4429058": 22, "442k": 16, "442kb": 16, "443": 154, "4433": 22, "443kb": 16, "4455": [2, 30], "445kb": 16, "446": 154, "447024": 32, "447kb": 16, "4483": 30, "4488": 2, "448kb": 16, "4497": 2, "449kb": 16, "44it": 32, "44m": 16, "45": [4, 5, 11, 16, 27, 29, 33, 153], "450": 16, "4500": 30, "451": 154, "4512": 2, "4517": 9, "4518": 10, "451kb": 16, "452": 11, "452kb": 16, "4535": 22, "453kb": 16, "453x": 35, "454": 154, "4549": 27, "454kb": 16, "455kb": 16, "4562": 2, "4564": 22, "456kb": 16, "457kb": 16, "458kb": 16, "459kb": 16, "45it": 32, "45m": 16, "46": [5, 11, 16, 26, 27], "460": 154, "4604": 22, "4609": 30, "460kb": 16, "461": 154, "461kb": 16, "462kb": 16, "4638": 30, "463kb": 16, "4645": [2, 30], "464kb": 16, "465": 154, "4655": 3, "465kb": 16, "466": 154, "4660": 22, "4664": 22, "4668": 30, "466kb": 16, "467": 154, "467kb": 16, "468": 154, "4686": 2, "469": 5, "4696": 29, "469kb": 16, "46m": 16, "47": [3, 4, 5, 9, 10, 11, 16, 27, 28, 29, 30, 32], "470": 154, "470kb": 16, "471": [49, 50, 51, 52, 68], "4712": 30, "471kb": 16, "472": 154, "472kb": 16, "473": 154, "4739": 2, "473kb": 16, "474": [49, 50, 51, 52, 68], "474kb": 16, "4757": 3, "475kb": 16, "4760": 10, "476kb": 16, "477kb": 16, "478137": 32, "4788": 9, "478kb": 16, "479": 154, "479kb": 16, "47m": 16, "48": [5, 10, 11, 16, 18, 20, 21, 27, 28, 29, 30, 32, 74, 98], "480kb": 16, "481kb": 16, "482": 11, "4822": 30, "4828": 30, "483kb": 16, "484kb": 16, "485": 154, "48550": 105, "4859": 30, "485kb": 16, "486kb": 16, "487": 154, "4870": 29, "487kb": 16, "488": 154, "4880": 5, "488kb": 16, "489": 154, "489kb": 16, "48it": 32, "49": [11, 16, 27, 153], "490": 154, "4904": 30, "490kb": 16, "491": 154, "4919893741607666": 32, "491kb": 16, "4922": 5, "4928": 11, "4929": 10, "492kb": 16, "493kb": 16, "494": 154, "494kb": 16, "495": 154, "495kb": 16, "496kb": 16, "497": 154, "4970": 8, "497kb": 16, "4985": 2, "498kb": 16, "499kb": 16, "49m": 16, "4d": 154, "4f": 5, "4m": [16, 27], "4mb": 27, "4th": 120, "5": [2, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 33, 72, 74, 89, 90, 93, 94, 95, 97, 98, 100, 104, 105, 107, 108, 109, 110, 111, 112, 114, 117, 123, 132, 153], "50": [3, 4, 5, 9, 10, 11, 14, 16, 19, 27, 28, 29, 32, 74, 93, 104], "500": [17, 19, 28, 134, 154], "500hz": 77, "500kb": 16, "501kb": 16, "502kb": 16, "503": 154, "5030": 5, "5033": 22, "503kb": 16, "504": 154, "50407195": 22, "5041": 22, "504kb": 16, "505": 154, "505kb": 16, "5069": 27, "506kb": 16, "507kb": 16, "508k": 16, "508kb": 16, "5093": 2, "509kb": 16, "50it": 32, "50m": 16, "51": [4, 11, 16, 27], "510kb": 16, "511kb": 16, "512": [5, 11], "5120": 5, "512kb": 16, "513": 154, "5134": 2, "5135": 28, "513kb": 16, "514": 154, "514kb": 16, "515": [11, 154], "5157": 28, "515kb": 16, "516186": 32, "5164": 5, "5169721": 22, "516kb": 16, "517": 154, "5170": 22, "5172": 22, "517kb": 16, "518kb": 16, "5196": 9, "519kb": 16, "51m": 16, "52": [11, 16, 26], "520": [11, 154], "5201": 22, "520kb": 16, "5210943": 22, "5211": [5, 22], "5215": 5, "521kb": 16, "522": 11, "522kb": 16, "523": 154, "5234": 5, "52350": 16, "5235000": 16, "523kb": 16, "524": 154, "5245": 5, "524kb": 16, "525kb": 16, "5266": 3, "5269": 9, "526kb": 16, "5272": 5, "527kb": 16, "528": 154, "528kb": 16, "529": 154, "5294": 9, "5297": 28, "529kb": 16, "52it": 32, "52m": 16, "53": [16, 22], "5307": 5, "530kb": 16, "531kb": 16, "532kb": 16, "5333": 5, "533kb": 16, "534kb": 16, "535": 154, "5356": 2, "535kb": 16, "536": 11, "5369": 30, "536kb": 16, "537kb": 16, "538": 154, "538kb": 16, "539": 154, "5391": [5, 27, 28, 29, 30, 31], "53910": 16, "5391000": 16, "5395": 22, "539kb": 16, "53it": 32, "54": 16, "5400": 5, "540kb": 16, "541": 154, "5411": 29, "541kb": 16, "5420": [27, 28, 29, 30, 31], "542kb": 16, "5430": 11, "543kb": 16, "544": [9, 13, 153], "544kb": 16, "545kb": 16, "546": 154, "546kb": 16, "5472": 5, "5474": 30, "5478": 29, "547kb": 16, "548": [32, 33, 153], "5486": 28, "548kb": 16, "5499": 5, "549kb": 16, "54m": [16, 27], "55": [5, 11, 16, 27, 28, 29, 30], "5500": 5, "5500m": 120, "5503989": 22, "5504": 22, "5505": 30, "550kb": 16, "551": 154, "5510": 22, "551kb": 16, "552kb": 16, "553": 154, "5534": 30, "5535": 30, "5538": 30, "5539": 30, "553kb": 16, "5543": 30, "5549": 30, "554kb": 16, "5557": 30, "555kb": 16, "556": 154, "5563": 30, "5565": 29, "556kb": 16, "557kb": 16, "558kb": 16, "559kb": 16, "55it": 32, "55m": 16, "55mb": 27, "56": [4, 9, 11, 16], "5608": 5, "560kb": 16, "561": 154, "5612": 5, "5619": 22, "561kb": 16, "562": 5, "5625": 3, "562kb": 16, "563599": 32, "563kb": 16, "5641": 5, "564kb": 16, "565": 11, "5651": 30, "5656": 30, "5659": 30, "565kb": 16, "5664": 30, "566k": 16, "566kb": 16, "5670986": 22, "5671": [9, 22], "5673": 30, "5674": 31, "5676": 5, "567kb": 16, "56835277": 22, "5686": 22, "5686462": 22, "568kb": 16, "569": 154, "5696": 29, "569kb": 16, "57": [5, 14, 16, 26], "570": 154, "570kb": 16, "5712": 5, "5714": 29, "5716": 30, "571kb": 16, "572": 154, "572kb": 16, "573": 154, "5730": 5, "5733": 30, "5739": 29, "573kb": 16, "5746": 5, "574kb": 16, "5755": 9, "575kb": 16, "5765": 5, "5768": 9, "576kb": 16, "5772": 5, "5779": 30, "578": 154, "5784": 30, "5786": 9, "5787": 5, "578kb": 16, "579": 154, "5790": [5, 30], "5792": 30, "5793": 30, "5797": 5, "579kb": 16, "57m": 16, "58": [5, 11, 16, 27], "5807": 11, "580kb": 16, "581": 154, "5812": 30, "5816": 30, "581kb": 16, "582": [20, 23, 153, 154], "5825": 30, "5826": 30, "5830": 30, "583kb": 16, "584kb": 16, "585kb": 16, "5866": 11, "5868": 29, "5876": 9, "587kb": 16, "5884": 30, "5886": [2, 3], "5889": 30, "588kb": 16, "589kb": 16, "58it": 32, "59": 16, "590": 154, "591": 154, "591kb": 16, "592": 154, "5920": 5, "5927": 9, "593": 154, "5936": 5, "5938": 5, "594": 154, "5949": 30, "594kb": 16, "5950": 5, "5953": 22, "595kb": 16, "597": 154, "5982": 2, "598kb": 16, "599": 154, "5990": 5, "5993": 3, "59m": 16, "5e": 5, "5m": [16, 27, 91], "5mb": 27, "6": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 23, 26, 27, 28, 29, 30, 31, 32, 33, 48, 67, 74, 77, 95, 120, 153], "60": [5, 10, 12, 16, 19, 32], "600": 154, "6011": 5, "6018": 30, "6021": 3, "6026": 11, "603kb": 16, "604": 11, "6044": 30, "606": 154, "6067": 28, "607": 154, "608": 154, "6087": 2, "6089": 22, "6090": 2, "6094": 5, "60_sleep": 80, "60m": 16, "61": [5, 9, 16, 26, 27], "611": 154, "6117": 5, "612": 154, "6120": 5, "6129": 11, "6134": 31, "6143": 30, "6145": 30, "614kb": 16, "615": 154, "6170": 5, "6172": 5, "6177": 5, "6179": 9, "6186": 30, "619": 154, "61m": 16, "62": [5, 14, 16, 26], "620": 11, "621": 154, "6213": 5, "62208": 74, "6227": 5, "6229": 22, "6235": 9, "6238": 5, "624": 154, "6240": 5, "6246": 22, "624k": 16, "625": 79, "6250": 5, "6251": 9, "6259": 5, "6263": 5, "6267": 22, "627": 154, "6272": 5, "6279": 22, "6281": 5, "6282": 22, "6299": 30, "62m": [16, 27], "63": 16, "6304": 29, "6309": 5, "631": 154, "632": [23, 153, 154], "6320": 5, "6322": 9, "6323": 5, "6328": 5, "633": [9, 12, 13, 17, 18, 19, 20, 21, 23, 153], "6337": 9, "6339": 2, "634": [22, 31, 33, 153], "635": [10, 11, 13, 153, 154], "6368": 27, "637": 154, "6372": 9, "6389": 29, "639": [3, 6, 153], "64": [2, 3, 4, 8, 10, 11, 14, 16, 17, 19, 27, 28, 29, 32, 89, 92, 102, 104, 105, 111], "640": 154, "6406": 5, "6407": 29, "640x480": [27, 28], "641": 11, "642": 154, "6422": 5, "643": 154, "6440": 5, "645": 11, "647": 33, "6471": 28, "6475": 2, "6480": 5, "6494": 29, "64it": 32, "64m": 16, "64mb": 27, "65": [11, 16], "6509": 22, "651": [12, 13, 153], "6515615": 22, "6516": 22, "6526": 31, "6529": 2, "653": 6, "6533": 22, "6562": 5, "6565": 29, "65902848": 22, "65m": 16, "66": [5, 16, 27], "660": 11, "661": [18, 23, 153], "6641": 5, "6652": 22, "66521484": 22, "666": [33, 153], "667": [11, 13, 26, 153], "6671": 22, "6676": 9, "6680": 5, "6685": 22, "67": [16, 117], "6719": 5, "673": [33, 153], "674": 30, "6751": 5, "6760": 5, "6790": 9, "67m": 16, "68": [5, 16], "6800": 5, "68056549": 22, "683e00": 29, "6840": 5, "6860": 9, "6875": 5, "6877": 9, "6880": 5, "688k": 16, "6890": 22, "68mb": 27, "69": [2, 3, 4, 5, 8, 9, 10, 12, 16, 27, 28, 29, 30, 32], "6920": 5, "6960": 5, "6978": 22, "698": 11, "6980": 31, "69it": 32, "6f": 32, "6m": [16, 27], "6mb": [16, 27], "7": [2, 3, 4, 5, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 33, 35, 77, 89, 98, 99, 110, 120, 123], "70": [5, 16, 104], "70052629": 22, "7013": 5, "7031": 5, "70380673": 22, "7040": 5, "7063": 2, "7075": 22, "7076": 9, "7080": 5, "7099": 30, "70m": 16, "71": [5, 16], "710": 95, "7109": 5, "7120": 5, "7149": 5, "7154": 9, "715kb": 27, "7160": 5, "716kb": 27, "718": 23, "719": 95, "71it": 32, "72": [11, 16, 27, 117, 133], "7200": [5, 10], "7216": 22, "726": 11, "727": 11, "7276": 22, "7280": 5, "72m": 16, "73": 16, "730": [5, 6, 153], "735": [8, 13, 153], "7360": 5, "73m": 16, "74": [5, 16, 27], "7400": 5, "7404": 22, "7419": 2, "7422": 5, "7427": 30, "7429778": 22, "7430": 22, "7443": 22, "7443461": 22, "7445": 11, "7449": 9, "7454": 11, "74it": 32, "74m": 16, "75": [3, 4, 5, 9, 14, 16, 26, 27, 28, 29, 32, 90, 95, 109, 115], "750": [11, 13], "754k": 16, "7556": 30, "755817": 79, "7578": 5, "758": [5, 9, 10, 111], "75m": 27, "76": 16, "7629": 30, "7638324": 22, "7656": 5, "7664": 22, "7666": 22, "7673": 22, "768": 153, "7685": 3, "769": [5, 9, 10, 111], "77": [5, 11, 16], "773": [16, 18], "7734": 5, "7754": 22, "77m": 16, "78": [16, 27, 80], "7826": 2, "784": [16, 18], "786": 11, "7876": 5, "788": [26, 33, 153], "7886": 5, "78it": 32, "78m": 16, "79": [5, 16], "7909": 5, "7929": 31, "7931": 5, "794": [22, 23, 153], "7945": 5, "7955": 5, "797205": 32, "7kb": 27, "7m": [16, 27], "7mb": 27, "8": [2, 3, 4, 5, 6, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 21, 23, 26, 27, 28, 29, 30, 31, 32, 33, 89, 90, 91, 95, 97, 100, 101, 102, 104, 105, 107, 111, 130, 150, 153], "80": [3, 4, 5, 10, 11, 16, 19, 26, 27, 28, 29, 32, 77, 104, 112], "800": [12, 18], "8000": 22, "8012": 5, "8013": 5, "8024": 22, "8025": 5, "8033": 5, "8036": 22, "8038": 5, "8039": 5, "804": 27, "8068": 5, "8086": 5, "8089": 5, "809": [10, 112], "8095": 5, "8097": 22, "80m": [16, 27], "81": [5, 16, 19], "8100": 5, "8103": 5, "8147": 5, "8148": 9, "8155": 5, "816": 9, "8174": 22, "818": [10, 112], "819k": 16, "81it": 32, "82": [16, 44, 63], "8206": 22, "8209": 5, "8218": 22, "8221": 5, "8225": 2, "8263": 31, "82it": 32, "82m": 16, "83": [11, 16, 22, 27], "8304": 8, "8358": 5, "8370": 5, "83it": 32, "83m": 16, "84": [11, 16, 27], "840": 26, "8419": 22, "844": 26, "8491": 29, "85": [16, 27, 28, 29], "8516": 22, "857": [16, 23, 153], "8585": 22, "8587": 30, "85m": 16, "86": [5, 11, 16], "86039335": 22, "8604": 22, "861": [2, 6, 153], "863": 11, "8659": 29, "8677": 30, "86m": 16, "87": [2, 5, 16, 31, 100], "871": [48, 67], "875": 46, "8754": 29, "876": 11, "87m": 16, "88": [5, 16], "880": 77, "8815": 10, "882": 26, "885": [6, 28, 33, 153], "885k": 16, "886": [4, 46], "887": [17, 23, 153], "8871": 29, "8881": 8, "889k": 27, "89": [10, 16], "890": [48, 67], "8904": 9, "8924": 5, "8943": 22, "898": 11, "8983": 29, "8k": 27, "8m": 16, "8mb": 27, "9": [2, 3, 4, 5, 6, 8, 9, 10, 11, 16, 17, 18, 19, 20, 21, 23, 26, 27, 28, 29, 32, 33, 74, 77, 79, 90, 91, 92, 98, 104, 107, 108, 117, 124, 153], "90": [5, 16, 27, 29, 30, 147], "902958": 32, "9052": 29, "9070": 29, "9071": 29, "9088": 29, "90k": 16, "90m": 16, "91": [11, 16], "912": 11, "912368": 32, "9132": 22, "9173": 29, "9182": 29, "91m": 16, "92": [16, 27], "921907": 32, "9237": 31, "924": 26, "9265": 29, "9266": 22, "9292": 22, "92922518": 22, "9292252": 22, "92it": 32, "92m": 16, "93": [11, 16, 44, 63], "9309": 30, "9353": 22, "9357": 29, "935963004": 107, "936484": 32, "939559": 22, "9396": 22, "93m": 16, "94": [11, 16, 29], "9406": 22, "9423": 30, "9438": 2, "9481": 22, "95": [12, 16, 72, 132], "950k": 16, "9512": 30, "9570": 30, "95it": 32, "96": [16, 27], "960": 11, "9618": 2, "963": 77, "9633": 10, "96330007": 22, "9662": 9, "96it": 32, "96m": 16, "97": 16, "9711": 22, "9730": 10, "976": [26, 27], "978": 31, "97m": 16, "98": 16, "9802": 29, "9819": 28, "9825": 22, "9859": 8, "9883": 22, "98m": 16, "99": 16, "990": 31, "994": [17, 19], "9942": 22, "996": [26, 29, 33, 153], "9968": 29, "9991178": 95, "99mb": 27, "9m": [16, 27], "9mb": 27, "A": [2, 3, 4, 5, 8, 9, 10, 16, 27, 28, 29, 30, 31, 34, 36, 38, 39, 42, 46, 56, 58, 60, 62, 72, 73, 75, 78, 79, 81, 82, 90, 94, 97, 98, 100, 101, 102, 104, 110, 111, 115, 120, 124, 125, 126, 131, 132, 135, 143, 147, 154], "And": [26, 27], "As": [5, 16, 26, 27, 29, 72, 132], "At": [27, 74], "But": [29, 32], "By": [29, 30, 31, 47, 72, 132], "For": [2, 4, 5, 8, 14, 26, 27, 28, 29, 32, 72, 117, 120, 124, 132, 134, 140, 142, 145, 149, 150, 151, 152], "If": [2, 8, 14, 18, 19, 22, 26, 29, 30, 32, 35, 37, 47, 48, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 121, 122, 123, 124, 125, 126, 130, 131, 132, 133, 135, 136, 140, 141, 142, 143, 148, 152], "In": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 18, 20, 21, 26, 27, 28, 29, 30, 32, 37, 44, 47, 49, 50, 51, 52, 54, 57, 63, 66, 68, 70, 72, 74, 91, 120, 121, 124, 132, 145], "It": [2, 3, 4, 5, 8, 9, 10, 11, 18, 27, 28, 29, 30, 32, 42, 48, 62, 72, 75, 83, 86, 91, 112, 126, 132, 149], "NO": 5, "No": [11, 19, 26, 29, 32, 74], "Not": [19, 26], "On": [4, 27, 30, 31, 76, 83], "One": [29, 30, 74, 97], "The": [2, 3, 4, 5, 8, 10, 11, 12, 14, 16, 18, 20, 21, 26, 27, 29, 30, 31, 32, 36, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 54, 61, 72, 74, 76, 77, 79, 83, 89, 90, 91, 92, 95, 97, 98, 101, 102, 103, 104, 105, 106, 107, 108, 110, 112, 113, 117, 118, 119, 120, 121, 123, 124, 130, 132, 142, 143, 147, 150, 152], "Then": 129, "There": [4, 24, 26, 93, 109, 150, 152], "These": [2, 5, 8, 26, 27, 28, 30, 123], "To": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 17, 22, 26, 27, 28, 29, 30, 31, 32, 107, 120, 151, 152], "Will": 54, "With": [10, 112], "_": [3, 5, 14, 16, 17, 26, 27, 28, 31, 32, 48, 154], "__doc__": 26, "__getitem__": [5, 72, 132], "__init__": [5, 32], "__len__": [72, 132], "__name__": 12, "__str__": 26, "__version__": [148, 152], "_causalconv1d": 10, "_check_optimize_result": 5, "_classif": 10, "_criteria": [72, 132], "_data": 31, "_decoderblock": 11, "_encoderblock": 11, "_encoderlay": 10, "_frequency_shift": 154, "_lazydatafram": 125, "_logist": 5, "_modul": [72, 132], "_mrcnn": 10, "_multiheadedattent": 10, "_nestedsequ": [84, 125, 126], "_optim": [72, 132], "_path": 73, "_positionwisefeedforward": 10, "_return_pair": 5, "_scalartype_co": [84, 128, 129], "_sebasicblock": 10, "_selay": 10, "_sublayeroutput": 10, "_supportsarrai": [84, 125, 126], "_t": [128, 129], "_tce": 10, "_tuhmock": [12, 22], "_warn_prf": 10, "a1": 12, "a2": 12, "a_max": 12, "a_min": 12, "aasm": [5, 9, 10, 11], "ab": [4, 5, 47, 66, 104, 142], "abb7a7": 115, "abbassalami": 96, "abbrevi": [3, 4, 18, 20, 21, 29, 30], "abl": [2, 3, 4, 5, 8, 9, 10, 11, 12, 27, 28, 30, 72, 132, 148], "ablat": 104, "abnorm": [14, 79, 82, 91], "about": [8, 9, 10, 12, 26, 30, 76, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 145, 148], "abov": [3, 14, 16, 22, 27, 29, 148, 150], "absolut": [43, 107], "acc": [5, 29, 32], "acceler": [72, 132], "accept": [72, 86, 116, 126, 132], "accepted_bads_ratio": [86, 126], "access": [5, 9, 10, 11, 12, 14, 26, 90, 91, 92, 96, 107, 108, 125, 134, 150], "accident": 154, "accommod": 14, "accord": [40, 59, 124], "accordingli": [9, 26, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 118], "account": [5, 75, 125, 131], "accumul": 32, "accur": [98, 105], "accuraci": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 140, 154], "accuracyof": 4, "achiev": [5, 9, 10, 11, 104], "acoust": 74, "acquir": 77, "acquisit": 120, "across": [113, 115, 124, 133, 137], "act": [16, 124], "action": 154, "activ": [4, 10, 19, 26, 48, 67, 72, 77, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 117, 154], "activation_first_conv_nonlin": 93, "activation_larg": 94, "activation_later_conv_nonlin": 93, "activation_mrcnn": 112, "activation_pool_nonlin": [26, 109], "activation_smal": 94, "activation_transfor": 95, "actual": [3, 5, 12, 14, 22], "ad": [19, 27, 75, 79, 81, 82, 90, 91, 95, 104, 107, 108, 115, 117, 118, 119, 120, 121, 123, 124, 131, 154], "adam": [5, 9, 10, 11, 14, 31], "adamw": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "adapt": [9, 11, 16, 96, 97, 107, 112, 114, 115], "adaptiveavgpool1d": [10, 115], "add": [3, 4, 5, 11, 26, 27, 28, 29, 32, 43, 44, 61, 63, 72, 75, 76, 83, 107, 120, 132, 140, 154], "add_log_softmax": [2, 8, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117], "add_physician_report": [12, 22, 81, 82], "add_safe_glob": 5, "addit": [2, 8, 12, 17, 20, 21, 26, 28, 29, 30, 32, 44, 63, 72, 74, 75, 76, 83, 86, 90, 126, 132, 147], "addition": [12, 18, 26, 35, 72, 132, 143], "address": [42, 62], "adjust": [4, 26, 29, 32, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117], "adjustmenty": 32, "admiss": 37, "advanc": [27, 113, 150], "advanced_train": [6, 153], "advantag": [16, 29, 97], "advis": [3, 27, 30, 42, 62, 132], "aertsen": [27, 28, 29, 30], "affect": [14, 27, 140], "affin": 10, "afr": [10, 112], "after": [5, 12, 16, 21, 26, 28, 29, 32, 74, 80, 90, 93, 109, 110, 111, 113, 123, 137, 140, 154], "after_reduced_cnn_s": 112, "afterward": [27, 29, 89, 90, 95, 98, 124], "ag": [5, 12, 18, 22, 74, 77, 79, 81, 82], "again": [18, 22, 29], "agcl": 74, "aggreg": [4, 90, 95], "aggregate_predict": [2, 72, 132], "aggregate_proba": 154, "ah": [9, 10, 11], "ai": [92, 145], "aim": [21, 22, 104], "ain": 79, "al": [9, 10, 11, 26, 46, 77, 91, 93, 94, 96, 101, 102, 103, 106, 109, 110, 111, 112, 114, 115, 117, 140], "alamgir": 79, "alex": 154, "alexandr": [28, 29, 30, 35], "algorithm": [14, 26, 28, 29, 30, 32], "alia": [26, 89, 93, 94, 95, 96, 97, 98, 101, 102, 103, 109, 110, 111, 112, 114, 115, 117], "all": [2, 3, 4, 8, 12, 14, 16, 24, 26, 27, 28, 29, 30, 32, 43, 44, 46, 54, 61, 63, 65, 70, 72, 73, 74, 77, 78, 80, 89, 90, 95, 97, 98, 99, 107, 118, 120, 121, 123, 124, 125, 126, 132, 140, 153, 154], "all_dataset": 29, "all_n_job": 16, "all_n_rec": 16, "all_result": 14, "allow": [3, 5, 14, 26, 29, 30, 32, 41, 72, 78, 86, 97, 104, 107, 126, 132, 154], "allowlist": 5, "almost": 79, "along": [26, 76, 83, 123, 151, 154], "alpha": [5, 9, 10, 11, 12, 47], "alreadi": [2, 3, 5, 8, 9, 10, 11, 14, 19, 27, 28, 29, 75, 76, 83, 131, 132, 148, 150], "also": [3, 4, 5, 9, 10, 11, 12, 14, 18, 21, 26, 28, 35, 72, 83, 95, 97, 112, 120, 121, 123, 132, 143, 148, 151, 152], "alsulaiman": 89, "altaheri": 89, "altern": [5, 26, 32, 72, 132], "although": [3, 72, 89, 90, 95, 98, 132], "alwai": [5, 29, 32, 35, 56, 72, 132], "amar": [5, 9, 10, 11], "among": 112, "amount": [9, 10, 11, 16, 123], "amper": [72, 132], "ampli_init_valu": 113, "amplifi": 74, "amplitud": [43, 61, 113, 125, 126, 154], "amplitude_c": 113, "amplitur": 107, "an": [2, 5, 8, 9, 10, 12, 14, 16, 18, 19, 20, 21, 22, 26, 27, 29, 30, 32, 41, 49, 50, 51, 52, 56, 72, 74, 76, 77, 79, 83, 86, 89, 90, 91, 93, 94, 96, 97, 98, 99, 103, 104, 105, 106, 107, 109, 110, 111, 112, 114, 116, 117, 119, 120, 122, 123, 124, 126, 132, 134, 140, 148, 149, 154], "analaysi": [7, 24], "analog": [29, 140], "analys": [2, 8, 29, 30, 73], "analysi": [4, 5, 9, 10, 11, 26, 35, 90, 149], "analyz": 30, "andreu": 96, "angl": [49, 50, 51, 52, 68, 147], "ani": [5, 17, 18, 26, 27, 29, 32, 72, 78, 84, 92, 108, 112, 120, 124, 125, 126, 128, 129, 132, 152], "ann": 154, "annot": [9, 10, 11, 18, 19, 21, 27, 28, 29, 30, 32, 79, 120, 154], "annual": [49, 50, 51, 52, 68], "anonym": 148, "anoth": [5, 21, 29, 32, 135], "answer": [29, 32], "anyth": [27, 72], "anywher": [72, 132], "apart": 5, "api": [26, 152], "appear": [9, 10, 11, 74], "append": [2, 8, 12, 14, 16, 27, 28, 31, 72, 120, 132], "appli": [2, 3, 4, 5, 8, 9, 10, 12, 16, 18, 19, 20, 26, 27, 28, 29, 30, 32, 36, 37, 38, 39, 40, 42, 43, 44, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 72, 76, 83, 90, 91, 92, 94, 95, 96, 101, 103, 104, 107, 108, 110, 111, 112, 113, 114, 115, 116, 117, 120, 122, 124, 130, 131, 132, 142, 154], "applic": [83, 120], "applied_exampl": [13, 153], "apply_batch_norm": [5, 110, 111], "apply_funct": 122, "apply_on_arrai": [9, 10, 12, 122], "apply_proj": 124, "approach": [4, 5, 9, 10, 11, 16, 24, 30, 46, 48, 67, 112, 133], "appropri": [35, 151], "approv": 77, "approx": 77, "approxim": [10, 50, 51, 52], "ar": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 19, 20, 22, 24, 26, 27, 28, 29, 30, 31, 32, 35, 37, 47, 66, 72, 75, 83, 84, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 124, 125, 126, 130, 132, 135, 137, 141, 148, 150, 151, 152, 154], "arang": [2, 8], "arbitrari": 5, "architectur": [2, 5, 8, 9, 10, 11, 26, 27, 28, 30, 72, 90, 91, 94, 95, 104, 107, 108, 110, 111, 112, 117, 132, 149], "arg": [72, 99, 132, 154], "argmax": 32, "argument": [3, 4, 16, 19, 26, 29, 32, 36, 38, 39, 40, 42, 48, 53, 55, 56, 72, 78, 118, 120, 121, 122, 123, 124, 130, 132, 140, 154], "aris": 16, "aristimunha": [4, 154], "armchair": 74, "arnal": [5, 9, 10, 111], "around": [4, 10, 32, 49, 50, 51, 52, 68, 91, 126, 133], "arrai": [2, 4, 8, 11, 17, 22, 26, 28, 29, 30, 37, 48, 49, 56, 57, 67, 68, 72, 84, 85, 86, 120, 121, 122, 123, 132, 136, 143, 147], "arrow": [74, 77], "articl": [26, 35], "artifici": 4, "arxiv": [4, 5, 31, 37, 38, 39, 40, 42, 44, 47, 54, 57, 58, 59, 60, 62, 63, 66, 70, 90, 101, 102, 104, 105, 107, 114, 135, 142], "as_tensor": 3, "ascend": [79, 81, 82], "ask": [35, 74], "assert": [2, 3, 4, 8, 14, 27, 28, 29, 30, 32], "assign": [27, 28, 144], "assist": 97, "associ": 97, "assum": [14, 26, 72, 118, 132, 137, 141, 154], "astyp": [9, 10], "asynchron": 46, "atcnet": [26, 154], "aten": 11, "att_depth": 95, "att_drop_prob": 95, "att_dropout": 89, "att_head": 95, "att_head_dim": 89, "att_num_head": [89, 91, 107], "attempt": [26, 89, 90, 91, 93, 94, 99, 103, 105, 106, 107, 109, 110, 111, 112, 114, 117, 124], "attent": [10, 89, 90, 91, 95, 107, 112], "attention_mod": 90, "attentionbasenet": [26, 154], "attenu": [16, 120], "attn_drop_r": 107, "attn_head_dim": 107, "attnsleep": 112, "attribut": [2, 8, 26, 28, 29, 30, 32, 72, 76, 83, 122, 132, 154], "attributeerror": 72, "aug": [26, 35, 93, 103, 106, 109, 147], "augment": [1, 6, 24, 75, 78, 95, 99, 109, 122, 126, 129, 131, 145, 149, 153, 154], "augmenteddataload": [3, 4, 154], "author": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31, 35, 92, 95, 96, 97, 98, 100, 101, 102, 104, 108, 113], "auto": [3, 4, 8, 14, 17, 19, 26, 28, 29, 30, 32, 72, 93, 95, 101, 102, 103, 109, 120, 123, 124, 132, 154], "auto_exampl": [6, 13, 23, 33, 34], "auto_examples_jupyt": 24, "auto_examples_python": 24, "auto_tutori": 80, "autocorrel": 5, "autoencod": 117, "autom": [14, 29], "automat": [12, 14, 26, 48, 73, 92, 94, 115, 124, 154], "avail": [2, 3, 4, 8, 9, 10, 11, 12, 14, 16, 19, 22, 26, 27, 28, 29, 30, 32, 73, 80, 90, 91, 95, 97, 104, 112, 125, 126, 133, 134], "avenu": 5, "averag": [10, 12, 27, 29, 31, 32, 72, 89, 90, 99, 104, 124, 132, 137], "avg": [5, 9, 10, 11], "avg_pool": 10, "avg_pool_block4": 100, "avg_pool_block5": 100, "avgpool1d": 11, "avgpool2d": [3, 4, 26, 27, 28, 29, 32], "avoid": [5, 9, 10, 11, 12, 14, 16, 22, 27, 29, 80, 154], "awar": [37, 44, 54, 57, 63, 70], "ax": [2, 3, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 31, 99], "ax1": [2, 5, 8, 9, 10, 11, 27, 28], "ax2": [2, 5, 8, 9, 10, 11, 27, 28], "axhlin": 12, "axi": [2, 3, 5, 8, 27, 28, 31, 49, 50, 51, 52, 53, 55, 68, 69, 71, 99, 123, 144], "azemi": [37, 44, 54, 57, 63, 70], "b": [5, 9, 10, 11, 16, 27, 40, 59, 90, 91, 92, 95, 101, 102, 104, 108, 117], "ba": 31, "back": 77, "backend": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 145, 154], "backtick": 148, "backward": [3, 4, 11, 14, 26, 27, 28, 29, 32, 99, 120, 154], "bad": [10, 14, 19, 120, 121, 124, 148], "bad_acq_skip": 120, "bai": 114, "bai2018": 114, "bal": 5, "balanc": [5, 9, 10, 11, 133, 154], "balanced_accuraci": [9, 10], "balanced_accuracy_multi": 11, "balanced_accuracy_scor": [5, 11], "balancedsequencesampl": 154, "ball": [26, 27, 28, 29, 30, 31, 35, 77, 93, 103, 106, 109, 147], "band": [37, 57, 120, 130, 154], "bandpass": [2, 3, 4, 8, 20, 27, 28, 29, 30, 32, 74, 120, 130], "bandwidth": [16, 37, 57], "bang": 107, "banvil": [4, 5, 9, 14, 16, 20, 135, 154], "banville2020": 135, "bao": 107, "bar": 4, "barach": [28, 29, 30], "barh": [12, 29], "base": [0, 2, 3, 4, 5, 8, 9, 10, 12, 16, 18, 20, 21, 27, 28, 29, 30, 31, 32, 36, 44, 46, 47, 48, 63, 65, 66, 67, 72, 74, 75, 89, 90, 91, 94, 95, 96, 97, 98, 101, 102, 108, 112, 113, 118, 120, 121, 123, 125, 126, 132, 134, 142, 154], "baseconcatdataset": [2, 5, 9, 10, 12, 14, 16, 21, 31, 72, 84, 85, 86, 87, 125, 126, 131, 132, 134, 143, 154], "basedataset": [31, 36, 75, 83, 87, 131, 154], "baseepoch": [83, 85, 122], "baselin": [19, 26, 104, 113], "baseraw": [76, 86, 122, 130], "basic": [15, 27, 29, 32, 33, 56, 75, 78, 98, 99, 109, 122, 126, 129, 131, 145, 147, 153, 154], "batch": [3, 4, 5, 26, 30, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 68, 69, 70, 71, 72, 93, 94, 99, 104, 106, 107, 108, 109, 110, 111, 112, 114, 115, 132, 139, 143, 154], "batch_i": 22, "batch_idx": 32, "batch_ind": 22, "batch_loss": 32, "batch_norm": [14, 26, 93, 108, 109], "batch_norm_alpha": [14, 26, 93, 97, 103, 109], "batch_norm_epsilon": 103, "batch_siz": [2, 3, 4, 5, 8, 9, 10, 11, 14, 22, 27, 28, 29, 30, 31, 32, 37, 47, 49, 57, 66, 68, 72, 91, 92, 94, 95, 99, 100, 104, 105, 106, 108, 110, 111, 112, 113, 114, 115, 116, 132, 137, 141, 143, 146], "batch_x": [5, 22], "batchnorm1d": [10, 11], "batchnorm2d": [3, 4, 26, 27, 28, 29, 32, 93, 97, 109], "batchscor": [72, 132], "bbci": 73, "bbox_to_anchor": 29, "bcewithlogitsloss": [5, 72, 132], "bci": [2, 4, 8, 21, 26, 27, 28, 29, 30, 42, 46, 62, 73, 74, 89, 98, 104, 107, 115], "bci2000": 77, "bcic": [1, 6, 7, 13, 20, 24, 25, 29, 32, 33, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 78, 99, 109, 122, 125, 126, 127, 129, 131, 137, 138, 139, 141, 145, 147, 153, 154], "bcicomp": 8, "bcicompetitionivdataset4": [2, 8, 154], "bd_cmap": 29, "bear": 148, "becaus": [2, 16, 26, 27, 29, 30, 148, 154], "becom": [14, 16, 29], "been": [2, 3, 4, 8, 10, 14, 16, 18, 20, 21, 27, 28, 29, 30, 32, 92, 96, 97, 98, 99, 100, 101, 102, 108, 113, 142, 148, 152, 154], "beetl": 97, "befor": [2, 11, 16, 27, 28, 29, 30, 32, 72, 75, 76, 80, 83, 89, 93, 94, 95, 110, 111, 112, 128, 129, 132, 140, 145, 151, 154], "beforehand": 19, "begin": [2, 27, 29, 30, 74, 110, 120, 125], "beginn": 150, "behavior": [10, 32, 72, 120, 132, 154], "behaviour": [2, 8, 73], "behind": [29, 32], "being": [4, 10, 14, 27, 72, 77, 132], "beit": 107, "beitv2": 107, "below": [3, 5, 35, 37, 148, 151, 154], "benchmark": [2, 3, 4, 5, 8, 9, 10, 11, 15, 23, 24, 27, 28, 29, 30, 31, 32, 75, 80, 82, 93, 100, 109, 122, 125, 131, 145, 153, 154], "benchmark_lazy_eager_load": [14, 23, 153], "benefici": 28, "benini": 105, "best": [1, 6, 24, 32, 36, 38, 42, 54, 56, 75, 78, 99, 109, 122, 126, 129, 131, 145, 153], "best_aug": 4, "best_estimator_": 4, "best_paramet": 29, "best_run": [4, 29, 30], "beta": [47, 113], "beta_init_valu": 113, "beta_per_sampl": 47, "better": [2, 5, 8, 10, 14, 16, 27, 28, 29, 32, 95, 140, 154], "between": [2, 3, 4, 5, 8, 9, 11, 26, 27, 28, 29, 37, 38, 39, 42, 43, 47, 49, 50, 51, 52, 56, 57, 58, 60, 62, 66, 74, 84, 85, 86, 90, 93, 95, 104, 109, 110, 118, 125, 126, 136, 141], "beyond": [31, 47, 66, 142], "bia": [9, 10, 11, 107, 108], "bias": 29, "bidirect": 94, "big": [7, 13, 24, 75, 81, 122, 125, 131, 153, 154], "bigger": 12, "bin": 12, "biologi": [49, 50, 51, 52, 68], "biomed": [5, 100], "biosign": [37, 44, 54, 57, 63, 70, 91, 92, 108], "biot": [26, 92, 108, 154], "biotencod": 91, "bipolar": 124, "birbaum": [27, 28, 29, 30], "biswal": [40, 59], "black": [2, 8, 12, 27, 28, 74, 77, 147, 154], "blackman": 120, "blanco": 110, "blanco2020": 110, "blob": 5, "block": [89, 90, 92, 97, 98, 100, 104, 105, 107, 108, 114, 117], "block_lay": 108, "block_postskip": 11, "block_prepool": 11, "block_preskip": 11, "blue": [2, 5, 8, 16, 27, 28], "bme": [9, 10, 11], "bn1": 10, "bn2": 10, "bnci": [4, 74], "bnci2014": [3, 4, 18, 20, 21, 29, 30, 74], "bnci2014001": [3, 4, 18, 20, 21, 29, 30], "bnci2014_001": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32], "bnorm": [3, 4, 26, 27, 28, 29, 32], "bold": 147, "bonsmann": 154, "bool": [14, 26, 42, 47, 49, 50, 51, 52, 62, 68, 72, 73, 75, 76, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 93, 94, 95, 96, 97, 98, 99, 101, 103, 106, 107, 108, 109, 110, 111, 112, 114, 115, 117, 118, 120, 121, 122, 123, 124, 125, 126, 130, 131, 132, 135, 136, 140, 143, 145, 147], "boost": 5, "bose": 98, "both": [4, 5, 16, 22, 30, 74, 77, 110, 111, 117], "bottleneck": [16, 32, 97, 115], "bottleneck_s": 108, "bottom": 11, "bouallegu": [104, 154], "box": [72, 132], "boxcar": 123, "br": 4, "brain": [4, 24, 25, 26, 27, 29, 30, 31, 33, 35, 48, 67, 75, 78, 79, 93, 97, 99, 101, 102, 103, 105, 106, 107, 109, 122, 126, 129, 131, 145, 147, 149, 153], "braincod": 151, "braindecod": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 33, 150, 151, 153, 154], "branch": 98, "brandt": [3, 20, 154], "braun": [27, 28, 29, 30], "break": [20, 74], "brodbeck": 35, "brook": 35, "bruna": 154, "brunner": [27, 28, 29, 30], "bruno": [4, 154], "bsd": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31], "bug": 99, "build": [12, 27, 32, 150, 152], "built": [35, 148], "bundl": 14, "burgard": [27, 28, 29, 30, 35], "butt": 79, "butterworth": 120, "byte": [84, 125, 126], "c": [4, 5, 9, 10, 11, 20, 27, 28, 29, 30, 42, 62, 91, 92, 94, 98, 101, 102, 107, 108, 113, 117, 133, 148], "c0": 4, "c1": 4, "c2": 4, "c3": [12, 26], "c4": [12, 26], "c_tuab": 82, "c_tueg": [12, 81], "ca": 115, "cach": [72, 132, 154], "cache_config": 78, "cagig": 97, "cakmak": [42, 62], "cal": 26, "calc_pad": 100, "calcul": [2, 3, 4, 27, 28, 29, 30, 32, 72, 100, 115, 132], "calibr": [48, 67], "call": [3, 16, 26, 27, 29, 32, 72, 75, 83, 86, 89, 90, 95, 98, 118, 122, 125, 126, 132, 138, 139, 140], "callabl": [3, 26, 41, 56, 72, 75, 76, 83, 93, 109, 122, 132, 140], "callback": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 72, 132, 140], "callbacks_": [72, 132], "callbacks__print_log__keys_ignor": [72, 132], "callbacks__valid_acc": 11, "camelcas": 0, "can": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 21, 22, 26, 27, 28, 29, 30, 32, 35, 43, 49, 68, 72, 75, 79, 80, 81, 82, 83, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 119, 120, 121, 123, 124, 132, 143, 150, 151, 154], "candid": [4, 29, 30], "cannot": [2, 3, 4, 5, 8, 9, 10, 11, 12, 27, 28, 29, 30, 32, 72, 118, 132], "canon": 35, "capabl": [12, 16, 29, 32, 72, 132], "capac": [29, 30, 90], "capit": 10, "captur": 112, "care": [89, 90, 95, 98], "carin": 113, "carlson": 113, "carri": [39, 60, 74], "cartesian": [49, 68], "case": [2, 5, 8, 16, 21, 26, 27, 28, 29, 30, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 124, 132, 145, 151, 154], "cast": [4, 41], "cat": 90, "categor": [4, 133], "categori": [2, 4, 31], "catlit": 90, "catplot": 14, "caus": [2, 8], "causal": [16, 120], "cavigelli": 105, "cbam": 90, "cbar": 30, "cd": 152, "cdot": [128, 129], "cedric": [3, 4, 154], "ceil": [9, 10, 115], "ceil_mod": [9, 10], "cell": 4, "center": [2, 8, 9, 10, 29, 37, 57], "certain": [72, 90, 132], "certif": 27, "ch": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117], "ch_dim": 90, "ch_name": [12, 14, 17, 26, 84, 119, 130], "ch_po": [49, 68], "ch_type": [12, 26, 124], "challeng": 113, "chambon": [5, 9, 10, 111], "chambon2018": [7, 13, 24, 75, 80, 99, 111, 116, 122, 126, 131, 134, 136, 145, 147, 153], "chan": [2, 3, 4, 8, 27, 28, 29, 30, 32, 74, 77], "chanc": [5, 9, 10], "chang": [2, 5, 8, 14, 18, 31, 45, 72, 91, 120, 124, 132, 140, 152], "channel": [2, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 38, 39, 40, 42, 43, 44, 46, 47, 49, 50, 51, 52, 54, 58, 59, 60, 61, 62, 63, 65, 66, 68, 70, 80, 81, 82, 83, 84, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 119, 120, 121, 124, 125, 126, 130, 154], "channel_indep": [42, 62], "channel_wis": [5, 9, 10, 11, 16], "channelsdropout": 4, "character": 16, "characterist": 113, "chat": 148, "check": [2, 3, 4, 8, 9, 10, 11, 26, 27, 28, 29, 30, 32, 35, 89, 92, 93, 95, 96, 97, 98, 99, 100, 101, 102, 103, 106, 108, 109, 110, 113, 114, 115, 117, 148, 151, 154], "checker": 154, "checkpoint": [5, 32], "checkpoint_connector": 32, "chehab": [4, 5, 11, 135, 154], "chen": 100, "cheng": [37, 44, 54, 57, 63, 70], "chenxiachan": 100, "chevalli": 154, "choic": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32, 90, 95, 104, 154], "choos": [2, 3, 4, 8, 18, 27, 28, 29, 30, 32], "chose": 3, "chosen": [2, 16, 18, 27, 32, 46, 54, 72, 120, 132, 143], "christian": 35, "christoph": 30, "chronolog": [12, 79, 81, 82], "chs_info": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132], "ci": 154, "cifar10": [47, 66, 142], "circl": 16, "circul": [5, 9, 10, 11], "ciss": [47, 66, 142], "cite": [2, 8, 73], "ckpt": 32, "ckpt_path": 32, "cl": 107, "clariti": 154, "class": [0, 3, 4, 5, 9, 10, 11, 12, 14, 18, 20, 21, 26, 27, 28, 29, 30, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 62, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 147, 154], "class_nam": [9, 10, 11, 27, 28, 147], "class_names_fonts": 147, "class_weight": [5, 9, 10, 11], "classes_": 72, "classic": 28, "classif": [5, 9, 10, 11, 26, 27, 30, 37, 42, 44, 54, 57, 62, 63, 70, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115], "classifi": [3, 4, 5, 9, 10, 11, 26, 29, 31, 107, 154], "classification_report": [5, 9, 10, 11], "classificationhead": [90, 91, 95], "claus": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26], "clear": 16, "clench": 77, "clf": [3, 4, 5, 9, 10, 11, 27, 28, 29, 30], "clf_pipe": 5, "clifford": [42, 62], "cliffordlab": [42, 62], "clinic": [4, 5, 7, 24, 80, 135], "clip": 12, "clone": [112, 154], "cloneabl": 154, "close": [5, 16, 18, 135, 148], "cluster": 90, "cm": [74, 147], "cmap": 30, "cmsaugment": [38, 39, 58, 60], "cnn": [108, 112], "cnosid": 8, "co": [40, 59, 113], "code": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 95, 96, 97, 100, 104, 107, 112, 113, 114, 115, 148, 150, 152, 154], "code2023": [91, 92, 108], "code2024": 107, "codebas": 154, "codeicassp2025": 113, "codeword": 90, "coeffici": [2, 8, 47, 66, 142], "cognit": [7, 24], "coil_typ": 26, "col": 14, "col_nam": 99, "cold": [72, 132], "collabor": 90, "collect": [26, 72, 77, 132], "color": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 147], "colormap": [5, 147, 154], "column": [2, 8, 19, 21, 22, 27, 28, 29, 30, 32, 75, 83, 87, 99, 133, 134, 147], "com": [2, 3, 5, 8, 9, 10, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31, 74, 77, 81, 82, 152], "combin": [14, 16, 75, 105], "combinedconv": [3, 4, 26, 27, 28, 29, 32], "come": [2, 8, 14, 28, 30, 32, 136, 145], "comfort": 74, "command": [151, 152], "commit": 154, "committe": 77, "common": [12, 14, 124, 151, 154], "commonli": 3, "compact": [29, 101, 102], "compar": [5, 14, 16, 22, 27, 29, 32, 90], "comparison": [4, 14, 27, 28], "compat": [3, 14, 17, 19, 30, 72, 84, 85, 86, 120, 132, 154], "compens": [29, 120], "competit": [2, 4, 8, 11, 14, 21, 26, 27, 28, 29, 30, 73, 74, 97, 104], "compil": [72, 132], "compile__dynam": [72, 132], "complet": [12, 14, 16, 27, 72, 132], "complex": [5, 9, 10, 11, 29, 32, 77, 84, 90, 110, 125, 126], "complexity_factor": 117, "complianc": 18, "compon": [5, 9, 10, 11, 77, 97], "compos": [90, 95], "composed_transform": 3, "composit": [3, 41], "compris": 74, "comput": [3, 4, 5, 9, 10, 11, 18, 22, 35, 48, 50, 51, 52, 67, 72, 74, 86, 89, 90, 92, 95, 97, 98, 101, 102, 110, 124, 125, 126, 128, 129, 132, 137, 138, 139, 141, 145, 148, 152, 154], "compute_amplitude_gradi": 154, "compute_class_weight": [9, 10, 11], "concat": [18, 75, 89, 125, 126, 131], "concat_d": [12, 16, 18, 125, 126, 127, 131], "concat_dataset": [87, 88], "concatdataset": 125, "concaten": [5, 9, 10, 75, 89, 116, 120, 125, 126], "concatenate_raw": 120, "conda": 154, "condit": 154, "conf": [27, 28], "confer": [44, 47, 49, 50, 51, 52, 63, 66, 68, 91, 107], "config": [27, 73], "configur": [12, 16, 27, 29, 32], "configure_optim": 32, "conflict": [32, 72, 132], "conform": 95, "conformercod": 95, "confus": [5, 9, 10, 11, 147, 154], "confusion_mat": [9, 10, 11, 27, 28, 147], "confusion_matrix": [5, 9, 10, 11, 27, 28, 147], "connect": [29, 30, 89, 95, 98, 105, 110, 117], "connectionpool": 27, "connector": 32, "consecut": [9, 10, 11, 54, 70, 116, 126, 133, 136], "consid": [2, 4, 29, 32, 50, 51, 52, 72, 132, 140], "consider": 16, "consist": [2, 3, 4, 5, 8, 9, 11, 27, 28, 50, 51, 52, 74, 77, 154], "constant": 2, "constant_valu": 2, "constantpad1d": 11, "constraint": [89, 105, 154], "construct": [5, 120, 124], "construct_iir_filt": 120, "contain": [2, 5, 8, 12, 14, 16, 18, 21, 22, 26, 31, 36, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 57, 65, 66, 68, 70, 72, 73, 75, 78, 79, 80, 83, 100, 124, 125, 126, 132, 133, 134, 135, 141, 142, 148, 154], "content": 80, "context": [4, 5, 29, 35, 90, 112, 135], "contigu": [16, 46, 54, 65, 70], "continu": [14, 16, 20, 76, 77, 84, 85, 86, 125, 126, 151, 154], "continuum": 108, "contrari": 89, "contrast": [2, 4, 5, 27, 37, 44, 54, 57, 63, 70, 91, 92], "contrastivenet": 5, "contrawr": [26, 154], "contribut": [150, 152], "contributor": [148, 152], "control": [4, 5, 10, 29, 72, 90, 100, 110, 113, 118, 120, 121, 123, 124, 125, 126, 131, 132, 154], "conv": [10, 11, 117], "conv1": 10, "conv1d": [10, 11, 117], "conv2": 10, "conv2d": [3, 4, 9, 26, 27, 28, 29, 32], "conv_bia": 108, "conv_block_depth_mult": 89, "conv_block_dropout": 89, "conv_block_kernel_length_1": 89, "conv_block_kernel_length_2": 89, "conv_block_n_filt": 89, "conv_block_pool_size_1": 89, "conv_block_pool_size_2": 89, "conv_classifi": [3, 4, 26, 27, 28, 29, 32], "conv_nonlin": [26, 109], "conv_nonlin_exp": [3, 4, 26, 27, 28, 29, 32], "conv_time_spat": [3, 4, 26, 27, 28, 29, 32], "conv_weight_init_fn": 103, "conveni": [5, 107, 124], "converg": [5, 29, 31], "convergencewarn": 5, "convert": [2, 3, 4, 5, 8, 9, 10, 12, 17, 19, 27, 28, 29, 30, 31, 32, 120], "convnet": [2, 8, 26, 27, 28, 93, 106, 109], "convolut": [2, 5, 8, 9, 11, 24, 25, 26, 27, 28, 29, 30, 33, 35, 42, 44, 62, 63, 75, 76, 89, 90, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 117, 125, 137, 145, 147, 153, 154], "coord_fram": 26, "coordin": [49, 68], "copi": [2, 11, 16, 42, 62, 73, 118, 148], "core": [12, 16, 32], "corpu": [7, 13, 14, 15, 23, 24, 75, 81, 82, 91, 122, 125, 131, 153, 154], "corr_coeff": [2, 8], "corrcoef": [2, 8], "correct": [19, 26, 32, 72, 92, 96, 97, 98, 100, 101, 102, 108, 113, 132, 154], "correctli": [9, 10, 11, 99, 152, 154], "correl": [2, 8, 27, 29], "correspond": [2, 5, 8, 12, 21, 29, 30, 31, 37, 40, 72, 73, 74, 75, 83, 84, 86, 124, 126, 131, 132, 133, 141], "corrupt": 148, "cortex": 77, "cosineannealinglr": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "cost": [2, 3, 4, 5, 8, 9, 11, 27, 28], "could": [4, 5, 14, 29, 32, 99, 152], "count": [12, 72, 132], "cours": [16, 73], "cover": [77, 147], "coverag": 154, "cp": 5, "cpp": 11, "cpu": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 72, 132], "creat": [14, 16, 17, 18, 19, 20, 21, 31, 72, 75, 83, 84, 85, 86, 124, 125, 126, 132, 143, 154], "create_example_model": 14, "create_filt": 120, "create_fixed_length_window": [2, 5, 12, 14, 16, 22, 31, 154], "create_from_mne_epoch": 19, "create_from_mne_raw": 19, "create_from_x_i": 17, "create_info": 26, "create_mne_dummy_raw": 31, "create_windows_from_ev": [3, 4, 5, 9, 10, 11, 18, 21, 27, 28, 29, 30, 32, 154], "create_windows_from_target_channel": [8, 154], "creation": [12, 22], "credibl": [29, 32], "criteria": [20, 72, 132], "criterion": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 72, 132], "criterion_": [72, 132], "criterion__loss_funct": [2, 27, 31], "criterion__weight": [9, 10, 11], "crop": [1, 6, 8, 10, 11, 12, 16, 20, 24, 25, 29, 30, 31, 32, 33, 72, 73, 75, 78, 80, 83, 99, 109, 122, 125, 126, 129, 131, 132, 137, 138, 139, 141, 143, 145, 147, 153, 154], "crop_wake_min": [5, 9, 10, 11, 16, 80], "croppedloss": [2, 27, 31], "croppedtimeseriesepochscor": 2, "cross": [2, 8, 16, 27, 28, 74, 91, 92, 104, 108], "cross_entropi": 27, "cross_val_scor": 29, "crossentropyloss": [3, 4, 9, 10, 11, 14, 26, 28, 29, 30, 32, 72, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 132], "csr": [72, 132], "csv": 14, "csvlogger": 32, "cuda": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 72, 120, 123, 132, 145, 151], "cuda_dependent_attributes_": [72, 132], "cuda_path": 151, "cudnn": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 145, 154], "cudnn_benchmark": [2, 3, 4, 5, 8, 9, 11, 27, 28, 145], "cue": [74, 77], "cumbersom": [72, 132], "cupi": [120, 123], "current": [5, 11, 72, 124, 132, 148], "curv": [2, 8, 28], "custom": [3, 4, 15, 23, 24, 36, 75, 84, 90, 153], "custom_crop": 12, "cut": [3, 4, 19, 28, 29, 30, 37, 57, 84, 120], "cutoff": [2, 8, 16, 120], "cv": [4, 29, 30, 107], "cv_result": 29, "cv_results_": [4, 29, 30], "cycl": 14, "cz": [10, 12, 26, 124, 130], "cz_4": 130, "cz_8": 130, "c\u00e9dric": [3, 4], "d": [2, 3, 4, 5, 8, 12, 14, 22, 26, 27, 28, 29, 30, 31, 32, 38, 39, 42, 58, 60, 62, 79, 89, 93, 102, 103, 106, 109, 110, 113, 115, 135, 147, 154], "d_ff": 112, "d_i": 12, "d_model": 112, "dafaram": 12, "dahl": 30, "dai": [12, 74], "dan": [20, 154], "daniel": [20, 35, 154], "darkner": [11, 117, 133], "darva": 77, "data": [1, 2, 5, 6, 7, 8, 9, 10, 11, 13, 14, 16, 17, 18, 19, 21, 25, 30, 32, 33, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 56, 60, 63, 66, 67, 68, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 86, 87, 91, 92, 93, 95, 99, 104, 107, 108, 109, 118, 120, 121, 122, 123, 124, 125, 126, 128, 129, 131, 132, 137, 142, 145, 147, 148, 149, 153, 154], "data_class": [48, 67], "data_connector": 32, "data_loading_end": 14, "data_loading_start": 14, "data_prepar": 14, "datafram": [2, 4, 5, 8, 9, 10, 11, 14, 16, 20, 21, 22, 27, 28, 29, 30, 72, 75, 132, 133, 134, 135, 136], "dataload": [3, 4, 5, 14, 32, 36, 72, 132, 143], "datapoint": 75, "dataset": [1, 6, 13, 14, 15, 16, 23, 25, 26, 33, 36, 38, 41, 42, 43, 53, 54, 56, 72, 87, 89, 91, 98, 99, 109, 111, 112, 116, 117, 122, 125, 126, 127, 129, 131, 132, 134, 136, 137, 138, 139, 141, 143, 145, 146, 147, 148, 149, 151, 152, 153, 154], "dataset__": [72, 132], "dataset_kwarg": 78, "dataset_load": 18, "dataset_load_kwarg": 78, "dataset_nam": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32, 78], "dataset_split": 2, "dataset_train": [72, 132, 138, 139, 140], "dataset_valid": [72, 132, 138, 139, 140], "datasets_io": [23, 153], "datautil": [0, 5, 18, 83, 154], "dauphin": [47, 66, 142], "david": [47, 66, 142], "db": [3, 16, 124], "dct": 90, "ddf2ff": 29, "de": 73, "deactiv": 11, "deal": [72, 132], "decai": 113, "decid": [8, 28, 38, 39, 40, 42, 48, 53, 55, 56], "decod": [1, 3, 4, 6, 7, 11, 13, 20, 22, 24, 25, 26, 29, 30, 31, 32, 33, 35, 72, 73, 75, 78, 84, 90, 93, 95, 99, 100, 103, 104, 106, 107, 109, 117, 122, 125, 126, 127, 129, 131, 132, 137, 138, 139, 141, 143, 145, 147, 149, 153, 154], "decompos": 120, "decomposit": [5, 92], "decreas": [2, 8, 11], "deep": [2, 3, 4, 5, 8, 9, 10, 11, 14, 26, 27, 28, 29, 30, 31, 32, 35, 44, 46, 63, 90, 93, 97, 103, 104, 106, 109, 111, 112, 115, 147, 149, 151], "deep4": [27, 28, 154], "deep4net": [14, 26, 31, 154], "deepconvnet": 31, "deepcopi": 2, "deepsleepnet": [26, 154], "def": [2, 3, 5, 8, 9, 10, 11, 12, 14, 16, 29, 31, 32], "default": [2, 5, 8, 11, 12, 27, 28, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 72, 73, 79, 80, 81, 82, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 103, 104, 105, 107, 108, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 123, 124, 126, 132, 140, 145, 154], "defin": [2, 5, 9, 10, 11, 12, 14, 20, 21, 27, 28, 30, 40, 56, 59, 72, 83, 89, 90, 95, 98, 113, 115, 126, 132, 135], "definit": [27, 72, 132], "degre": [29, 32, 49, 50, 51, 52, 68], "deiss": [40, 59], "del": 14, "delai": [120, 154], "delboui": 154, "delet": [5, 22, 75, 131], "delta_freq": [43, 61], "deman": 128, "demand": 4, "demarc": [29, 30], "demean": 128, "demeanin": 128, "demonstr": [3, 4, 7, 22, 24, 26, 32], "deni": [35, 154], "denot": 89, "dens": [27, 99, 108, 110, 111], "densefilt": 115, "densenet": [108, 115], "densiti": 3, "depend": [4, 5, 9, 10, 11, 14, 16, 26, 29, 30, 32, 35, 72, 77, 112, 132, 143, 150, 152, 154], "deprec": [2, 5, 10, 19, 31, 154], "depreci": [3, 4, 8, 27, 28, 29, 30, 31, 32], "depth": [3, 4, 11, 26, 27, 28, 29, 30, 32, 89, 90, 97, 99, 100, 104, 105, 117], "depth_multipli": [97, 100, 105], "depthwis": [89, 97, 100, 105], "deriv": 113, "desc_4": 73, "describ": [5, 11, 26, 27, 28, 29, 32, 77, 79, 93, 94, 97, 98, 99, 103, 109, 110, 111, 112, 117], "descript": [2, 5, 8, 12, 17, 18, 19, 20, 22, 27, 28, 29, 30, 32, 73, 74, 75, 76, 81, 82, 83, 86, 87, 89, 90, 95, 98, 100, 101, 102, 103, 104, 105, 106, 108, 110, 117, 125, 126], "design": [5, 16, 91, 92, 104, 107, 112, 120], "desir": [37, 49, 57, 68, 74, 118, 124], "despit": [9, 10, 11], "detail": [5, 26, 29, 32, 47, 48, 66, 67, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 123, 124, 130, 131, 145, 152], "detect": [16, 17, 19, 30, 77, 79], "determin": [12, 30, 72, 90, 97, 132], "develop": [26, 29, 32, 92, 108, 148, 152], "deviat": [44, 63], "devic": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 36, 72, 132, 154], "df": [2, 5, 8, 9, 10, 11, 12, 16, 27, 28], "df_of_ages_gend": 12, "dh": 89, "dict": [5, 9, 10, 11, 21, 26, 36, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 75, 76, 78, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 125, 126, 130, 132, 154], "dictionari": [21, 26, 72, 75, 78, 120, 132], "diederik": 31, "differ": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 18, 21, 26, 27, 28, 29, 30, 74, 97, 98, 117, 135, 150], "differenti": [38, 39, 58, 60], "digit": [11, 22, 117, 133], "dilat": [9, 10, 11, 27, 99, 100], "dilation_block_4": 100, "dilation_block_5": 100, "dim": [2, 8, 107], "dimens": [2, 5, 8, 46, 54, 65, 70, 89, 90, 95, 107, 112, 117, 123, 154], "dimension": [5, 72, 90, 91, 95, 104, 113, 132, 143], "dimshuffl": [3, 4, 26, 27, 28, 29, 32], "ding": 46, "direct": [77, 120, 148], "directli": [2, 3, 5, 8, 12, 22, 26, 27, 28, 30, 31, 72, 83, 122, 124, 132, 152], "directori": [12, 16, 18, 27, 73, 75, 79, 81, 82, 87, 131, 152], "dirnam": 5, "disabl": [32, 72, 120, 132], "disappear": 74, "discard": [12, 80], "disconsid": 12, "discov": 5, "discret": [15, 23, 24, 75, 81, 125, 153, 154], "discrimin": 30, "disk": [12, 14, 16, 81, 82, 126], "dispatch": 14, "displai": [5, 9, 10, 11, 27, 28, 29, 32, 77, 145], "distanc": [37, 57, 74], "distinct": [29, 32], "distinguish": 29, "distribut": [9, 10, 29, 47, 107, 113, 150], "divers": [2, 4, 8], "divid": [77, 84, 85, 86, 125], "divis": [29, 32, 110, 112, 129], "divyesh": [10, 154], "dl": 22, "do": [4, 12, 14, 26, 27, 29, 32, 72, 84, 85, 86, 117, 125, 126, 132, 136, 145, 152, 154], "doc": [26, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 145, 152, 154], "docstr": [26, 154], "document": [4, 5, 10, 12, 35, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 118, 120, 121, 123, 124, 148, 152, 154], "doe": [2, 8, 14, 16, 18, 27, 29, 32, 45, 72, 89, 99, 126, 132, 148], "doesn": [32, 72, 73, 132], "dogrusoz": [37, 44, 54, 57, 63, 70], "doi": [2, 8, 10, 26, 27, 28, 29, 30, 35, 73, 89, 93, 96, 97, 103, 105, 106, 109, 110, 112, 115, 147], "domain": [2, 4, 8, 16, 28, 30, 43, 48, 61, 67, 104, 117, 120, 123], "dominiqu": 35, "don": [5, 11, 17, 19, 72, 132], "done": [3, 11, 16, 18, 26, 27, 89, 125, 126], "dong": [94, 107], "doubl": 120, "double_time_conv": 14, "down": [74, 110, 117, 123, 145], "download": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 73, 81, 82, 151], "downsampl": [9, 10, 90, 104, 123], "downsid": 16, "downstream": 5, "downward": 77, "draw": [42, 62], "drawn": 47, "driver": 151, "drop": [3, 4, 10, 14, 19, 26, 27, 28, 29, 32, 38, 58, 86, 119, 126, 130], "drop_bad": [14, 86, 126], "drop_bad_window": [86, 126], "drop_channel": 119, "drop_index": [72, 132], "drop_last_window": [2, 12, 14, 17, 19, 22, 27, 31, 84, 85, 86, 125, 126], "drop_original_sign": 130, "drop_path_r": 107, "drop_prob": [14, 26, 30, 93, 95, 96, 97, 101, 102, 105, 109, 114, 115], "drop_rat": [100, 107, 108], "dropchannel": 154, "dropout": [3, 4, 5, 9, 10, 26, 27, 28, 29, 30, 32, 89, 90, 93, 95, 96, 97, 100, 107, 108, 109, 110, 111, 112, 114, 115], "dropout_inp": 90, "droppath": 107, "dtype": [22, 84, 125, 126, 128, 129, 154], "due": [18, 32, 154], "dummi": [2, 27], "dunder": [72, 132], "duplic": [144, 154], "dur": [2, 3, 5, 8, 9, 10, 11, 26, 27, 28, 29, 30, 31], "durat": [12, 29, 30, 31, 118, 120, 126], "dure": [2, 4, 5, 8, 9, 10, 11, 12, 14, 27, 28, 29, 30, 32, 72, 73, 90, 107, 108, 120, 124, 132, 154], "dx": [26, 35, 93, 97, 103, 106, 109, 147], "dynam": [72, 113, 132], "dzirasa": 113, "e": [5, 9, 10, 11, 14, 16, 26, 27, 28, 29, 30, 32, 37, 40, 44, 46, 54, 56, 57, 59, 63, 65, 70, 72, 76, 79, 80, 81, 82, 83, 86, 89, 93, 94, 95, 96, 97, 98, 99, 101, 103, 106, 107, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 126, 130, 132, 136, 140, 147, 152, 154], "e1750": 108, "e1762": 108, "e215": [5, 9, 10, 11], "e220": [5, 9, 10, 11], "e231": 154, "e46769": 92, "each": [2, 4, 8, 9, 10, 11, 12, 14, 16, 17, 19, 21, 22, 26, 29, 30, 31, 36, 37, 38, 42, 46, 48, 49, 53, 55, 57, 58, 62, 65, 67, 68, 69, 71, 72, 73, 74, 75, 77, 80, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 123, 125, 126, 132, 134, 136, 138, 139, 140, 144], "eager": [15, 23, 24, 82, 93, 109, 125, 153], "earli": 29, "early_stop": 5, "earlystop": [5, 29, 32], "easiest": [26, 29], "easili": [2, 8, 20, 26, 28, 29, 30, 32, 134], "eca": 90, "ecg": 91, "ecog": [1, 6, 7, 13, 24, 73, 75, 99, 109, 122, 124, 125, 127, 129, 131, 138, 139, 141, 145, 149, 153, 154], "ecosystem": 32, "edf": [14, 16, 17, 19, 22], "edfx": 80, "edg": [16, 120], "edit": 152, "edu": [2, 4, 8, 73], "eeg": [1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 20, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33, 35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 74, 75, 77, 78, 79, 80, 81, 82, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 121, 122, 124, 125, 126, 129, 131, 134, 135, 142, 145, 147, 149, 153, 154], "eegbci": [17, 19], "eegclassifi": [2, 5, 9, 10, 11, 26, 27, 28, 29, 30, 154], "eegconform": [26, 154], "eegincept": [97, 154], "eeginceptionerp": [26, 154], "eeginceptionmi": [26, 154], "eegitnet": [26, 154], "eegmmidb": [17, 19], "eegmodulemixin": [2, 31, 154], "eegnet": [101, 102, 105], "eegnet4": 102, "eegnetv1": 26, "eegnetv4": 26, "eegnex": [26, 154], "eegnexcod": 100, "eegregressor": [2, 8, 26, 31, 154], "eegresnet": [26, 154], "eegsimpleconv": [26, 154], "eegtcnet": [26, 154], "eegwindowsdataset": [5, 9, 16, 126, 154], "eeyhsong": 95, "effect": [3, 19], "effici": [2, 3, 16, 27, 90], "egg": 152, "eggensperg": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 147], "einop": 154, "either": [2, 8, 26, 28, 29, 30, 72, 74, 75, 77, 99, 120, 124, 132, 143], "el": [104, 154], "elabor": [29, 32], "eldel": [10, 112], "eldele2021": [7, 13, 24, 75, 80, 99, 112, 116, 122, 126, 131, 134, 136, 145, 147, 153], "electrocorticograph": [2, 8, 73], "electrod": [4, 20, 74, 77, 124], "electroencephalogram": [37, 44, 54, 57, 63, 70, 92, 100], "electroencephalograph": [49, 50, 51, 52, 68], "electroencephalographi": 35, "electrophysiolog": 149, "element": [48, 49, 54, 68, 90], "elementwise_affin": 10, "elif": [14, 31], "elouaya": 104, "els": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 27, 28, 29, 30, 31, 32, 72, 107, 132], "elu": [11, 89, 90, 91, 92, 93, 94, 95, 96, 97, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 114, 115, 117], "emadeldeen24": 112, "emb": [5, 91], "emb_siz": [5, 91, 92, 107], "embc": [49, 50, 51, 52, 68], "embed": [5, 9, 10, 89, 91, 92, 95, 105, 107], "embedd": 5, "emg": 80, "emir": 11, "emit": 119, "emot": [44, 63, 113], "empir": [47, 66, 114, 142], "emploi": 90, "empti": [29, 72, 120, 124], "en": 27, "enabl": [14, 16, 27, 32, 72, 74, 115, 132, 154], "encapsul": 126, "encnet": 90, "encod": [11, 46, 90, 91, 112, 117], "encount": [16, 18, 148], "encourag": [2, 8, 24, 27, 28], "end": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 35, 72, 98, 118, 123, 125, 126, 132, 138, 139, 140, 154], "end_dim": [9, 10], "enforc": 154, "eng": 115, "engemann": [4, 5, 35, 135, 154], "engin": [4, 5, 9, 10, 28, 29, 30, 46, 49, 50, 51, 52, 68, 94, 95, 97, 98, 111, 112], "enough": [5, 77], "ensembl": [136, 154], "ensur": [2, 117, 145, 151, 154], "ensure4d": [3, 4, 26, 27, 28, 29, 32], "ensure_odd_conv_s": 117, "ensuredim": [3, 4, 26, 27, 28, 29, 32], "enter": [104, 152], "entir": [5, 14, 20, 29, 32, 154], "entri": [21, 119], "enumer": [5, 12, 29, 32], "env": 154, "environ": [4, 73, 145], "eog": [80, 117], "ep": [10, 129], "epo": [18, 75, 87], "epoch": [2, 3, 4, 5, 8, 9, 10, 11, 14, 19, 24, 25, 27, 28, 29, 30, 31, 32, 33, 72, 75, 83, 85, 86, 99, 109, 118, 119, 120, 121, 122, 124, 125, 126, 132, 135, 138, 139, 140, 153, 154], "epochsarrai": 26, "epochscor": [5, 8, 9, 10, 11, 72, 132], "epochscoring_1": [72, 132], "equal": [2, 8, 32, 84, 85, 86, 99, 107, 125], "equival": [3, 120], "eras": 38, "eric": 35, "erp": 97, "error": [12, 22, 27, 30, 31, 86, 119, 125, 126, 127, 132, 148, 154], "error_scor": [4, 29, 30], "eskandarian": 98, "especi": [9, 30, 32], "estim": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32], "et": [10, 26, 46, 77, 91, 93, 94, 96, 101, 102, 103, 106, 109, 110, 111, 112, 114, 115, 117, 140], "etc": [14, 28, 30, 91, 122], "ethic": 77, "eval": [4, 30, 32, 154], "eval_i": [4, 30], "eval_set": [4, 30], "eval_x": [4, 30], "evalu": [2, 3, 4, 5, 8, 9, 10, 11, 14, 21, 27, 28, 30, 92, 104, 114], "even": [11, 26, 29, 32, 72, 73, 117, 132], "event": [18, 19, 20, 21, 26, 27, 28, 29, 30, 32, 80, 86, 125, 126], "event_cod": [17, 19], "everi": [9, 10, 11, 12, 14, 18, 22, 29, 32, 77, 89, 90, 95, 98, 154], "evok": [119, 120, 121, 124], "exact": 26, "exactli": 126, "exampl": [1, 2, 6, 8, 9, 10, 11, 13, 14, 15, 16, 22, 23, 25, 31, 33, 34, 37, 39, 40, 44, 45, 46, 47, 48, 49, 55, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 124, 148, 153, 154], "exce": 118, "exceed": [86, 126], "except": [77, 80], "excess": 22, "excit": 90, "exclud": [118, 120, 121, 124], "exclus": [29, 32], "execut": [5, 6, 11, 12, 13, 14, 16, 17, 19, 23, 33, 34, 77, 131, 153, 154], "exemplifi": 154, "exist": [16, 18, 22, 29, 31, 73, 75, 76, 83, 124, 131], "exp": 113, "expand": [72, 90, 117, 132], "expand_dim": 31, "expans": [90, 107], "expect": [5, 14, 26, 32, 72, 92, 132], "expens": [14, 72, 132], "experi": [7, 14, 24, 29, 32, 73, 77], "experiment": [5, 125, 154], "expert": [9, 10, 11, 108], "explain": [1, 4, 24, 27, 96], "explan": [2, 27, 130, 131], "explicit": [27, 140], "explicitli": [5, 29, 32, 120, 121, 124], "explor": [5, 29], "exponent": [128, 129], "exponenti": [2, 3, 4, 8, 27, 28, 29, 30, 32, 117, 128, 129], "exponential_moving_standard": [2, 3, 4, 8, 27, 28, 29, 30, 32], "expos": 154, "express": [3, 4, 26, 27, 28, 29, 32], "extra": [32, 154], "extra_param": 90, "extract": [2, 8, 12, 14, 16, 17, 19, 22, 27, 32, 83, 97, 98, 107, 110, 112, 113, 125, 126, 133, 135], "extractor": [5, 9, 10, 94, 110, 111, 112, 117], "f": [4, 5, 10, 11, 12, 14, 16, 17, 22, 26, 27, 28, 29, 30, 31, 32, 44, 48, 63, 67, 79, 93, 97, 103, 106, 109, 115, 147], "f1": [5, 9, 10, 11, 89, 102, 140], "f2": 102, "f3": 12, "f4": 12, "f7": 12, "f8": 12, "f811": [12, 22], "f_c": 113, "f_criterion": 5, "f_histori": 5, "f_name": 5, "f_optim": 5, "facebookresearch": [47, 66, 142], "facilit": [26, 154], "factor": [3, 4, 5, 9, 10, 12, 27, 28, 29, 30, 32, 48, 90, 104, 107, 112, 115, 117, 123], "factor_new": [2, 3, 4, 8, 27, 28, 29, 30, 32, 128, 129], "factornew": [128, 129], "fail": [5, 12], "fake": [24, 25, 26, 33, 75, 76, 93, 99, 109, 125, 137, 145, 153, 154], "fake_data_split": 31, "fake_descript": 31, "fake_dur": 31, "fake_regression_dataset": 31, "fake_sfreq": 31, "fall": [86, 126], "fals": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 22, 26, 27, 28, 29, 30, 31, 32, 42, 47, 49, 50, 51, 52, 62, 68, 72, 73, 75, 76, 79, 80, 81, 82, 83, 86, 88, 89, 90, 91, 93, 94, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 109, 110, 111, 112, 114, 115, 117, 118, 122, 124, 125, 126, 127, 130, 131, 132, 135, 136, 138, 139, 145, 147, 154], "familiar": 150, "far": [5, 135], "farrugia": 104, "fast": [14, 16, 32, 145], "faster": [10, 16, 27, 72, 123, 132], "fattouh": [2, 8, 154], "favor": 154, "favour": 154, "fc": [10, 112], "fca": 90, "feat": 5, "feat_extractor": [9, 10], "featur": [5, 9, 10, 26, 29, 90, 94, 95, 97, 98, 99, 104, 107, 110, 111, 112, 113, 117, 148, 152, 154], "feature_extractor": [9, 10], "feature_map": 104, "features1": 10, "features2": 10, "fed": [2, 27, 50, 51, 52, 104], "feed": [89, 112], "feed_forward": 10, "feedback": [5, 9, 10, 11, 74], "feedforwardblock": 95, "feel": [29, 32], "feet": [17, 18, 19, 21, 27, 28, 29, 30, 32, 74, 77], "femal": [12, 77], "female_df": 12, "fernand": 108, "fernandez": 110, "fetch": [17, 19, 20, 21, 74, 77, 78], "fetcher": 149, "few": [5, 9, 10, 11, 14, 16, 26, 154], "fewer": [117, 120], "fexion": 8, "fft": 123, "fieder": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 147], "field": [2, 27, 72, 124, 132, 143], "fif": [14, 16, 18, 75, 87, 154], "fiff_unit_v": 26, "fiff_unitm_non": 26, "fiffv_coil_eeg": 26, "fiffv_coord_head": 26, "fiffv_eeg_ch": 26, "fig": [2, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 31, 147], "figsiz": [2, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 31, 147], "figur": [12, 27, 28, 29, 74, 89, 147], "file": [5, 6, 12, 13, 14, 16, 17, 18, 19, 23, 26, 33, 34, 75, 80, 81, 82, 87, 118, 136, 148, 153, 154], "file_id": 136, "fileexistserror": 131, "fill": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117], "filter": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 20, 26, 27, 28, 29, 30, 32, 37, 57, 74, 89, 90, 93, 95, 97, 98, 100, 102, 105, 109, 111, 113, 114, 115, 117, 122, 123, 130, 154], "filter_1": [100, 105], "filter_2": 100, "filter_data": 120, "filter_length": 120, "filter_length_2": [14, 93], "filter_length_3": [14, 93], "filter_length_4": [14, 93], "filter_time_length": [14, 26, 93, 95, 109], "filter_width": 113, "filterbank": 154, "filtfilt": 120, "final": [2, 4, 5, 8, 9, 10, 11, 12, 14, 16, 26, 27, 29, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 129], "final_conv_length": [2, 3, 4, 8, 14, 26, 27, 28, 29, 30, 31, 32, 93, 101, 102, 109, 154], "final_fc_length": 95, "final_lay": [3, 4, 11, 26, 27, 28, 29, 32], "final_pool_length": [103, 154], "find": [2, 4, 8, 30], "fine": 30, "finer": [8, 154], "finger": [1, 6, 7, 13, 24, 73, 75, 77, 99, 109, 122, 125, 127, 129, 131, 138, 139, 141, 145, 153, 154], "fir": [16, 120, 123], "fir_design": 120, "fir_window": 120, "first": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 26, 27, 28, 30, 40, 46, 54, 65, 70, 72, 75, 79, 80, 81, 82, 89, 90, 93, 95, 100, 104, 105, 109, 112, 120, 123, 124, 126, 132, 148, 152], "first_filter_length": 103, "first_pool_mod": [14, 93], "first_pool_nonlin": 93, "first_samp": 118, "firstli": [12, 21], "firwin": [16, 120], "firwin2": 120, "fit": [2, 3, 5, 8, 9, 10, 11, 14, 24, 26, 27, 28, 29, 30, 31, 32, 72, 126, 132], "fit_loop": 32, "fit_param": [4, 30, 132], "fit_transform": 5, "five": [12, 73], "fix": [3, 40, 59, 91, 107, 120, 148, 154], "fix_init_weight_and_init_embed": 107, "fixat": 74, "flag": [90, 154], "flake8": 154, "flat": [10, 19, 38, 58, 125, 126, 127], "flatten": [5, 9, 10, 11], "flexion": [1, 6, 7, 13, 24, 73, 75, 99, 109, 122, 125, 127, 129, 131, 138, 139, 141, 145, 153, 154], "flip": [5, 53, 55, 69, 71], "float": [3, 5, 26, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 63, 68, 72, 80, 84, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 123, 125, 126, 128, 129, 130, 132, 142, 147], "float32": 22, "float64": [17, 19, 31], "fly": [2, 8, 28, 30, 76, 83, 154], "fmax": 3, "fmin": 3, "fmt": 30, "fn": [18, 122], "fname": 14, "fnin": 35, "focu": 4, "fold": [4, 30, 32], "folder": [14, 73], "follow": [3, 4, 5, 9, 10, 11, 14, 26, 29, 32, 91, 97, 104, 107, 120, 123, 126, 132, 150, 151, 152, 154], "font": 147, "font_scal": 29, "fontsiz": [2, 8, 12, 27, 28], "fontweight": 147, "foot": 74, "footcit": 124, "forc": 73, "force_upd": 73, "form": [26, 47, 66, 74, 75, 76, 83], "format": [4, 14, 17, 19, 26, 84, 85, 86], "former": [26, 72, 89, 90, 95, 98, 132], "fortun": 26, "forum": 145, "forward": [3, 4, 5, 11, 26, 27, 28, 29, 32, 41, 56, 72, 89, 90, 91, 92, 94, 95, 98, 99, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 117, 120, 122, 124, 132, 137, 141, 143], "forward_featur": 107, "found": [2, 8, 10, 12, 16, 18, 19, 20, 21, 26, 27, 28, 29, 30, 32, 73, 124, 125, 126], "four": [5, 9, 49, 74, 77, 90], "fourier": [42, 62, 92], "fp1": 12, "fp2": 12, "fpz": 10, "fr": [3, 4, 11], "fraction": [29, 31], "framework": [4, 90], "frank": 35, "free": [29, 32], "freedom": [29, 32], "freez": [9, 10, 154], "freiburg": 77, "freq": [3, 74, 77], "freq_idx": 90, "freq_shift": 3, "freqs_to_notch": [37, 57], "frequenc": [2, 3, 4, 8, 11, 12, 16, 17, 26, 27, 28, 29, 30, 31, 32, 37, 43, 57, 61, 77, 84, 89, 90, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 123, 130, 133, 154], "frequency_band": 130, "frequencyshift": 3, "frequent": [9, 10, 11], "friendli": 154, "from": [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 38, 39, 42, 47, 49, 50, 51, 52, 58, 60, 62, 68, 72, 74, 76, 77, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 93, 94, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 124, 125, 126, 132, 133, 134, 135, 136, 138, 139, 140, 142, 143, 150, 153, 154], "front": 74, "frontier": [27, 28, 29, 30, 35, 79], "frontiersin": 35, "ft": [42, 62, 89], "ft_surrog": 154, "ftsurrog": 4, "full": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 145], "fulli": [11, 29, 30, 89, 95, 97, 98, 105], "function": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 20, 22, 26, 27, 28, 30, 31, 32, 35, 42, 56, 72, 75, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 122, 124, 126, 132, 138, 139, 140, 145, 154], "functool": 30, "fundament": [24, 25], "further": [2, 4, 5, 8, 9, 10, 11, 27, 29, 32, 72, 90, 132], "furu": 107, "fusion": 90, "futur": [5, 10, 19, 26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117], "futurewarn": [2, 5, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117], "fz": 12, "g": [5, 9, 10, 11, 14, 16, 26, 27, 28, 29, 30, 32, 37, 40, 42, 44, 54, 56, 57, 59, 62, 63, 72, 76, 79, 80, 81, 82, 83, 86, 89, 93, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 109, 110, 111, 114, 115, 116, 117, 118, 119, 120, 121, 122, 126, 130, 132, 136, 140, 147, 154], "galleri": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 153], "galtier": [5, 9, 10, 111], "gamma": 77, "gamma_1": 107, "gamma_2": 107, "gao": 95, "gate": 90, "gather": 90, "gaussian": [31, 44, 63], "gave": [4, 30], "gb": [9, 10, 11], "gca": 12, "gct": 90, "ge": [90, 108], "gelu": [10, 95, 107, 112], "gemein": [12, 17, 18, 19, 20, 21, 22, 31, 154], "gender": [12, 18, 22, 79, 81, 82], "gener": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 32, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 67, 72, 99, 107, 110, 113, 114, 120, 132, 140, 147, 154], "georg": 30, "get": [14, 16, 17, 22, 27, 28, 29, 32, 48, 72, 107, 132], "get_augmentation_param": [37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 56, 154], "get_center_label": [9, 10], "get_classifi": 107, "get_config": 27, "get_data": 17, "get_default_callback": [72, 132], "get_fc_siz": 95, "get_iter": [72, 132], "get_label": [2, 8, 27, 28], "get_legend_handles_label": 5, "get_loss": 72, "get_metadata": [5, 9, 10, 11, 27, 28, 29, 31, 75, 134], "get_num_lay": 107, "get_output_shap": [2, 27, 31, 99, 154], "get_param": 154, "get_posit": [49, 68], "get_torchinfo_statist": 99, "get_ylim": [27, 28], "geyer": 100, "gh": 154, "ghaith": 154, "gillmeist": 96, "gilmer": 30, "git": 152, "github": [4, 5, 30, 90, 91, 92, 104, 107, 108, 148, 150, 154], "give": [10, 12, 22, 26, 49, 68, 120, 148], "given": [3, 4, 5, 21, 32, 38, 39, 40, 42, 48, 53, 55, 56, 72, 73, 87, 120, 121, 124, 132, 143, 154], "gizzi": 90, "glass": [5, 9, 10, 11], "glasstett": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 147], "global": [72, 90, 104, 132, 140], "glossari": [2, 4, 8], "gmail": [2, 5, 8, 9, 10, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31], "gnassoun": [11, 154], "go": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 118], "goal": [32, 97, 98], "godbol": 30, "goe": 16, "goh": [37, 44, 54, 57, 63, 70], "goj": 35, "goldberg": [5, 9, 10, 11], "good": [2, 8, 26, 27, 28], "googl": 30, "gordon": [101, 102], "got": 30, "gpu": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 72, 132, 151, 154], "gradient": [27, 154], "gradiomet": 3, "grai": 77, "gramfort": [4, 5, 9, 10, 35, 111, 135, 154], "grand": 113, "grangier": [38, 39, 58, 60], "greater": [37, 57], "green": 12, "grid": [29, 30], "gridsearchcv": [4, 29, 30, 140, 154], "gridsearchcvifittedgridsearchcv": 4, "grifcc": 97, "gripon": 104, "ground": [31, 74, 77], "group": 110, "groupbi": 16, "growth": [108, 115], "growth_rat": 108, "gsop": 90, "gt": 4, "guarante": [92, 96, 97, 98, 100, 101, 102, 108, 113], "guetschel": [26, 154], "guid": [22, 29, 151], "guidelin": 152, "guo": 94, "gustavo": 154, "h": [2, 4, 5, 8, 27, 28, 37, 40, 44, 54, 57, 59, 63, 70, 79, 89, 94, 96, 100, 135], "h_freq": [2, 3, 4, 5, 8, 9, 10, 16, 27, 28, 29, 30, 32, 120], "h_trans_bandwidth": 120, "ha": [2, 3, 4, 5, 8, 10, 12, 18, 19, 20, 21, 22, 27, 28, 29, 30, 31, 32, 50, 51, 52, 72, 75, 76, 80, 83, 86, 92, 96, 97, 98, 100, 101, 102, 108, 113, 117, 126, 131, 132, 142, 148, 154], "hac": [9, 10, 11], "had": [77, 97, 99], "half": [111, 120], "halv": 117, "ham": [16, 120], "hamlet": [40, 59], "hand": [17, 19, 24, 28, 30, 74, 77], "handl": [2, 3, 4, 8, 27, 28, 30, 124], "hangbo": 107, "hann": 120, "happen": [148, 154], "hard": 148, "hardwar": [14, 16], "hasattr": 30, "hausdorff": [5, 9, 10, 11], "have": [2, 4, 5, 8, 11, 12, 14, 16, 17, 19, 21, 26, 27, 28, 29, 30, 32, 46, 49, 54, 65, 68, 70, 72, 84, 85, 86, 98, 104, 107, 122, 124, 125, 132, 140, 148, 151, 152, 154], "hbm": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 147], "hbm23730": 35, "he": [9, 10, 11], "head": [89, 91, 95, 107, 112, 134], "head_dim": 107, "health": [37, 44, 54, 57, 63, 70, 91], "healthi": [77, 79, 80], "heart": 91, "heatmap": 30, "heavi": 147, "height": [12, 29, 100], "held": [9, 10], "help": [5, 9, 10, 21, 124], "helper": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31], "henrik": 154, "here": [2, 3, 4, 5, 8, 10, 11, 12, 21, 22, 24, 26, 27, 28, 29, 30, 32, 43, 61, 79, 86, 91, 98, 126], "hersch": 105, "heterogen": [38, 39, 58, 60], "high": [2, 3, 4, 8, 11, 27, 28, 29, 30, 32, 37, 57, 77, 97, 117, 120, 133], "high_cut_hz": [2, 3, 4, 5, 8, 9, 10, 27, 28, 29, 30, 32], "higher": [2, 5, 8, 32, 112], "highli": 29, "hint": 154, "hist": 12, "histori": [2, 5, 8, 9, 10, 11, 27, 28, 31, 72, 132], "hold": [18, 75, 76, 83, 125, 126], "holdout": 29, "home": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 27, 28, 29, 30, 31, 32], "hong": 108, "hongyi": [47, 66, 142], "honor": [72, 132], "hook": [89, 90, 95, 98, 154], "hop": 91, "hop_length": [91, 92], "horizont": 12, "horizontalalign": 29, "hornero": 97, "hospit": [12, 81, 82, 154], "host": 27, "how": [2, 3, 4, 5, 8, 9, 10, 11, 12, 17, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 30, 31, 33, 72, 75, 78, 90, 99, 109, 118, 122, 124, 126, 129, 131, 132, 145, 153, 154], "howev": [2, 3, 4, 5, 8, 11, 14, 16, 21, 26, 27, 28, 29, 126], "hpu": 32, "hspace": 12, "html": [2, 4, 5, 8, 12, 26, 27, 72, 80, 81, 82, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 132, 145, 147, 154], "http": [2, 4, 5, 8, 12, 26, 27, 28, 29, 30, 35, 47, 66, 72, 73, 74, 77, 80, 89, 93, 95, 96, 97, 98, 99, 101, 103, 105, 106, 109, 110, 112, 114, 115, 117, 132, 142, 145, 147, 152], "hubert": [5, 9, 14, 16, 20, 154], "hue": 14, "hum": [27, 28, 29, 30], "human": [2, 8, 26, 31, 35, 40, 59, 73, 93, 103, 106, 109, 120, 147], "hung": [101, 102], "hutter": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 147], "hybrid": 106, "hybridnet": 26, "hyeperparamet": 30, "hyperparamet": [2, 5, 8, 9, 10, 11, 14, 24, 25, 27, 28, 32, 33, 47, 72, 75, 78, 99, 104, 109, 122, 126, 129, 131, 132, 145, 153, 154], "hypnogram": [9, 10, 11], "hyv\u00e4rinen": [4, 5, 135], "hz": [2, 3, 4, 5, 8, 9, 11, 16, 27, 29, 30, 31, 37, 43, 57, 61, 74, 89, 95, 98, 117, 120], "h\u00e4m\u00e4l\u00e4inen": 35, "i": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 21, 22, 26, 27, 28, 30, 31, 35, 37, 41, 42, 43, 46, 47, 49, 54, 56, 57, 61, 62, 65, 66, 68, 70, 72, 73, 74, 75, 76, 77, 78, 79, 83, 84, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 122, 123, 124, 125, 126, 131, 132, 135, 140, 144, 145, 149, 150, 151, 154], "i_class": [27, 28], "i_start_in_tri": [83, 134], "i_stop_in_tri": [83, 134, 144], "i_window_in_tri": [83, 134, 144], "icassp": 113, "iclr": [47, 66, 107], "id": [12, 18, 20, 21, 27, 28, 29, 30, 32, 75, 79, 81, 82, 87, 125, 126, 131, 154], "ideal": 77, "ident": [9, 11, 32, 45, 72, 93, 132], "identifi": [9, 10, 11, 86, 126], "ids_to_load": [18, 87], "idx": [3, 4, 9, 10, 11, 26, 27, 28, 29, 30, 32], "idx_perm": [47, 66], "idx_shuffl": [48, 67], "idx_train": 8, "idx_valid": 8, "ie": 125, "ieee": [5, 9, 10, 11, 46, 48, 49, 50, 51, 52, 67, 68, 89, 94, 95, 96, 97, 111, 112], "ieeexplor": 95, "igel": [11, 117, 133], "ignor": [2, 3, 4, 8, 54, 72, 89, 90, 95, 98, 119, 122, 125, 126, 132, 135], "ii": 29, "iia": 74, "iir": 120, "iir_param": 120, "ill": 10, "illustr": [3, 29], "illutr": 3, "imag": [74, 97, 107], "imageri": [4, 74, 89, 90, 96, 98, 104, 105, 154], "imagin": [17, 19], "imbal": [42, 62, 80], "imbalanc": [9, 10, 11], "immedi": 125, "impact": [14, 27, 30], "implement": [9, 10, 14, 16, 26, 29, 46, 47, 56, 65, 66, 72, 89, 92, 96, 97, 98, 100, 101, 102, 107, 108, 113, 132, 142, 143, 149, 154], "implicitli": [5, 27, 29, 32], "import": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 42, 62, 148, 152], "impos": [89, 105], "imposs": 14, "improv": [2, 3, 5, 8, 9, 10, 11, 32, 120, 148, 154], "in_chan": [11, 26, 31, 93, 101, 102, 103, 106, 109, 115, 117], "in_channel": [96, 97, 98, 107], "in_featur": [9, 10], "inat": 74, "incept": [96, 97, 98, 154], "inceptionnet": [97, 98], "includ": [9, 11, 12, 14, 28, 29, 30, 32, 39, 60, 78, 104, 118, 120, 121, 125, 126, 148, 149], "include_tmax": [12, 118], "incom": [72, 132], "incompat": 154, "incomplet": 12, "inconsist": 126, "incorrect": 154, "increas": [2, 3, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 32, 90, 98, 112, 154], "ind": 22, "ind1": 5, "ind2": 5, "inde": 4, "independ": [29, 32, 42, 62, 120, 154], "indetermin": [2, 3, 4, 5, 8, 9, 11, 27, 28], "index": [2, 5, 8, 9, 10, 11, 17, 27, 28, 30, 31, 76, 90, 113, 118, 128, 129, 133, 134, 144, 150], "indic": [5, 9, 10, 21, 31, 47, 48, 66, 67, 75, 90, 120, 121, 124, 134, 135, 136, 154], "indices_": 29, "individu": [9, 10, 11, 12, 26, 27, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132, 154], "industri": 89, "inf": 12, "infer": [26, 29, 30, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 126, 132, 140], "infin": 124, "info": [2, 3, 4, 8, 12, 14, 16, 17, 19, 20, 21, 26, 27, 28, 29, 30, 32, 75, 83, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 121, 124, 134, 136, 148, 154], "inform": [3, 4, 12, 14, 17, 18, 20, 26, 29, 30, 42, 62, 72, 75, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 132, 134, 152], "informat": 89, "ingolfsson": 105, "inherit": [8, 9, 10, 11, 26, 28, 30, 72, 132], "init_block_s": [2, 3, 4, 8, 27, 28, 29, 30, 32, 128, 129], "init_scal": 107, "init_valu": 107, "initi": [3, 4, 5, 9, 10, 11, 26, 29, 30, 32, 72, 90, 95, 97, 107, 113, 117, 132], "initialis": [30, 132], "initialized_": [72, 132], "initialz": [72, 132], "inplac": [9, 10, 16], "input": [2, 3, 4, 8, 10, 11, 14, 21, 26, 27, 28, 29, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 68, 69, 70, 71, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 132, 154], "input_chan": 107, "input_s": 99, "input_size_": [89, 110, 111, 112, 117], "input_size_sampl": [5, 9, 10, 11], "input_window_": 98, "input_window_sampl": [2, 3, 4, 8, 14, 26, 27, 28, 29, 30, 31, 32, 93, 95, 96, 97, 101, 102, 103, 106, 109, 115], "input_window_second": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132], "inria": [3, 4, 11], "insecurerequestwarn": 27, "insert": [12, 22, 99], "insid": [4, 29, 30, 95, 97, 152], "insight": 5, "inspir": [107, 113, 133], "inst": [20, 119, 120, 121, 124], "instal": [32, 72, 120, 123, 132, 154], "instanc": [5, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 72, 89, 90, 95, 98, 118, 119, 120, 121, 124, 132, 134, 154], "instanti": [2, 3, 4, 8, 14, 26, 27, 28, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 72, 78, 132, 154], "instead": [3, 4, 5, 8, 22, 27, 28, 29, 30, 31, 32, 72, 89, 90, 95, 98, 99, 124, 132, 154], "instruct": 150, "int": [3, 4, 5, 9, 10, 14, 16, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 65, 67, 70, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 121, 123, 124, 125, 126, 128, 129, 131, 132, 133, 134, 135, 136, 143, 145, 147], "integ": [21, 22, 27, 28, 40, 46, 54, 59, 65, 70, 75, 120, 121, 131], "integr": [9, 10, 32, 154], "intend": 92, "intens": [4, 104], "inter": [74, 77], "interest": [5, 12, 22, 26], "interfac": [32, 35, 48, 67, 97, 101, 102, 105], "intermedi": 99, "intern": [11, 14, 16, 20, 21, 44, 47, 49, 50, 51, 52, 63, 66, 68, 107, 122], "interpol": [47, 49, 50, 51, 52, 66, 68], "interpret": [35, 40, 59, 108, 120, 121, 132], "interquartil": 11, "interrupt": [72, 132], "interv": [32, 77, 126, 154], "introduc": [5, 9, 10, 11, 14, 15, 24, 25, 27, 31], "invari": [115, 154], "invas": 77, "invert": 40, "invert_xaxi": 12, "invert_yaxi": 29, "investig": 26, "io": [5, 9, 16, 17, 19, 27, 76, 118, 120, 130], "ioven": 154, "ipynb": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32], "irregular": 148, "is_abbrev": [3, 4, 18, 20, 21, 29, 30], "is_avail": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32], "isinst": [9, 10], "isip": [12, 14, 81, 82], "isnan": 2, "isotrak": 16, "issn": 35, "issu": [5, 14, 16, 148, 154], "issubset": 12, "item": [5, 14, 19, 20, 26, 27, 28, 32], "iter": [3, 4, 5, 20, 22, 47, 72, 99, 119, 132, 143], "iterator_test": [72, 132], "iterator_test__batch_s": [72, 132], "iterator_train": [3, 4, 72, 132], "iterator_train__batch_s": [72, 132], "iterator_train__drop_last": [72, 132, 154], "iterator_train__num_work": 5, "iterator_train__sampl": [5, 9, 10, 11], "iterator_train__shuffl": [2, 5, 9, 10, 11, 27, 31, 72, 132], "iterator_train__transform": [3, 4], "iterator_valid": [72, 132], "iterator_valid__num_work": 5, "iterator_valid__sampl": [5, 9, 10, 11], "itertool": [14, 16], "itnet": [96, 154], "its": [3, 4, 5, 9, 10, 16, 18, 20, 21, 26, 29, 30, 31, 72, 75, 122, 131, 132], "itself": [14, 29, 30, 148], "iv": [1, 6, 7, 13, 20, 21, 24, 25, 26, 28, 29, 30, 32, 33, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 78, 89, 98, 99, 109, 122, 125, 126, 127, 129, 131, 137, 138, 139, 141, 145, 147, 153, 154], "ivanov": [5, 9, 10, 11], "izadi": [37, 44, 54, 57, 63, 70], "j": [2, 4, 5, 8, 26, 27, 28, 29, 30, 31, 37, 40, 42, 44, 54, 57, 59, 62, 63, 70, 73, 90, 91, 92, 93, 96, 101, 102, 103, 106, 108, 109, 111, 114, 115, 147], "ja": 35, "jankauska": 154, "javad": 154, "jayaram": [28, 29, 30], "jbanvil": [5, 9, 14, 16, 20], "je": [9, 10, 11], "jennum": [11, 117, 133], "jiang": [44, 63, 107], "jiang2024": 107, "jimmi": 31, "jin": [40, 59], "jing": 108, "jing2023": 108, "jjl": [9, 10, 11], "jm": [9, 10, 11], "jmir": 92, "job": [12, 72, 81, 82, 87, 120, 123, 125, 126, 131, 132], "joblib": [16, 131], "john": 154, "joint": 124, "jointli": 29, "josef": 35, "jost": 35, "journal": [4, 28, 29, 30, 35, 98], "json": [18, 75, 87, 154], "jupyt": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "just": [2, 4, 8, 22, 26, 28, 29, 30, 72, 93, 109, 132], "justin": 30, "k": [3, 5, 9, 10, 11, 26, 27, 28, 30, 31, 32, 37, 44, 49, 50, 51, 52, 54, 57, 63, 68, 70, 93, 98, 103, 106, 109, 113, 147], "kai": [2, 8, 73], "kaiser": 123, "kale": 31, "kamboh": 79, "kamphuisen": [5, 9, 10, 11], "katharina": 35, "kathrin": 154, "kc": 89, "keep": [3, 4, 10, 11, 16, 27, 28, 29, 30, 32, 77, 80, 154], "kei": [21, 26, 27, 28, 75, 76, 83, 107, 125, 126], "kemp": [5, 9, 10, 11], "kempfner": [11, 117, 133], "kept": [29, 32], "kern_length": 105, "kernel": [3, 4, 11, 26, 27, 28, 29, 30, 32, 49, 50, 51, 52, 68, 89, 90, 97, 98, 100, 104, 105, 110, 111, 114, 117], "kernel_block_4": 100, "kernel_block_5": 100, "kernel_length": 102, "kernel_s": [9, 10, 90, 99, 100, 104, 105, 114, 154], "kernel_unit_": 98, "keyboard": [72, 132], "keyword": [35, 36, 78, 118, 120, 121, 122, 123, 124, 130], "kfold": [4, 29, 30], "khan": 79, "khan2022": 79, "kiessner": 154, "kim": [49, 50, 51, 52, 68, 98], "kind": [14, 26], "kingma": 31, "know": [2, 3, 4, 26, 27], "known": [4, 72], "kobayashi": 105, "kolter": 114, "koltun": 114, "kosta": 115, "krell": [49, 50, 51, 52, 68], "kt": 89, "kumar": 31, "kv": [27, 28], "kwarg": [36, 72, 99, 122, 132, 138, 139, 140], "l": [5, 9, 10, 11, 12, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 89, 90, 93, 103, 105, 106, 109, 113, 117, 133, 147], "l2": [5, 89, 105], "l_freq": [2, 3, 4, 5, 8, 9, 10, 16, 27, 28, 29, 30, 32, 120], "l_trans_bandwidth": 120, "lab": 77, "label": [2, 3, 5, 8, 9, 10, 11, 12, 16, 22, 26, 27, 28, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 116, 132, 135, 137, 141, 143, 147], "label_dict": [27, 28], "labelcolor": [2, 5, 8, 27, 28], "labelpad": 12, "labels": [2, 8, 12, 27, 28], "labels1": 5, "labels2": 5, "labram": [26, 154], "lack": 145, "lam": [47, 66], "lambda": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32, 72, 103, 132], "lampx": 27, "lan": [9, 10, 11], "lanc": [101, 102], "languag": 91, "larg": [2, 5, 14, 16, 26, 27, 75, 91, 107, 126, 131], "larger": [2, 5, 27, 97], "largest": 97, "larson": 35, "last": [5, 22, 27, 31, 32, 46, 48, 54, 65, 70, 77, 80, 84, 85, 86, 89, 95, 105, 120, 123, 125, 126, 154], "last_samp": 118, "last_target_onli": [2, 8, 83, 125, 127], "latenc": 104, "later": [5, 12, 22, 76, 77, 79, 81, 82, 93], "later_pool_mod": [14, 93], "later_pool_nonlin": 93, "latest": [148, 151, 152], "latter": [89, 90, 95, 98], "lauri": 35, "lawhern": [101, 102], "layer": [3, 4, 5, 9, 10, 11, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 154], "layernorm": [10, 107], "lazi": [12, 15, 16, 23, 24, 82, 93, 109, 125, 153, 154], "lazy_metadata": [125, 154], "lazy_vs_eager_loading_result": 14, "lbfg": 5, "lead": [27, 29, 72, 124, 132], "leaderboard": [74, 77], "leakag": [29, 32], "leakyrelu": 115, "learn": [1, 2, 3, 4, 6, 8, 9, 10, 11, 24, 25, 27, 28, 29, 31, 32, 33, 35, 37, 38, 39, 40, 44, 46, 47, 54, 57, 58, 59, 60, 63, 66, 70, 72, 75, 78, 80, 90, 91, 92, 93, 97, 99, 103, 104, 106, 107, 108, 109, 111, 112, 122, 126, 129, 131, 132, 134, 135, 145, 147, 149, 151, 153, 154], "learnabl": [29, 107, 113], "learning_r": 30, "least": [12, 120, 134, 135, 144], "leav": [5, 29, 154], "leeb": [27, 28, 29, 30], "left": [12, 27, 28, 29, 40, 72, 74, 77, 132], "left_hand": [18, 21, 27, 28, 29, 30, 32], "leftward": 77, "legaci": [20, 120], "legend": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 31], "len": [5, 8, 9, 10, 11, 12, 14, 17, 20, 22, 29, 32, 130], "len_last_lay": [9, 10], "length": [8, 9, 11, 12, 14, 16, 26, 27, 30, 46, 47, 65, 66, 74, 75, 77, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 120, 123, 125, 126, 154], "less": [5, 27, 29, 32], "let": [3, 4, 22, 26], "level": [5, 9, 10, 22, 73, 108, 118, 120, 121, 123, 124, 154], "leverag": [5, 112], "lfilter": 120, "lfp": 113, "li": [107, 113], "li2017": 113, "liang": 107, "lib": [2, 5, 10, 11, 27, 31, 32], "librari": [2, 3, 4, 8, 24, 26, 28, 29, 30, 35, 73, 152], "licens": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31], "light": [11, 147], "lightning_log": 32, "lightningmodul": 32, "like": [2, 8, 16, 26, 28, 29, 30, 32, 37, 42, 48, 49, 57, 62, 67, 68, 72, 84, 85, 86, 90, 91, 92, 94, 96, 101, 103, 104, 107, 108, 110, 111, 112, 114, 115, 117, 120, 121, 132, 134, 152, 154], "likelihood": [27, 72], "limit": [2, 5, 8, 11, 12, 16, 26, 118], "lin": 108, "line": [2, 8, 14, 27, 28, 31, 74, 148], "line2d": [2, 8, 27, 28], "linear": [5, 9, 10, 26, 30, 47, 66, 89, 91, 93, 94, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 109, 110, 111, 112, 114, 115, 117, 120, 123], "linear_model": 5, "linearattentiontransform": 91, "linearsegmentedcolormap": 147, "lines1": 5, "lines2": 5, "linestyl": [2, 8, 12, 27, 28], "linewidth": [2, 8, 27, 28], "link": [148, 154], "linspac": [4, 12], "lioi": 104, "list": [3, 5, 11, 14, 16, 21, 22, 26, 27, 28, 29, 31, 32, 35, 36, 40, 41, 48, 50, 51, 52, 59, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 119, 120, 121, 124, 125, 126, 130, 131, 132, 142, 144, 147, 154], "list_of_d": [5, 75], "list_of_epoch": [19, 85], "lit_model": 32, "lite": 90, "litmodul": 32, "littl": 77, "liu": [44, 63, 95], "ll": 22, "load": [12, 16, 17, 19, 22, 23, 73, 75, 78, 80, 82, 87, 93, 109, 122, 125, 126, 131, 153, 154], "load_concat_dataset": [18, 154], "load_data": [17, 19, 78], "load_eeg_onli": 80, "load_example_data": 14, "load_param": 5, "load_state_dict": 99, "loader": [3, 4, 5, 14, 32], "loc": [2, 8, 12, 26, 27, 28, 29], "local": [2, 5, 10, 11, 14, 27, 31, 32, 73, 124, 148, 152], "locat": [27, 73], "locuslab": 114, "log": [22, 26, 27, 32, 72, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 118, 120, 121, 123, 124, 125, 126, 132, 154], "log10": 3, "log_dict": 32, "log_every_n_step": 32, "log_reg": 5, "logger": 32, "logger_connector": 32, "logic": [8, 9, 10, 11, 28, 30, 32], "logist": 5, "logisticregress": 5, "logit": 89, "logno": 26, "logsoftmax": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 154], "long": [8, 14, 29, 30, 77, 94], "longer": [5, 29, 32, 72, 132], "look": [11, 12, 17, 22, 26, 29, 73, 134], "loop": [5, 9, 10, 11, 14, 72, 132], "lope": 154, "lopez": [47, 66, 142], "loss": [2, 5, 8, 9, 10, 11, 14, 26, 27, 28, 31, 32, 72, 89, 91, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 132, 137, 141, 142], "loss_fn": 32, "loss_funct": [137, 141], "loss_val": 14, "lot": [9, 10, 11, 72, 132], "lott": [48, 67], "low": [2, 3, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 32, 37, 57, 97, 104, 120], "low_cut_hz": [2, 3, 4, 8, 27, 28, 29, 30, 32], "lower": [5, 9, 12, 29, 32, 37, 57, 120, 140], "lower_is_bett": [2, 5, 8, 9, 10, 11, 138, 139, 140], "lowest": 5, "lowpass": [5, 9, 10, 16], "lr": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 72, 132], "lr_schedul": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "lrschedul": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "lt": 4, "lu": 107, "luessi": 35, "luka": [12, 17, 18, 19, 20, 21, 22, 31, 35, 154], "m": [3, 4, 5, 9, 10, 11, 12, 16, 22, 26, 27, 28, 29, 30, 31, 32, 37, 40, 44, 49, 50, 51, 52, 54, 57, 59, 63, 68, 70, 79, 89, 90, 91, 92, 93, 101, 102, 103, 105, 106, 108, 109, 111, 117, 120, 133, 147, 152], "m1": 124, "m2": 124, "m_": [128, 129], "m_t": [128, 129], "machin": [12, 14, 16, 29, 32, 35, 37, 40, 44, 54, 57, 59, 63, 70, 72, 105, 132], "maciej": [2, 8, 154], "maciek": [2, 8], "macro": [5, 9, 10, 11], "made": [16, 27, 98, 154], "mae": [37, 44, 54, 57, 63, 70], "magnitud": [42, 54], "mai": [2, 3, 4, 5, 8, 9, 10, 11, 16, 18, 19, 27, 28, 29, 32, 35, 46, 65, 72, 107, 132, 140, 145, 148], "main": [5, 97, 98], "mainak": 35, "maintain": 77, "make": [2, 3, 4, 5, 8, 9, 11, 12, 27, 28, 29, 30, 32, 112, 120, 148, 154], "make_pipelin": 5, "make_standard_montag": [49, 68], "male": 12, "male_df": 12, "malici": 5, "manag": [8, 9, 10, 11, 28, 30, 31], "mandatori": 4, "mani": [2, 4, 5, 8, 16, 26, 27, 29, 32, 75], "manipul": 17, "manual": [26, 27, 29, 151], "map": [5, 9, 10, 11, 22, 26, 27, 28, 29, 30, 31, 35, 72, 86, 89, 93, 103, 104, 106, 109, 116, 125, 126, 132, 147], "map_loc": 5, "marco": 154, "mark": [5, 9, 10, 11], "marker": [2, 5, 8, 16, 27, 28], "martin": [35, 154], "martin2023": 90, "martincod": 90, "martinez": 97, "martinwimpff": 90, "mask": [2, 5, 46, 54, 65, 70, 107, 112, 141], "mask_len_sampl": [4, 54, 70], "mask_start_per_sampl": [54, 70], "maskencod": 154, "mass": 9, "master": 152, "mastoid": [74, 124], "match": [16, 18, 19, 26, 75, 89], "mathemat": 27, "mathrm": [128, 129], "matplotlib": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31, 147, 154], "matric": [27, 28, 50, 51, 52, 72, 132], "matrix": [5, 9, 10, 11, 39, 40, 49, 59, 60, 68, 95, 104, 147, 154], "matter": [29, 32, 79, 81, 82], "matthieu": 154, "matti": 35, "max": [14, 16, 26, 29, 93, 101, 104, 109, 111, 115, 117, 120, 129], "max_degre": [49, 50, 51, 52], "max_delta_freq": [3, 43], "max_epoch": [5, 29, 32, 72, 132], "max_freq": 37, "max_it": 5, "max_mask_ratio": 46, "max_mem": 16, "max_norm_const": [89, 105], "max_pool_s": 110, "max_pool_size_": 111, "maxim": [9, 10, 30, 37], "maximum": [43, 49, 50, 51, 52, 89, 105, 125], "maxpool": [11, 117], "maxpool1d": [10, 11], "maxpool2d": 9, "mb": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 34, 153], "md": 5, "mean": [2, 3, 4, 8, 10, 12, 14, 16, 19, 26, 27, 29, 30, 31, 32, 77, 93, 102, 107, 109, 123, 124, 128, 129, 132, 148], "mean_test_scor": [4, 30], "mean_train_scor": [4, 30], "meaning": 29, "measur": 16, "mechan": [90, 112, 154], "med": [11, 117, 133], "median": 11, "medicin": [49, 50, 51, 52, 68], "meg": [3, 4, 20, 27, 28, 29, 30, 32, 35, 120, 121, 149], "meg0111": [120, 121], "meg2623": [120, 121], "mehr": [27, 28, 29, 30], "mem": [6, 13, 16, 23, 33, 34, 153], "memor": [29, 32], "memori": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 72, 126, 132], "memory_profil": 16, "memory_usag": 16, "mention": [26, 29], "merg": [5, 9, 10, 11, 154], "messag": [12, 14, 22, 148], "messi": 29, "metadata": [19, 26, 75, 83, 125, 132, 133, 134, 135, 136], "method": [2, 4, 5, 8, 12, 16, 21, 26, 29, 31, 32, 35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 72, 73, 75, 76, 78, 83, 89, 90, 91, 92, 94, 95, 98, 99, 100, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 120, 122, 123, 124, 132, 133, 134, 135, 137, 138, 139, 140, 141, 154], "methodolog": [90, 95, 104], "methodologi": 4, "metric": [2, 5, 9, 10, 11, 27, 28, 32, 147], "mi": [2, 8, 104], "mib": 16, "michael": 35, "micro": 12, "microcontinu": [5, 9, 10, 11], "microvolt": [5, 9, 10], "middl": 116, "mietu": [9, 10, 11], "might": [5, 14, 16, 26, 29, 30, 32, 126, 134], "miller": [2, 8, 27, 28, 29, 30, 73], "min": [5, 12, 29, 80, 120], "ming": 107, "mini": [72, 132], "minibatch": 14, "minim": [31, 47, 48, 66, 67, 92, 142, 148], "minimum": 120, "minimum_phas": 120, "minut": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 80], "mirror": [120, 123], "misc": [2, 4, 8, 83], "misclass": [27, 28], "misclassif": [27, 28], "mismatch": 154, "miss": [26, 89, 90, 95, 98, 101, 102, 103, 104, 105, 106, 108, 110, 117, 154], "mistak": 148, "mix": [16, 18, 47, 48, 66, 142], "mixin": 99, "mixup": [142, 154], "mkdtemp": [12, 18], "ml": [29, 32], "mlp": [90, 107], "mlp_ratio": 107, "mne": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 15, 16, 17, 18, 20, 22, 23, 24, 25, 28, 30, 33, 49, 68, 73, 75, 76, 80, 83, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 130, 132, 148, 153, 154], "mne_data": [16, 17, 19, 27, 73], "mne_datasets_": 73, "mne_datasets_bnci_path": 27, "mne_filter_kwarg": 130, "mnepreproc": 154, "mo": [2, 8], "moabb": [3, 4, 15, 18, 21, 23, 24, 27, 28, 29, 30, 32, 74, 75, 77, 78, 122, 131, 151, 152, 153, 154], "moabbdataset": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32, 154], "mock": [12, 22], "mode": [2, 5, 24, 32, 72, 93, 107, 120, 123, 132, 140, 152, 154], "model": [12, 14, 21, 33, 35, 44, 63, 72, 75, 76, 78, 79, 122, 125, 126, 129, 131, 132, 137, 138, 139, 140, 141, 142, 143, 145, 146, 149, 153, 154], "model_build": [32, 33, 153], "model_evalu": [72, 132], "model_kind": 14, "model_nam": 31, "model_select": [4, 5, 8, 29, 30], "model_train": 14, "model_training_end": 14, "model_training_start": 14, "models_dict": [26, 72, 132, 154], "modelstatist": 99, "modif": [92, 107, 113], "modifi": [3, 5, 10, 12, 42, 62, 72, 90, 99, 118, 119, 121, 122, 130, 132, 145], "modul": [2, 4, 5, 8, 9, 10, 11, 14, 26, 28, 30, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 132, 143, 145, 147, 151, 154], "module_": [3, 4, 9, 10, 11, 26, 72, 132], "module__": 26, "module__drop_prob": 30, "module__final_conv_length": 26, "modulelist": 10, "moham": [2, 8, 154], "mohammad": 154, "mohsenvand": [37, 44, 54, 57, 63, 70], "momentum": [10, 26, 93, 97, 109], "monopolarli": 74, "montag": [50, 51, 52, 74, 81, 82, 154], "month": [12, 35], "moodi": [9, 10, 11], "more": [1, 2, 3, 4, 5, 8, 9, 10, 11, 16, 18, 20, 21, 22, 24, 26, 27, 28, 29, 30, 46, 65, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 119, 120, 121, 123, 124, 131, 132, 145, 152, 154], "moreau": [4, 154], "morlet": 113, "most": [3, 9, 10, 11, 14, 135, 148, 151], "mostli": 27, "motor": [2, 4, 8, 27, 28, 74, 77, 89, 90, 96, 98, 104, 105, 154], "moustapha": [47, 66, 142], "move": [2, 3, 4, 8, 14, 16, 27, 28, 29, 30, 32, 73, 99, 128, 129, 154], "movement": [74, 77], "mrcnn": 112, "mse": 31, "mse_loss": [2, 31], "mseloss": [8, 132], "msg": [2, 31], "much": [5, 27, 72, 90, 123, 132], "mueller": [27, 28, 29, 30], "muhammad": 89, "mult": [3, 4, 11, 26, 27, 28, 29, 32], "multi": [90, 112], "multi_class": 5, "multiclass": 32, "multiindex": 134, "multimedia": [44, 63], "multimod": [5, 9, 10, 111], "multinomi": 5, "multipl": [2, 3, 4, 8, 9, 10, 14, 15, 16, 21, 23, 24, 27, 29, 30, 72, 75, 81, 90, 98, 116, 117, 120, 124, 125, 130, 132, 143, 153, 154], "multipli": [3, 4, 5, 9, 10, 12, 27, 28, 29, 30, 32, 89, 97, 100, 105], "multitap": 3, "multivari": [5, 9, 10, 111], "murad": 154, "muscular": 77, "music": 113, "must": [3, 4, 12, 14, 16, 18, 20, 21, 26, 29, 30, 83, 93, 109, 110, 116, 118, 122, 124, 125, 133, 151, 154], "mypi": 154, "m\u00fcller": [27, 28, 29, 30], "n": [14, 16, 22, 26, 27, 28, 29, 30, 32, 34, 37, 38, 39, 44, 47, 54, 57, 58, 60, 63, 66, 70, 89, 91, 101, 102, 104, 105, 111, 142], "n1": [5, 9, 10, 11], "n2": [5, 9, 10, 11], "n3": [5, 9, 10, 11], "n4": 10, "n_attn_head": 112, "n_batch": [32, 137, 141], "n_block": 114, "n_chan": [2, 8, 11, 26, 27, 28, 30, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132], "n_channel": [3, 4, 5, 9, 10, 14, 17, 19, 22, 29, 31, 32, 47, 49, 66, 68, 84, 89, 91, 92, 94, 95, 104, 106, 108, 110, 111, 112, 114, 115, 116, 128, 129], "n_class": [2, 3, 4, 9, 10, 11, 14, 26, 27, 28, 29, 30, 31, 32, 72, 89, 93, 94, 95, 96, 97, 98, 101, 102, 103, 106, 109, 110, 111, 112, 115, 117, 132, 137, 141, 143], "n_codeword": 90, "n_compon": 5, "n_conv": [98, 104], "n_conv_ch": [5, 111], "n_conv_chan": 110, "n_epoch": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32], "n_exampl": [5, 135], "n_examples_test": 5, "n_examples_train": 5, "n_examples_valid": 5, "n_fake_ch": 31, "n_fake_chan": 31, "n_fake_rec": 31, "n_fake_target": 31, "n_filter": [97, 98, 114], "n_filters_2": [14, 31, 93], "n_filters_3": [14, 31, 93], "n_filters_4": [14, 31, 93], "n_filters_spat": [14, 26, 31, 93, 109], "n_filters_tim": [14, 26, 31, 93, 95, 109], "n_first_filt": 103, "n_freq": 92, "n_group": 110, "n_in_chan": 114, "n_iter_i": 5, "n_job": [2, 3, 4, 5, 12, 14, 16, 27, 28, 29, 30, 32, 79, 81, 82, 87, 120, 123, 125, 126, 127, 131, 154], "n_layer": [91, 107], "n_layers_per_block": 103, "n_out_chan": 8, "n_output": [5, 9, 10, 11, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132], "n_patch": 107, "n_predict": [72, 132, 137, 141, 143], "n_preds_per_input": [2, 27, 31], "n_rec": 16, "n_record": [14, 134], "n_repet": 16, "n_repetit": 14, "n_segment": [46, 48, 65, 67], "n_sequenc": [133, 136], "n_split": [4, 29, 30], "n_target": [72, 132, 143], "n_tce": 112, "n_temporal_filt": 90, "n_test": 29, "n_time": [3, 4, 5, 8, 9, 10, 11, 12, 14, 17, 19, 26, 27, 28, 29, 30, 31, 32, 47, 66, 84, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 128, 129, 132, 137, 141], "n_time_filt": 117, "n_timestep": [95, 104], "n_train": 29, "n_train2": 29, "n_trial": [72, 84, 132, 143], "n_val": 29, "n_window": [9, 10, 11, 22, 89, 133, 136], "n_windows_strid": [9, 10, 11, 136], "nado": 30, "name": [0, 2, 3, 4, 5, 8, 9, 10, 11, 16, 17, 18, 20, 21, 22, 26, 29, 30, 32, 40, 72, 74, 75, 76, 78, 84, 87, 119, 120, 121, 122, 124, 132, 138, 139, 140, 154], "nan": [26, 141], "narayanan": [10, 154], "nativ": 11, "natur": [2, 8, 14, 73], "nbsp": 4, "nbviewer": 4, "ncol": 29, "ndarrai": [22, 49, 68, 72, 84, 123, 128, 129, 132, 136, 143, 144], "ndataset": 29, "necessari": [4, 72, 124, 132], "need": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 26, 27, 28, 29, 32, 72, 89, 90, 95, 98, 132, 145, 150, 154], "neg": [5, 27, 31, 72, 135], "neg_root_mean_squared_error": 31, "neighbour": 27, "neighbourhood": 27, "nemati": [42, 62], "net": [5, 8, 26, 72, 112, 113, 117, 132, 138, 139, 140], "network": [2, 4, 5, 7, 8, 10, 13, 14, 25, 26, 27, 28, 29, 32, 33, 35, 44, 63, 72, 75, 76, 80, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 101, 102, 103, 104, 105, 106, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 122, 125, 126, 131, 132, 134, 136, 137, 143, 145, 147, 153, 154], "neural": [2, 4, 5, 8, 9, 10, 11, 14, 25, 26, 27, 28, 29, 33, 35, 44, 46, 63, 75, 76, 90, 91, 92, 93, 94, 95, 97, 98, 99, 103, 104, 106, 107, 108, 109, 110, 111, 112, 113, 115, 125, 137, 145, 147, 153, 154], "neural_token": 107, "neuralnet": [72, 132], "neuralnetclassifi": [9, 10, 11, 28, 30], "neuralnetregressor": 8, "neurip": [91, 97], "neurologi": 108, "neuron": [5, 9, 10, 11], "neurophysiolog": 149, "neurosci": [27, 28, 29, 30, 35, 79], "neuroscientist": 149, "never": [29, 32], "new": [5, 9, 10, 11, 20, 40, 48, 59, 67, 72, 107, 118, 124, 132, 148, 152], "next": [3, 4, 5, 9, 10, 11, 12, 14, 16, 18, 22], "nice": 32, "night": [9, 10, 11], "nikol": [11, 117, 133], "nllloss": 72, "nmt": 154, "nn": [2, 3, 4, 5, 8, 9, 10, 11, 14, 26, 27, 28, 29, 30, 31, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 132, 143], "nnloss": 32, "no_grad": [5, 32], "nois": [31, 44, 63, 74], "noisi": [42, 62], "nolt": [27, 28, 29, 30], "nomenclatur": 40, "non": [3, 4, 11, 16, 22, 26, 27, 28, 29, 30, 32, 72, 77, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 120, 132, 154], "none": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 18, 19, 20, 22, 26, 27, 28, 29, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 62, 63, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 121, 123, 124, 125, 126, 127, 128, 129, 131, 132, 133, 134, 135, 136, 138, 139, 140, 145, 147, 154], "nonlinear": [5, 29, 72, 89, 132], "noqa": [12, 22], "norm": [10, 89, 105], "norm_ax": 147, "norm_lay": 107, "normal": [2, 5, 8, 9, 10, 28, 30, 107, 108, 110, 111, 113, 134, 147, 154], "normalis": [26, 93, 104, 109], "notabl": [72, 132], "notat": [72, 132], "notch": 74, "notch_filt": 120, "note": [2, 3, 4, 5, 8, 9, 11, 17, 20, 26, 27, 28, 43, 61, 72, 73, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 121, 124, 132, 140, 145], "notebook": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "novel": [26, 46, 97], "novemb": 91, "now": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 22, 26, 27, 28, 30, 124, 152, 154], "np": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 26, 29, 31, 32, 72, 128, 129, 132, 133, 134, 135, 136, 143], "npad": 123, "npj": [11, 117, 133], "nrepetit": 14, "nsplit": 29, "num_class": 32, "num_filt": 113, "num_head": 107, "num_param": 99, "num_work": [5, 14, 32, 143], "number": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 22, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 65, 67, 68, 70, 72, 75, 80, 81, 82, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 123, 125, 126, 130, 131, 132, 133, 134, 135, 136, 143, 144], "numer": 126, "numpi": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 17, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 68, 72, 120, 123, 132, 145, 147], "numpypreproc": 154, "nvidia": 151, "nyquist": 37, "o": [2, 4, 5, 8, 16, 27, 28, 37, 38, 39, 40, 44, 54, 57, 58, 59, 60, 63, 70, 90, 135], "o1": [12, 130], "o1_4": 130, "o1_8": 130, "o2": 12, "obery": 5, "obery\u00e9": [9, 10, 11], "object": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 18, 19, 21, 27, 28, 29, 30, 31, 32, 41, 76, 79, 80, 81, 82, 83, 86, 118, 122, 125, 126, 131, 147, 154], "obtain": [2, 3, 4, 5, 8, 9, 11, 27, 28, 49, 68, 72, 76, 77, 83, 104, 132, 134], "odd": [11, 98, 117], "off": [26, 29, 30, 120], "offici": [89, 151], "offset": [3, 4, 27, 28, 29, 30, 32, 75, 86, 125, 126, 131, 154], "often": [4, 9, 10, 11, 28, 30], "old": [75, 131, 154], "omar": [11, 154], "omega": 113, "omega_init_valu": 113, "omit": [9, 37], "on_batch_end": 139, "on_epoch_end": [138, 139, 140], "on_miss": [119, 125, 126], "on_train": [2, 5, 8, 9, 10, 11, 138, 139], "onc": [5, 16, 29, 120, 125, 135, 152], "one": [2, 4, 8, 9, 10, 11, 14, 16, 20, 26, 27, 29, 30, 32, 41, 46, 47, 54, 65, 70, 72, 74, 75, 89, 90, 95, 98, 99, 117, 124, 125, 126, 131, 132, 133, 134, 135, 148], "ones": [12, 26, 133, 154], "onli": [2, 4, 5, 8, 9, 10, 11, 12, 14, 18, 19, 21, 26, 27, 29, 30, 32, 41, 56, 72, 77, 80, 86, 91, 96, 97, 98, 100, 101, 102, 107, 118, 120, 121, 123, 124, 125, 126, 132, 141, 148, 152, 154], "onlin": [47, 66, 93, 97, 103, 106, 109, 142, 147], "onset": [86, 126], "open": [5, 16, 18, 79, 148, 149, 151], "openli": [4, 5, 9, 10, 11], "oper": [2, 3, 4, 8, 16, 37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 64, 90, 118, 123], "optim": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 72, 77, 132, 154], "optimizer__lr": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 72, 132], "optimizer__momentum": [72, 132], "optimizer__weight_decai": [2, 3, 4, 8, 27, 28, 29, 31], "optimizer_lr": 31, "optimizer_weight_decai": 31, "option": [5, 10, 18, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 72, 75, 78, 86, 89, 90, 91, 92, 97, 98, 99, 100, 104, 105, 107, 108, 113, 120, 123, 126, 132, 143, 147, 152, 154], "orang": [5, 12, 16], "order": [3, 4, 12, 21, 26, 40, 48, 50, 51, 52, 59, 72, 77, 79, 81, 82, 90, 120, 124, 130, 132, 136, 154], "order_by_frequency_band": 130, "ordered_ch_nam": [40, 50, 51, 52], "org": [2, 4, 5, 8, 26, 27, 28, 29, 30, 35, 47, 66, 72, 73, 80, 89, 93, 95, 96, 97, 98, 99, 101, 103, 104, 105, 106, 109, 110, 112, 114, 115, 117, 132, 142, 145, 147], "orient": 12, "origin": [3, 11, 17, 19, 26, 29, 47, 48, 49, 50, 51, 52, 54, 66, 68, 70, 75, 86, 90, 92, 95, 96, 97, 98, 100, 101, 102, 104, 107, 108, 113, 120, 126, 130, 131], "oscil": 113, "oscillatori": [48, 67], "oskar": 154, "other": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 18, 26, 29, 30, 32, 56, 72, 77, 80, 89, 90, 91, 93, 94, 99, 103, 105, 106, 107, 109, 110, 111, 112, 114, 117, 132], "otherwis": [2, 14, 27, 29, 31, 86, 126], "ou": 4, "ouahidi": [104, 154], "our": [2, 5, 8, 9, 10, 11, 12, 16, 20, 26, 27, 28, 30, 32, 77, 150], "out": [4, 8, 9, 10, 26, 37, 46, 54, 57, 65, 70, 72, 74, 90, 91, 113, 132, 133, 141, 148], "out_channel": 107, "out_featur": [9, 10], "out_path": 12, "outcom": [72, 132], "outlier": 12, "output": [2, 3, 4, 5, 11, 12, 14, 21, 26, 27, 28, 29, 30, 31, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 121, 123, 124, 125, 126, 132], "output_s": [10, 99, 116], "output_shap": 99, "outsid": [86, 126], "over": [4, 10, 16, 29, 31, 32, 42, 49, 50, 51, 52, 62, 68, 72, 132, 154], "overal": 14, "overfit": [2, 8, 9, 10, 11, 29, 90], "overhead": [14, 126], "overlaid": [9, 10, 11], "overlap": [9, 10, 11, 46, 65, 84, 85, 86, 120, 125, 126], "overnight": 80, "overrid": [72, 73, 132], "overridden": [89, 90, 95, 98], "overwrit": [16, 18, 72, 75, 76, 79, 81, 82, 83, 88, 131, 132], "own": [2, 8, 27, 28, 29, 30, 32, 77, 148], "oz": 10, "p": [5, 9, 10, 27, 28, 29, 30, 31, 37, 44, 54, 57, 63, 70, 79, 100, 101, 102, 111], "p2": 89, "p3": 12, "p4": 12, "p_drop": [4, 38, 58], "p_shuffl": [39, 60], "pa": 89, "pace": 77, "packag": [2, 5, 10, 11, 27, 31, 32, 35, 150, 151], "pad": [2, 9, 10, 11, 27, 100, 111, 120, 123, 154], "pad_and_select_predict": 2, "pad_size_": 111, "padding_height": 100, "padding_width": 100, "page": [4, 29, 32, 35, 148, 154], "paillard": 4, "pair": [5, 135], "pan": 100, "panda": [2, 4, 5, 8, 9, 10, 11, 14, 16, 20, 21, 27, 28, 29, 30, 31, 72, 75, 76, 83, 86, 132], "paper": [4, 11, 35, 49, 50, 51, 52, 68, 89, 90, 95, 96, 97, 98, 100, 101, 102, 104, 112, 154], "paperswithcod": [74, 77], "paradigm": [4, 5, 72, 74, 104, 132, 143], "parallel": [12, 14, 15, 23, 24, 75, 80, 81, 82, 87, 97, 98, 120, 122, 123, 125, 126, 131, 153, 154], "param": [3, 4, 5, 11, 26, 27, 28, 29, 30, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54], "param_grid": [4, 29, 30], "param_iterator_train__transform": 4, "param_module__drop_prob": 30, "param_optimizer__lr": 30, "paramet": [2, 3, 4, 5, 8, 10, 14, 16, 17, 18, 19, 26, 28, 29, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 140, 141, 142, 143, 144, 145, 147, 154], "parameter": 113, "parent": [79, 81, 82], "parkkonen": 35, "pars": 12, "part": [2, 8, 16, 17, 19, 28, 29, 32, 38, 39, 46, 54, 58, 60, 65, 70, 95, 97], "partial": 30, "particip": 79, "particular": 26, "pasdeloup": 104, "pass": [3, 4, 9, 10, 11, 16, 22, 26, 27, 28, 29, 32, 36, 41, 56, 72, 78, 89, 90, 91, 92, 94, 95, 98, 100, 104, 105, 106, 108, 110, 111, 112, 113, 114, 115, 118, 120, 121, 123, 124, 132, 137, 140, 141, 154], "passband": 16, "past": 148, "patch": [29, 107], "patch_siz": 107, "patchemb": 107, "patchembed": 95, "patchfrequencyembed": 91, "path": [12, 14, 17, 18, 19, 22, 32, 73, 75, 79, 81, 82, 87, 88], "pathlib": 87, "patholog": [14, 18, 79, 82], "pathologi": 30, "patienc": 5, "patient": [12, 73], "pattern": 108, "paz": [47, 66, 142], "pazo": 110, "pc": 89, "pca": 5, "pch": [9, 10, 11], "pd": [2, 4, 5, 8, 9, 10, 11, 14, 16, 27, 28, 29, 30, 31, 75, 76, 83, 133, 134, 135, 136], "pdf": 73, "peak": [16, 125, 126], "pearson": 8, "pearson_r_scor": 8, "penalti": 5, "peng": [9, 10, 11, 44, 63, 107], "peopl": 115, "per": [2, 4, 5, 8, 9, 10, 11, 27, 46, 47, 54, 65, 70, 74, 77, 80, 98, 104, 108, 115, 124, 154], "percent": [27, 28], "percentag": 115, "percept": 32, "perceptron": 90, "perez": 96, "perform": [2, 4, 8, 9, 10, 11, 26, 27, 28, 29, 30, 32, 74, 75, 77, 89, 90, 95, 98, 104, 112, 128, 129, 154], "period": [31, 108], "permut": [39, 40, 47, 59, 60, 66], "persist": 148, "perslev": [11, 117, 133], "perslev2021": 133, "perturb": [42, 62], "phase": [16, 42, 62, 107, 113, 120, 123], "phase_freq": 4, "phase_init_valu": 113, "phase_noise_magnitud": [4, 42, 62], "phenomenon": 4, "phi_c": 113, "physic": 89, "physician": [81, 82], "physiobank": [5, 9, 10, 11], "physiolog": [5, 9, 10, 11], "physionet": [5, 7, 13, 16, 24, 75, 80, 99, 111, 112, 116, 117, 122, 126, 131, 134, 136, 145, 147, 153, 154], "physionet_path": [17, 19], "physiotoolkit": [5, 9, 10, 11], "pi": [31, 42, 62], "pick": [2, 8, 10, 12, 19, 20, 120, 125, 126, 127, 154], "pick_channel": [12, 119, 122], "pick_typ": [2, 3, 4, 8, 20, 27, 28, 29, 30, 32, 119], "pickl": 5, "pickleabl": [72, 132], "piconepress": [12, 14, 81, 82], "pierr": [26, 154], "pietquin": [38, 39, 58, 60], "pin": 14, "pin_memori": 14, "pip": [32, 150, 151, 152, 154], "pipelin": [2, 5, 8, 29, 32], "pivot": 30, "pivot_t": 30, "pj": [11, 117, 133], "place": [20, 31, 99, 118, 130], "playbook": 30, "pleas": [2, 4, 5, 8, 11, 12, 22, 26, 27, 32, 73, 89, 93, 95, 96, 97, 98, 99, 101, 103, 104, 106, 109, 110, 114, 115, 117, 130, 152, 154], "plot": [3, 5, 12, 14, 16, 29, 31, 154], "plot_basic_training_epoch": [26, 33, 153], "plot_bcic_iv_2a_moabb_crop": [27, 33, 153], "plot_bcic_iv_2a_moabb_tri": [28, 33, 153], "plot_bcic_iv_4_ecog_crop": [2, 6, 153], "plot_bcic_iv_4_ecog_tri": [8, 13, 153], "plot_benchmark_preprocess": [16, 23, 153], "plot_confusion_matrix": [9, 10, 11, 27, 28, 154], "plot_custom_dataset_exampl": [17, 23, 153], "plot_data_augment": [3, 6, 153], "plot_data_augmentation_search": [4, 6, 153], "plot_how_train_test_and_tun": [29, 33, 153], "plot_hyperparameter_tuning_with_scikit": [30, 33, 153], "plot_k_fold": 29, "plot_load_save_dataset": [18, 23, 153], "plot_mne_dataset_exampl": [19, 23, 153], "plot_moabb_dataset_exampl": [20, 23, 153], "plot_psd": 3, "plot_regress": [31, 33, 153], "plot_relative_posit": [5, 6, 153], "plot_simple_train_test": 29, "plot_sleep_staging_chambon2018": [9, 13, 153], "plot_sleep_staging_eldele2021": [10, 13, 153], "plot_sleep_staging_usleep": [11, 13, 153], "plot_split_dataset": [21, 23, 153], "plot_train_in_pure_pytorch_and_pytorch_lightn": [32, 33, 153], "plot_train_valid_test": 29, "plot_tuh_discrete_multitarget": [22, 23, 153], "plot_tuh_eeg_corpu": [12, 13, 153], "plt": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31], "plt_histogram": 12, "pmlr": [37, 44, 54, 57, 63, 70], "point": [19, 20, 26, 74, 124, 128, 129], "polici": [38, 39, 58, 60], "poly1d": 31, "polyfit": 31, "polyphas": 123, "pool": [3, 4, 26, 27, 28, 29, 32, 89, 90, 93, 95, 97, 99, 100, 104, 107, 109, 111, 113, 115, 117], "pool_length": 90, "pool_length_inp": 90, "pool_mod": [26, 101, 102, 109], "pool_nonlin_exp": [3, 4, 26, 27, 28, 29, 32], "pool_siz": 113, "pool_strid": 90, "pool_stride_inp": 90, "pool_time_length": [14, 26, 93, 95, 109], "pool_time_strid": [14, 26, 93, 95, 109], "pooling_s": 97, "popul": [72, 132, 154], "popular": 26, "portion": 148, "posit": [1, 6, 24, 27, 37, 46, 49, 50, 51, 52, 54, 57, 65, 68, 70, 75, 80, 99, 107, 111, 122, 126, 131, 134, 135, 144, 145, 153], "positionwisefeedforward": 112, "possibl": [3, 4, 5, 11, 12, 16, 18, 26, 72, 74, 125, 132, 145, 148, 154], "potenti": [14, 16, 32, 151], "power": [3, 5, 30, 120, 123], "pp": [10, 37, 44, 49, 50, 51, 52, 54, 57, 63, 68, 70, 95, 112], "pre": [26, 84, 91, 107, 124, 154], "preced": 8, "precis": [5, 9, 10, 11, 147], "pred": [2, 8, 32, 137, 141, 142, 144], "predefin": [2, 8, 28, 30], "predefined_split": [2, 3, 5, 8, 9, 10, 11, 27, 28, 29, 31], "predict": [2, 4, 5, 8, 9, 10, 11, 27, 28, 31, 72, 76, 79, 99, 104, 116, 132, 137, 138, 139, 140, 141, 142, 143, 144, 154], "predict_nonlinear": [72, 132], "predict_proba": [72, 132, 154], "predict_tri": [2, 72, 132, 154], "preds_per_tri": 144, "preds_test": [2, 8], "preds_train": [2, 8], "preds_valid": [2, 8], "prefer": [72, 132], "prefix": [26, 72, 132], "prefixes_": [72, 132], "preload": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 22, 27, 28, 29, 30, 31, 32, 79, 80, 81, 82, 86, 87, 124, 125, 126, 127, 131, 154], "prepar": [14, 16, 20, 32], "prepare_data": 16, "prepocess": [2, 8, 28, 30], "preprint": [5, 31, 37, 38, 39, 40, 42, 44, 54, 57, 58, 59, 60, 62, 63, 70, 90, 101, 102, 104, 105, 114, 135], "preprocess": [14, 15, 18, 19, 20, 21, 22, 23, 24, 26, 31, 75, 80, 149, 153, 154], "preprocessor": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 18, 20, 27, 28, 29, 30, 32, 131, 154], "presampl": [5, 135], "present": [4, 29, 32, 74, 77, 91, 119], "preserv": [48, 67, 79, 81, 82], "pretext": 4, "pretti": [14, 148], "prevent": 90, "previou": [32, 154], "previous": [29, 32], "print": [2, 4, 5, 8, 9, 10, 11, 14, 17, 20, 21, 22, 26, 27, 28, 29, 30, 32, 72, 132, 148], "print_batch_stat": 32, "print_log": [72, 132], "prior": [5, 99], "prob": 4, "proba_drop": 38, "probabl": [3, 4, 26, 30, 32, 37, 38, 39, 40, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 72, 89, 90, 91, 93, 96, 109, 114, 115, 132], "problem": [5, 26, 42, 62, 148, 151], "proc": 16, "proceed": [48, 67], "process": [2, 4, 5, 7, 8, 13, 14, 15, 16, 22, 24, 29, 30, 48, 67, 75, 81, 90, 91, 100, 113, 122, 125, 131, 153, 154], "process_pipelin": 78, "processor": [29, 30], "produc": [27, 29, 32, 112], "product": [14, 16], "progress_bar": 32, "project": [5, 12, 14, 19, 26, 81, 82, 124], "projector": 124, "prompt": [74, 148], "propag": 154, "proper": [2, 8], "properli": [29, 120, 123, 124], "properti": [5, 75, 154], "proport": [86, 97, 126], "propos": [4, 38, 39, 42, 48, 54, 58, 60, 62, 70, 91, 98, 154], "protonmail": [3, 20], "provid": [2, 8, 9, 10, 11, 26, 28, 30, 32, 35, 72, 74, 75, 76, 79, 81, 82, 91, 116, 120, 121, 122, 131, 132, 148], "provind": 4, "proxim": 77, "psd": 3, "psd_array_multitap": 3, "psds_mean": 3, "pseudo": 77, "psg": 16, "pt": [5, 89], "publish": 26, "pure": [2, 5, 8, 28, 30, 154], "purpos": [3, 14, 16, 32], "push": [27, 72, 132], "putz": [27, 28, 29, 30], "py": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 153, 154], "pypi": 150, "pyplot": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31], "pyproject": 154, "python": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 35, 118, 145, 149, 150, 152, 154], "python3": [2, 5, 10, 11, 27, 31, 32], "pythonhashse": 145, "pytorch": [2, 5, 8, 14, 22, 24, 25, 26, 27, 28, 30, 33, 72, 75, 78, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 108, 109, 110, 111, 112, 114, 115, 117, 122, 126, 129, 131, 132, 143, 145, 151, 153, 154], "pz": [10, 12], "q": 95, "qixiang": 107, "qk_norm": 107, "qk_scale": 107, "qkv_bia": 107, "quadrat": [49, 50, 51, 52, 68], "quantiti": 5, "quantiz": [90, 107], "queri": 107, "quick": [5, 134], "quickli": 29, "quit": [26, 29], "r": [3, 5, 9, 10, 11, 26, 27, 28, 29, 30, 31, 37, 44, 54, 57, 63, 70, 79, 93, 97, 101, 102, 103, 106, 109, 112, 147], "r2": [2, 8], "r2_score": 2, "r2_train": 2, "r2_valid": 2, "r37c4761d4e92": 97, "r382d436f3223": 74, "r5661533ddc63": 104, "r5e478952091a": 77, "raa3392861949": 46, "rais": [4, 14, 26, 29, 30, 31, 72, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 119, 126, 131, 154], "rand_indic": [48, 67], "randint": [26, 31], "randn": 26, "random": [2, 3, 4, 5, 8, 9, 10, 11, 26, 27, 28, 30, 31, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 77, 133, 134, 135, 136, 140, 145, 154], "random_st": [4, 5, 8, 30, 37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 133, 134, 135, 136], "randomli": [3, 5, 27, 37, 38, 39, 44, 46, 48, 54, 58, 60, 63, 136], "randomst": [133, 134, 135, 136], "rang": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 26, 27, 28, 29, 31, 32, 42, 62, 73, 104, 113, 130, 147], "rank_test_scor": [4, 29, 30], "rate": [2, 5, 14, 27, 28, 29, 30, 31, 32, 72, 90, 95, 97, 100, 107, 108, 110, 111, 112, 117, 132, 154], "rather": [9, 10], "ratio": [29, 46, 107], "ravel": 31, "raw": [2, 3, 4, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 27, 28, 29, 30, 31, 75, 76, 79, 80, 81, 82, 86, 94, 118, 119, 120, 121, 122, 124, 125, 126, 130, 149, 154], "raw_or_epoch": 122, "raw_preproc_kwarg": 75, "rawarrai": [17, 19, 31, 86], "rbf": [49, 50, 51, 52, 68], "re": [12, 21, 72, 124, 132, 148], "re49696d5b28b": 65, "reach": [5, 9, 10, 32], "read": [12, 14, 16, 17, 18, 19, 79, 81, 82, 87, 126], "read_raw_edf": [17, 19], "readabl": [29, 32, 120], "readi": [12, 16, 17, 18, 19, 31], "readthedoc": 27, "real": 32, "realiz": 154, "realli": 29, "rearrang": [3, 4, 26, 27, 28, 29, 32, 154], "reason": [5, 10, 29, 32, 72, 132, 140], "rec_ind": [133, 134], "recal": [5, 9, 10, 11], "recalibr": [90, 112], "receiv": [5, 95], "recent": [4, 26, 148], "recept": [2, 27, 72, 132, 143], "recip": [89, 90, 95, 98], "reciproc": 120, "recod": 12, "recoding_id": 154, "recogn": [29, 32], "recognit": [44, 63, 113], "recombin": 95, "recommend": [5, 9, 11, 16, 29, 30, 35, 95, 104, 151, 152], "recomput": 140, "reconstruct": [48, 67, 120], "record": [2, 4, 8, 9, 10, 11, 14, 16, 21, 22, 26, 31, 73, 74, 77, 79, 80, 81, 82, 86, 90, 92, 93, 94, 95, 96, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 124, 125, 126, 133, 134, 135, 154], "recording_id": [5, 9, 10, 11, 12, 14, 16, 22, 79, 80, 81, 82], "recordingsampl": [133, 135, 136], "recurr": 114, "red": [2, 8, 27, 28], "reddi": 31, "reduc": [5, 10, 14, 16, 80, 90, 126], "reduct": 90, "reduction_r": 90, "redund": 27, "ref_channel": [12, 124], "refactor": 154, "refer": [12, 35, 37, 38, 39, 40, 42, 44, 46, 47, 48, 49, 50, 51, 52, 54, 57, 58, 59, 60, 62, 63, 66, 67, 68, 70, 73, 74, 79, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 124, 130, 133, 135, 142, 147], "referenc": 124, "refit": [4, 29, 30], "reflect": [120, 123], "reflect_limit": [120, 123], "regard": [12, 104], "regardless": [72, 132], "regim": 5, "region": [12, 120], "regist": [89, 90, 95, 98], "regress": [2, 5, 8, 24, 25, 30, 33, 75, 76, 93, 99, 109, 125, 132, 137, 145, 153, 154], "regressor": [2, 8, 26, 31, 154], "regular": [5, 90, 128, 129], "rehabilit": [5, 9, 10, 46, 94, 95, 97, 111, 112], "reimplement": [96, 97, 98, 100, 101, 102], "reiniti": [29, 32], "reject": [10, 19, 125, 126, 127], "rel": [1, 6, 24, 29, 30, 75, 80, 99, 111, 122, 126, 131, 134, 135, 145, 153], "relat": [4, 5, 26, 27, 35, 77, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132, 154], "relativepositioningdataset": 5, "relativepositioningsampl": 5, "relax": 77, "releas": [5, 148, 152], "relev": [5, 29, 35, 72, 132], "reliabl": [29, 32, 100], "reload": [12, 16, 131], "relu": [9, 10, 90, 91, 92, 94, 96, 98, 101, 103, 104, 107, 108, 110, 111, 112, 113, 114, 115, 117], "rem": [9, 10, 11], "remain": [16, 29, 32], "rememb": [4, 29, 32], "remi": 154, "remov": [2, 3, 4, 5, 8, 9, 11, 18, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 119, 124, 144, 154], "renam": [3, 4, 18, 20, 21, 29, 30, 81, 82, 154], "rename_channel": [12, 81, 82], "render": 4, "reorder": [38, 39, 58, 60], "reorder_channel": 119, "repeat": [14, 148], "repetit": [14, 16, 77], "replac": [29, 46, 54, 65, 70, 154], "replic": 148, "repo": 152, "report": [5, 9, 10, 11, 14, 29, 32, 81, 82, 89, 148], "report_messag": 4, "repositori": [104, 150], "repres": [21, 50, 51, 52, 95, 104], "represent": [4, 37, 44, 47, 54, 57, 63, 66, 70, 91, 92, 107, 154], "reproduc": [2, 3, 4, 5, 8, 9, 10, 11, 24, 27, 28, 30, 145, 154], "request": [27, 120, 124, 148], "requir": [5, 11, 12, 14, 16, 17, 22, 56, 72, 77, 83, 132, 154], "rerun": 4, "res_channel": 92, "resampl": [5, 12, 14, 18, 20, 80, 120, 154], "resample_poli": 123, "resampling_freq": 104, "rescal": [29, 30], "research": [5, 9, 10, 11, 30, 35, 149], "reset": 107, "reset_classifi": 107, "residu": [89, 92, 103, 105, 107], "resili": [11, 117, 133], "resolut": 112, "resolv": [72, 132], "resourc": [5, 7, 9, 10, 11, 13, 16, 24, 75, 81, 122, 125, 131, 153, 154], "resp": 56, "respect": [4, 5, 30, 123], "respir": 80, "respons": [8, 9, 10, 11, 28, 30], "rest": [77, 124], "restor": [32, 72], "result": [3, 12, 14, 16, 29, 32, 72, 86, 123, 126, 132, 140, 145, 148], "results_column": [2, 8, 27, 28], "results_df": 14, "retain": 120, "return": [2, 5, 8, 9, 10, 11, 12, 14, 17, 19, 21, 29, 30, 31, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 69, 70, 71, 72, 75, 76, 79, 81, 82, 83, 84, 85, 86, 87, 91, 92, 94, 95, 99, 100, 104, 105, 107, 108, 110, 111, 112, 113, 116, 117, 118, 119, 120, 121, 123, 124, 125, 126, 128, 129, 130, 131, 132, 133, 134, 140, 142, 143, 144, 147, 154], "return_all_token": 107, "return_feat": [9, 10, 94, 110, 111, 112], "return_featur": [91, 95, 104], "return_pair": 5, "return_patch_token": 107, "return_target": [2, 72, 132, 143], "return_train_scor": [4, 29, 30], "reus": [5, 9, 11], "review": [27, 28, 29, 30], "rg": [9, 10, 11], "rhythmic": 108, "right": [2, 4, 8, 12, 27, 28, 29, 32, 40, 74, 77, 152], "right_hand": [18, 21, 27, 28, 29, 30, 32], "rightward": 77, "rippl": 16, "risk": [29, 47, 66, 142], "rivero": 110, "rmse": 31, "robin": [35, 154], "robust": 98, "robust_scal": 11, "rodrigu": 154, "roman": 35, "rommel": [3, 4, 154], "room": [27, 28], "root": [31, 48, 152], "rot": 4, "rotat": [29, 49, 50, 51, 52, 68, 147], "rotate_col_label": 147, "rotate_precis": 147, "rotate_row_label": 147, "rough": 29, "roughli": [2, 3, 4, 5, 8, 9, 11, 27, 28, 77], "round": [2, 8], "row": [14, 22, 40, 75, 99, 147], "row_set": 99, "rp": 5, "rudzicz": 115, "rule": [27, 72, 132], "run": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 72, 74, 77, 86, 89, 90, 95, 98, 110, 120, 122, 123, 126, 132, 134, 145, 148, 152, 154], "run_0": 134, "run_train": 14, "runner": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 27, 28, 29, 30, 31, 32], "runtim": 27, "runtimewarn": 27, "s0": 22, "s001": 22, "s004": 22, "s00500": 110, "s022": [17, 19], "s022r05": [17, 19], "s022r06": [17, 19], "s022r09": [17, 19], "s022r10": [17, 19], "s022r13": [17, 19], "s022r14": [17, 19], "s41562": [2, 8, 73], "s_growth": 115, "saeed": [38, 39, 58, 60], "safelog": [3, 4, 26, 27, 28, 29, 32, 109], "sake": 14, "salami": 96, "salami2022": 96, "salvocalcagno": 113, "same": [2, 3, 4, 5, 8, 9, 10, 11, 14, 18, 21, 27, 28, 29, 30, 32, 43, 54, 61, 70, 72, 77, 80, 100, 112, 120, 123, 132, 135], "same_rec_neg": [5, 135], "sampl": [2, 3, 4, 5, 8, 9, 10, 14, 16, 17, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 42, 43, 47, 48, 49, 50, 51, 52, 54, 57, 60, 61, 62, 70, 72, 74, 76, 84, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 125, 126, 133, 134, 135, 136, 142, 148, 154], "sample_class": 133, "sample_record": 134, "sample_window": 134, "sampler": 154, "sanjiv": 31, "santamaria": 97, "santamaria2020": 97, "sara": [31, 154], "sashank": 31, "satyen": 31, "save": [2, 3, 4, 5, 8, 9, 10, 12, 14, 15, 16, 23, 24, 27, 28, 29, 30, 32, 72, 75, 78, 87, 122, 126, 131, 132, 153, 154], "save_dir": [12, 16, 131], "savgol_filt": 120, "sc4001e0": 16, "sc4011e0": 16, "scalar": 140, "scale": [5, 9, 10, 11, 12, 16, 95, 97, 98, 107, 154], "scales_samples_": 97, "scalp": 79, "scanno": 26, "scatter": [5, 16, 31], "scenario": [16, 126], "schalk": 77, "schedul": [31, 32], "scheme": [29, 32, 124, 154], "schirrmeist": [26, 27, 28, 29, 30, 31, 35, 77, 93, 103, 106, 109, 147, 154], "schirrmeister2017": [26, 77, 93, 103, 106, 109], "schwabed": [42, 62], "scientif": 35, "scikit": [5, 24, 25, 33, 72, 75, 78, 99, 109, 122, 126, 129, 131, 132, 145, 147, 153, 154], "scipi": [49, 50, 51, 52, 68, 72, 120, 123, 132], "score": [2, 4, 5, 9, 10, 11, 29, 30, 72, 94, 110, 132, 138, 139, 140, 154], "scorer": 140, "screen": 74, "script": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 145], "se": [10, 90], "seaborn": [14, 29, 30], "seamlessli": 32, "search": [1, 6, 24, 29, 30, 36, 38, 42, 54, 56, 72, 75, 78, 99, 109, 122, 126, 129, 131, 132, 145, 148, 153, 154], "search_result": [4, 29, 30], "searchwork": [2, 8, 73], "sec": [16, 17, 18, 19, 31], "second": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 30, 31, 32, 40, 74, 77, 79, 81, 82, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118], "second_kernel_s": 101, "section": [12, 22, 77, 151], "secur": 5, "sedlar": [31, 154], "see": [2, 3, 4, 5, 8, 9, 10, 11, 16, 18, 20, 21, 24, 26, 27, 28, 29, 30, 32, 47, 48, 66, 67, 72, 73, 74, 77, 80, 82, 83, 96, 99, 101, 102, 106, 114, 115, 118, 119, 120, 121, 123, 124, 125, 126, 131, 132, 133, 135, 136, 142, 145, 148, 151, 152], "seed": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 145], "seeg": 124, "segment": [12, 16, 29, 32, 46, 48, 65, 67, 95, 107, 120], "segment_length": [46, 65], "segmentationreconstruct": 154, "segmentpatch": 107, "seizur": 108, "select": [2, 4, 8, 9, 16, 20, 27, 28, 29, 30, 32, 37, 77, 107, 124, 133], "select_by_channel": 12, "select_by_dur": 12, "self": [1, 4, 6, 11, 24, 32, 72, 75, 80, 89, 92, 95, 99, 111, 122, 126, 131, 132, 134, 135, 136, 145, 148, 153, 154], "self_attn": 10, "send": [2, 3, 4, 8, 9, 10, 11, 16, 27, 28, 29, 30, 32], "sensit": [30, 74, 147], "sensor": [3, 4, 27, 28, 29, 30, 32, 40, 49, 50, 51, 52, 68, 77], "sensors_positions_matrix": [49, 68], "sent": [72, 132], "separ": [5, 29, 32, 74, 104, 120, 126, 135], "seq2seq": 11, "seq_len": 116, "sequenc": [36, 41, 72, 107, 114, 116, 132, 133, 136, 143, 151, 154], "sequencesampl": [9, 10, 11, 154], "sequenti": [3, 4, 5, 9, 10, 11, 16, 26, 27, 28, 29, 30, 32, 77, 99], "seri": [2, 4, 5, 8, 9, 10, 29, 30, 31, 72, 76, 83, 86, 92, 104, 110, 111, 132, 134, 138, 154], "serial": [5, 12, 15, 18, 23, 24, 75, 80, 122, 125, 131, 153, 154], "serv": [14, 74, 76, 83], "session": [2, 4, 8, 12, 18, 20, 21, 27, 28, 29, 30, 31, 32, 74, 77, 134], "session_t": 134, "set": [2, 4, 8, 9, 10, 11, 12, 14, 16, 17, 19, 22, 26, 27, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 66, 72, 74, 75, 77, 81, 82, 93, 97, 98, 109, 110, 111, 115, 117, 118, 121, 124, 125, 126, 131, 132, 145, 151, 154], "set_bipolar_refer": 124, "set_config": 27, "set_descript": [22, 32, 75, 76, 83], "set_eeg_refer": [12, 124], "set_log_level": [2, 8, 12, 14, 22], "set_montag": [12, 81, 82], "set_num_thread": 14, "set_param": [11, 72, 132], "set_random_se": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 154], "set_titl": [2, 8, 16, 31], "set_xlabel": [2, 4, 5, 8, 9, 10, 11, 16, 27, 28, 31], "set_xlim": 29, "set_ylabel": [2, 5, 8, 9, 10, 11, 16, 27, 28, 31], "set_ylim": [4, 27, 28], "seta": 12, "setb": 12, "seteegrefer": 154, "setter": 5, "setup": [2, 4, 8, 27, 150], "seven": 110, "seventh": 91, "sever": [4, 12, 18, 24, 90, 125, 126, 149], "sex": 5, "sfreq": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 26, 27, 28, 29, 30, 31, 32, 37, 43, 57, 61, 84, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 132, 154], "sgd": [72, 132], "shafait": 79, "shallow": [2, 8, 14, 26, 27, 28, 31, 109], "shallowconvnet": [26, 31], "shallowfbcsp": 154, "shallowfbcspnet": [2, 3, 4, 8, 14, 26, 27, 28, 29, 30, 31, 32], "shallu": 30, "shape": [2, 3, 4, 5, 8, 9, 10, 11, 17, 20, 22, 26, 27, 28, 29, 30, 32, 49, 68, 72, 92, 94, 95, 99, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 117, 136, 137, 141], "share": [2, 8, 14, 27, 28, 113], "sharex": [9, 10, 11], "shell": 148, "shh": 112, "shift": [3, 29, 43, 61, 113], "short": [11, 29, 32, 74, 92, 94], "short_ch_nam": 12, "shorter": [11, 154], "shortest": 120, "should": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 20, 26, 27, 28, 30, 37, 40, 46, 49, 54, 57, 65, 68, 70, 72, 73, 75, 76, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 121, 123, 124, 132, 140, 148, 152], "show": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 26, 28, 29, 30, 31, 32, 77, 99, 154], "show_titl": 12, "showcas": [12, 29, 32], "shown": [4, 5, 9, 11, 16, 29, 32, 74, 77], "shrink": 117, "shtml": [12, 81, 82], "shuffl": [4, 8, 14, 29, 30, 32, 39, 47, 48, 60, 67, 72, 132, 154], "siames": 5, "side": [40, 120], "sigmoid": [10, 72, 132], "sign": [53, 69], "sign_flip": 3, "signal": [2, 3, 4, 5, 8, 9, 10, 11, 12, 18, 20, 26, 28, 29, 30, 31, 36, 37, 38, 39, 42, 43, 46, 48, 49, 50, 51, 52, 54, 57, 58, 60, 61, 62, 65, 67, 68, 70, 74, 76, 80, 84, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 123, 124, 125, 126, 130, 132, 135, 154], "signatur": 140, "signflip": 3, "signific": 30, "significantli": 16, "silenc": 32, "silent": [89, 90, 95, 98], "similar": [5, 27, 118], "similarli": [21, 32], "simon": [3, 20, 154], "simonbrandt": [3, 20], "simpl": [5, 12, 16, 24, 25, 32, 33, 91, 99, 104, 109, 153], "simpleconv": 104, "simpler": 11, "simplest": 16, "simpli": [22, 26], "simplifi": [9, 10, 134, 154], "simul": 26, "simultan": [27, 97], "sin": 31, "sinc": [5, 9, 10, 11, 12, 22, 26, 30, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 132, 148], "singl": [5, 9, 10, 27, 30, 41, 42, 43, 61, 62, 72, 91, 94, 104, 112, 124, 132, 143, 154], "sinusoid": 31, "sit": 74, "site": [2, 5, 10, 11, 27, 31, 32], "situat": [72, 132], "size": [2, 3, 4, 5, 11, 14, 16, 26, 27, 28, 29, 30, 31, 32, 37, 46, 54, 57, 65, 70, 72, 84, 85, 86, 89, 90, 91, 92, 95, 97, 98, 99, 100, 104, 105, 107, 110, 111, 113, 114, 115, 117, 120, 123, 125, 126, 132, 135, 137, 141, 143, 147], "skip": [18, 22, 29, 32, 98, 117], "skip_by_annot": 120, "sklearn": [2, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 31, 72, 132, 140, 147, 154], "skorch": [2, 3, 4, 5, 8, 9, 10, 11, 17, 26, 27, 28, 29, 30, 31, 72, 84, 85, 86, 132, 154], "sleep": [7, 13, 16, 24, 30, 42, 62, 75, 80, 91, 92, 94, 99, 110, 111, 112, 116, 117, 122, 126, 131, 133, 134, 136, 145, 147, 153, 154], "sleep_physionet": [5, 9, 10, 11], "sleepdata": 112, "sleepphysionet": [5, 9, 10, 11, 16, 154], "sleepstagerblanco2020": [26, 154], "sleepstagerchambon2018": [5, 9, 26], "sleepstagereldele2021": [10, 26, 154], "slice": [30, 120, 121, 125, 126], "slicedata": 4, "slicedataset": [4, 29, 30], "slid": 89, "slide": [14, 31, 89, 125], "slightli": 140, "sliwowski": [2, 8], "slow": [5, 9, 10, 11, 16, 145, 154], "slower": [10, 14, 19, 126], "small": [11, 12, 27, 29, 148], "smaller": [5, 27, 32, 86, 97, 126], "smallest": 148, "smoothli": [54, 70], "smoothtimemask": 4, "sn": [14, 29, 30], "snippet": 148, "snyder": [42, 62], "so": [2, 5, 8, 9, 10, 11, 14, 16, 18, 26, 27, 28, 29, 30, 32, 37, 40, 72, 117, 125, 130, 132, 154], "societi": [49, 50, 51, 52, 68], "soft": 110, "softmax": [26, 27, 31, 72, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 132], "softwar": [35, 148], "solon": [101, 102], "solut": [16, 124], "solv": [145, 154], "solver": 5, "some": [2, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 22, 26, 27, 28, 30, 35, 72, 75, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 124, 132, 145], "song": [95, 154], "song2022": 95, "sort": [12, 27, 28, 154], "sound": [29, 32], "sourc": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 149, 150], "sourceestim": 120, "space": [5, 16, 91], "span": 79, "sparcnet": [26, 154], "spars": [72, 132], "spat_lay": 115, "spatial": [4, 26, 42, 62, 90, 93, 109, 117, 154], "spatial_conv": 9, "spatial_expans": 90, "speak": [9, 11, 14], "special": [72, 132], "specif": [5, 9, 10, 11, 16, 18, 30, 72, 87, 110, 113, 118, 132, 134, 150], "specifi": [2, 3, 5, 8, 9, 10, 11, 12, 18, 21, 22, 26, 27, 28, 29, 72, 73, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 124, 131, 132], "spectral": [3, 92], "speed": [10, 11, 16, 154], "speedup": 14, "spent": [9, 10, 11], "spheric": [49, 50, 51, 52, 68], "spherical_splin": [49, 50, 51, 52, 68], "sphinx": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "spline": [49, 50, 51, 52, 68], "split": [12, 15, 20, 23, 24, 26, 31, 48, 72, 75, 78, 93, 109, 126, 132, 153, 154], "split_first_lay": [14, 26, 93, 103, 109], "split_id": [5, 9, 10, 11, 12, 75, 154], "splitter": 29, "spoclab": 115, "springenberg": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 147], "sqrt": 129, "squar": [31, 48, 109, 132], "squeez": [2, 3, 4, 26, 27, 28, 29, 30, 32, 90], "src": 11, "srm": 90, "ss3": 9, "ssl": [5, 27], "ssvep": 46, "stabil": 129, "stabl": [2, 4, 5, 8, 16, 26, 72, 80, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 132, 145, 147], "stack": [3, 8], "stage": [7, 13, 24, 29, 30, 32, 75, 80, 92, 94, 99, 110, 111, 112, 116, 117, 122, 126, 131, 133, 134, 136, 145, 147, 153, 154], "stager": 116, "stai": [16, 27, 74], "standard": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 36, 44, 49, 50, 51, 52, 63, 68, 81, 82, 124, 129, 154], "standard_1020": [49, 68], "standard_scal": [5, 9, 10], "standardscal": 5, "stanford": [2, 8, 73], "stanlei": [5, 9, 10, 11], "start": [3, 4, 5, 12, 14, 16, 22, 27, 28, 29, 30, 32, 46, 54, 65, 70, 72, 86, 104, 118, 123, 125, 126, 132, 150], "start_dim": [9, 10], "start_ind": 17, "start_offset_sampl": [2, 14, 22, 31, 125], "state": [32, 133, 134, 135, 136], "state_dict": 99, "static": [37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 73, 100, 107], "statist": 12, "statu": 5, "std": [12, 29, 44, 63, 77], "std_train_scor": 4, "step": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 18, 22, 28, 29, 30, 32, 86, 92, 107, 126, 148, 154], "stft": [91, 92], "still": [2, 3, 4, 5, 8, 9, 11, 27, 28, 29, 77, 104], "stim": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32], "stim_channel": [17, 19], "stimuli": 77, "stimulu": [29, 30], "stochast": 31, "stop": [5, 32, 37, 57, 86, 125, 126, 144, 154], "stop_ind": 17, "stop_offset_sampl": [2, 14, 22, 31, 125, 154], "stopband": 16, "storag": 14, "store": [2, 4, 8, 9, 10, 11, 12, 14, 18, 22, 28, 29, 30, 32, 73, 75, 87, 154], "stori": [29, 32], "str": [14, 22, 26, 27, 28, 29, 36, 72, 73, 75, 76, 78, 79, 81, 82, 83, 84, 86, 87, 90, 93, 95, 99, 109, 118, 119, 120, 121, 122, 123, 124, 125, 126, 131, 132, 140, 147], "straightforward": 104, "strategi": [4, 25, 29, 30, 90], "strength": 4, "stricker": 79, "strictli": 5, "stride": [2, 9, 10, 11, 26, 27, 84, 85, 86, 90, 93, 95, 99, 109, 115, 125, 126], "stride_before_pool": [14, 31, 93], "string": [21, 22, 26, 35, 40, 50, 51, 52, 72, 75, 120, 121, 122, 131, 132, 140], "strip": 14, "strohmeier": 35, "strong": [104, 107], "strongli": [2, 8, 27, 28, 97, 98], "structur": [4, 5, 16, 17, 19, 134, 135, 154], "studi": [4, 5, 7, 24, 91, 92, 100, 104], "stumbl": 26, "style": [2, 5, 8, 27, 28, 50, 51, 52, 90, 115], "st\u00f8rmer": 154, "sub": [27, 154], "sub_df": 16, "subclass": [89, 90, 95, 98], "subdirectori": [16, 18, 75, 131], "subj": [74, 77], "subj_test": 5, "subj_train": 5, "subj_valid": 5, "subject": [4, 5, 9, 10, 11, 12, 14, 18, 19, 20, 21, 22, 29, 37, 44, 54, 57, 63, 70, 73, 74, 76, 77, 78, 80, 104, 134], "subject_id": [2, 3, 4, 5, 8, 9, 10, 11, 16, 17, 18, 19, 20, 21, 27, 28, 29, 30, 32, 73, 74, 77, 78, 80, 154], "sublayer_output": 10, "subplot": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31], "subplots_adjust": 12, "subsequ": [90, 118], "subset": [5, 8, 20, 29, 31, 75, 120, 121, 154], "subset_nam": 20, "substanti": [2, 3, 4, 5, 8, 9, 10, 11, 14, 19, 27, 28, 126], "suffici": 29, "suffix": [72, 132], "suggest": [37, 40, 44, 49, 50, 51, 52, 54, 57, 59, 63, 68, 86, 126], "sum": [32, 154], "summar": 14, "summari": [72, 99, 115, 132], "sun": [40, 59, 91, 92, 108], "super": [5, 32, 138, 139], "supervis": [1, 4, 6, 24, 29, 32, 75, 80, 92, 99, 111, 122, 126, 131, 134, 135, 145, 153, 154], "suppli": [2, 3, 5, 8, 9, 10, 11, 27, 28, 29], "support": [5, 9, 10, 11, 18, 27, 32, 72, 120, 123, 124, 130, 132, 154], "suppos": 26, "suppress": [48, 67, 74, 120], "supratak": 94, "supratak2017": 94, "suptitl": 12, "sure": 148, "surrog": [42, 62], "switch": [5, 32, 154], "sylvain": 154, "symmetr": 120, "synchron": 113, "synchroni": 113, "syncnet": [26, 154], "synthet": 48, "system": [5, 9, 10, 46, 49, 68, 81, 82, 91, 94, 95, 97, 111, 112, 113, 120, 151], "systemat": 4, "t": [2, 4, 5, 11, 17, 19, 26, 27, 28, 29, 30, 31, 32, 42, 62, 72, 73, 74, 79, 93, 103, 105, 106, 109, 117, 118, 128, 129, 132, 145, 147], "t0": 19, "t1": 19, "t2": 19, "t3": 12, "t4": 12, "t5": 12, "t6": 12, "t_filter": 115, "t_max": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "tab": [2, 5, 8, 16, 27, 28], "tabl": [27, 28, 29, 30, 32, 89, 99, 154], "take": [9, 10, 11, 16, 17, 29, 31, 56, 87, 89, 90, 91, 92, 95, 98, 112], "taken": [2, 5, 8, 14], "tangermann": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 147], "tanh": 11, "tap": 77, "target": [2, 4, 5, 8, 9, 10, 15, 17, 18, 20, 23, 24, 27, 28, 29, 31, 47, 56, 66, 72, 73, 75, 76, 81, 83, 84, 86, 87, 113, 125, 126, 132, 133, 134, 137, 138, 141, 142, 143, 147, 153, 154], "target_extractor": [138, 139, 140], "target_from": 26, "target_nam": [12, 14, 18, 22, 31, 75, 76, 79, 81, 82, 87, 154], "target_sfreq": [2, 8], "target_subset": 31, "target_transform": [2, 8, 9, 10, 75, 154], "targets_from": [2, 83, 125, 132], "task": [4, 9, 10, 11, 26, 30, 42, 62, 74, 76, 79, 135], "tau": 113, "tau_max": 135, "tau_neg": [5, 135], "tau_po": [5, 135], "tb": 14, "tce": 112, "tcn": [26, 89, 105, 154], "tcn_activ": 89, "tcn_depth": 89, "tcn_dropout": 89, "tcn_kernel_s": 89, "tcn_n_filter": 89, "tcnet": 105, "techniqu": [40, 59, 120, 124], "tell": [3, 4, 148], "temp": [2, 8], "temp_filter_length": 90, "temp_filter_length_inp": 90, "temp_lay": 115, "temp_len": 115, "temp_span": 115, "temperatur": 80, "tempfil": [12, 16, 18], "templ": [12, 81, 82, 154], "tempor": [5, 9, 10, 14, 26, 89, 90, 93, 95, 96, 97, 105, 107, 108, 109, 110, 111, 112, 114, 115, 117, 154], "temporalconv": 107, "temporari": [18, 154], "temporarydirectori": 16, "ten_twenty_montag": [49, 68], "teng": 100, "tensor": [9, 10, 11, 22, 26, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 91, 92, 94, 95, 98, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 132, 137, 141, 142], "tensorboard": 32, "tensorboardx": 32, "tensorflow": [89, 100], "teon": 35, "term": [2, 4, 8, 94, 99], "terri": 154, "test": [9, 10, 11, 16, 21, 24, 25, 27, 28, 30, 33, 72, 75, 77, 78, 99, 109, 122, 126, 129, 131, 132, 145, 153, 154], "test_acc": [29, 32], "test_accuraci": 32, "test_bal_acc": 5, "test_dataload": 32, "test_load": 32, "test_loss": 32, "test_model": 32, "test_sampl": 5, "test_set": [2, 8, 29, 31, 32], "test_siz": [5, 8, 29], "test_step": 32, "test_y_pr": 5, "text": [9, 10, 11, 29, 147], "textcolor": 147, "tf": [42, 62], "than": [2, 5, 8, 9, 10, 11, 12, 14, 16, 27, 32, 37, 46, 57, 65, 72, 79, 86, 120, 126, 132, 154], "thei": [2, 3, 4, 5, 8, 14, 16, 26, 27, 28, 29, 30, 32, 124, 154], "them": [3, 4, 5, 12, 14, 16, 17, 19, 26, 27, 29, 32, 72, 75, 89, 90, 91, 93, 94, 95, 98, 99, 103, 105, 106, 107, 109, 110, 111, 112, 114, 117, 132, 152], "theo": [11, 154], "therefor": [2, 8, 12, 16, 27, 28, 29, 30, 32, 140], "thi": [0, 2, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 22, 31, 50, 51, 52, 72, 73, 74, 75, 77, 79, 80, 81, 82, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 120, 123, 124, 126, 128, 129, 131, 132, 134, 140, 145, 148, 152, 154], "thing": 152, "thinker": [115, 154], "thinkerinvari": 115, "third": 32, "third_kernel_s": [101, 102], "thirti": 91, "thoma": 154, "those": [2, 4, 5, 8, 12, 72, 120, 121, 132], "though": [14, 16, 29, 32], "thread": 14, "three": [4, 16, 29, 32, 72, 73, 79, 95, 97, 104, 132, 148], "through": [3, 4, 11, 12, 14, 16, 20, 22, 27, 49, 68, 76, 83, 91, 94, 107, 110, 111, 112, 154], "throughout": [2, 8, 9, 10, 11, 28, 29, 32], "thu": [2, 4, 8, 118], "thumb": [2, 8, 27], "th\u00e9o": 154, "tibor": [35, 154], "tick_param": [2, 5, 8, 12, 27, 28], "tidnet": [26, 154], "tight": [72, 132], "tight_layout": [2, 4, 5, 8, 9, 10, 11, 27, 28, 30], "tii": 89, "time": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 46, 48, 55, 65, 67, 71, 72, 73, 75, 80, 83, 89, 90, 91, 92, 93, 94, 95, 96, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 120, 123, 128, 129, 131, 132, 133, 137, 138, 141, 144, 154], "time_as_index": 118, "time_conv_size_": [111, 117], "time_frequ": 3, "time_start": [46, 65], "time_taken": 16, "timecrop": 154, "timedistribut": [9, 10, 154], "timeseri": 141, "timeseriesloss": 2, "timestep": 27, "titl": [3, 12, 29, 30, 35], "tmax": [2, 8, 12, 118], "tmin": [2, 8, 12, 16, 19, 118], "tmp": [16, 18], "tmp4f42zyu": 16, "tmp_3ygye_x": 18, "tmp_dir": 16, "tmpdir": 18, "tmpgwi690jo": 16, "tmpufi4ur1h": 16, "tmpvtj60y_x": 16, "tnsre": [10, 97, 112], "to_csv": 14, "to_dense_prediction_model": [2, 27, 31, 99, 154], "to_list": [5, 9, 10, 11], "to_numpi": [31, 138, 139, 140], "tobia": 35, "todo": 2, "toe": 77, "togeth": [16, 27, 154], "token": 107, "tokenizor": 107, "toml": 154, "tone": 74, "tongu": [18, 21, 27, 28, 29, 30, 32, 74], "tonio": 35, "too": [11, 91], "tool": [2, 4, 8, 80, 149, 152], "toolbox": 149, "top": [5, 9, 10, 11, 35], "topic": [1, 24, 35], "torch": [2, 3, 4, 5, 8, 9, 10, 11, 14, 22, 26, 27, 28, 29, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 132, 137, 141, 142, 143, 145, 154], "torch_stft": 92, "torchinfo": [27, 28, 29, 32, 99, 154], "torchmetr": 32, "torchvis": [2, 8, 28, 30], "total": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 34, 74, 153], "total_tri": [74, 77], "toward": 100, "tpu": 32, "tqdm": 32, "tr_idx": 29, "track_running_stat": 10, "tracker": 148, "tradeoff": 16, "tradit": 95, "train": [12, 14, 20, 21, 33, 72, 75, 77, 78, 83, 90, 91, 99, 107, 109, 122, 126, 129, 131, 132, 145, 153, 154], "train_acc": 5, "train_accuraci": [3, 27, 28, 29, 30, 32], "train_bal_acc": [5, 9, 10, 11], "train_dataload": 32, "train_i": [4, 30], "train_indic": 29, "train_load": 32, "train_loss": [2, 3, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 72, 132], "train_misclass": [27, 28], "train_neg_root_mean_squared_error": 31, "train_one_epoch": 32, "train_pearson_r": 8, "train_r2": 8, "train_sampl": [5, 9, 10, 11], "train_set": [2, 3, 4, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32], "train_split": [2, 3, 4, 5, 8, 9, 10, 11, 26, 27, 28, 29, 30, 31, 72, 132], "train_subset": 29, "train_test_split": [5, 8, 29], "train_val_split": 29, "train_x": [4, 30], "train_y_pr": 5, "trainabl": [3, 4, 11, 26, 27, 28, 29, 32], "trained_model": 14, "trainer": 32, "training_scor": 4, "training_setup": 14, "training_setup_end": 14, "training_setup_start": 14, "training_step": 32, "tran": [5, 9, 10], "transact": [5, 10, 46, 89, 94, 95, 97, 111, 112], "transax": 29, "transform": [2, 5, 8, 9, 10, 11, 20, 27, 28, 29, 30, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 69, 70, 71, 72, 76, 83, 84, 85, 86, 90, 91, 92, 95, 99, 107, 108, 132, 154], "transformerencod": 95, "transforms_freq": 4, "transforms_spati": 4, "transforms_tim": 4, "transit": [16, 37, 57, 120], "translat": 3, "transposit": 154, "tremend": 107, "trend": 31, "tri": 140, "trial": [2, 3, 4, 8, 19, 21, 27, 28, 29, 30, 31, 32, 48, 67, 72, 74, 77, 84, 86, 126, 132, 138, 139, 143, 144, 154], "trial_label": [72, 132, 143], "trial_predict": [72, 132, 143], "trial_start_offset_sampl": [3, 4, 5, 9, 10, 11, 18, 19, 21, 27, 28, 29, 30, 32, 86, 126], "trial_start_offset_second": [3, 4, 27, 28, 29, 30, 32], "trial_stop_offset_sampl": [3, 4, 5, 9, 10, 11, 18, 19, 21, 27, 28, 29, 30, 31, 32, 86, 126, 154], "trial_stop_offset_second": [29, 30], "trialwis": [2, 4, 8, 20, 27, 28, 30, 72, 132, 143, 154], "trigger": 11, "troubleshoot": 151, "true": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 26, 27, 28, 29, 30, 31, 32, 47, 49, 50, 51, 52, 72, 75, 76, 79, 80, 81, 82, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117, 118, 122, 124, 125, 126, 127, 130, 132, 135, 136, 138, 139, 140, 143, 145, 154], "truncat": 107, "trust": 4, "trustworthi": [28, 29, 30], "truth": 31, "try": [3, 4, 12, 18, 22, 24, 30, 148, 152], "tsne": 5, "tugraz": 27, "tuh": [7, 13, 14, 15, 23, 24, 75, 82, 91, 122, 125, 131, 153, 154], "tuh_eeg": [12, 14, 22, 81, 82], "tuh_eeg_abnorm": 14, "tuh_path": [12, 14, 22], "tuh_preproc": 12, "tuh_window": [12, 22], "tuhabnorm": [14, 18, 154], "tuk": [5, 9, 10, 11], "tune": [24, 25, 32, 33, 75, 78, 95, 99, 109, 122, 126, 129, 131, 145, 153, 154], "tuning_playbook": 30, "tupl": [29, 30, 47, 56, 66, 72, 76, 80, 81, 82, 91, 99, 100, 113, 123, 130, 132, 135, 147], "tutori": [2, 3, 4, 5, 8, 9, 10, 11, 22, 24, 26, 27, 28, 29, 30, 32, 152, 154], "tuzel": [37, 44, 54, 57, 63, 70], "tweak": 29, "twelfth": 107, "twenti": 74, "twice": 120, "twinx": [2, 5, 8, 27, 28], "two": [4, 5, 9, 10, 11, 12, 14, 16, 18, 27, 29, 32, 47, 54, 66, 74, 77, 80, 98, 104, 107, 110, 120, 123, 124, 135, 136, 142, 154], "type": [2, 3, 4, 8, 11, 26, 27, 28, 29, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 66, 72, 75, 77, 84, 85, 86, 87, 90, 92, 98, 99, 100, 104, 105, 107, 108, 113, 116, 120, 121, 123, 124, 125, 126, 128, 129, 131, 132, 134, 136, 142, 144, 147, 154], "typic": [27, 72, 118, 132], "u": [3, 5, 7, 13, 24, 30, 75, 80, 99, 117, 122, 126, 131, 133, 134, 136, 145, 147, 152, 153, 154], "ufabc": 4, "ul": 79, "ultim": 14, "ultrabold": 147, "ultralight": 147, "umap": 5, "unabl": 4, "unaffect": [72, 132], "uncov": [4, 5, 135], "undefinedmetricwarn": 10, "under": [5, 14, 73, 131, 152, 154], "underli": [2, 5, 8, 28, 30, 122], "underscore_cas": 0, "understand": [5, 24, 29, 104], "unexpect": 148, "unfilt": 130, "unifi": 154, "uniform": [56, 113], "uniformli": [42, 47, 49, 50, 51, 52, 62, 133], "uniniti": [4, 72, 132], "uninstanti": [72, 132], "unintend": 112, "uniqu": [5, 9, 10, 11, 21, 72, 76, 79, 132], "unit": [11, 26, 120, 152], "unit_mul": 26, "univers": [12, 77, 81, 82, 154], "unknown": [31, 140], "unlabel": 5, "unless": [5, 32, 132], "unmodifi": [72, 132], "unoffici": 108, "unpickl": [5, 72, 132], "unreli": 29, "unseen": 29, "until": [29, 74], "untrac": 154, "untrust": 5, "unverifi": 27, "up": [16, 17, 74, 117, 123, 154], "updat": [32, 72, 73, 75, 76, 83, 86, 126, 130, 132, 151, 154], "update_path": [17, 19], "upfirdn": 123, "upon": [18, 26], "upper": [12, 16, 120], "upsampl": [11, 117, 123], "upward": 77, "url": 35, "urllib3": 27, "us": [2, 3, 4, 7, 8, 13, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 35, 37, 39, 40, 44, 46, 47, 48, 49, 50, 51, 52, 55, 58, 60, 62, 63, 67, 68, 72, 74, 77, 79, 83, 89, 90, 92, 95, 96, 97, 98, 100, 101, 103, 104, 105, 106, 107, 108, 110, 113, 114, 115, 118, 120, 121, 123, 124, 132, 140, 143, 148, 151, 152, 153, 154], "usag": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 148, 154], "use_abs_pos_emb": 107, "use_cach": [72, 132, 138, 139], "use_deterministic_algorithm": 145, "use_log_softmax": 154, "use_mean_pool": 107, "use_mlp": 90, "use_mne_epoch": [126, 154], "user": [5, 27, 72, 132, 148, 150, 151, 154], "userwarn": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 18, 19, 27, 28, 29, 30, 31, 32], "usleep": [11, 26, 154], "usual": [2, 3, 4, 8, 16, 29, 32, 72, 132], "util": [2, 3, 4, 5, 8, 9, 10, 11, 14, 18, 22, 26, 27, 28, 30, 31, 32, 72, 132, 154], "uv": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32], "v": [2, 3, 4, 5, 8, 9, 10, 12, 16, 27, 28, 29, 30, 32, 97, 101, 102, 104, 114], "v1": [22, 32], "v2": [14, 107], "v4": 102, "v_": 129, "v_num": 32, "v_t": 129, "val_idx": 29, "val_indic": 29, "val_subset": 29, "valentin": 154, "valid": [2, 21, 26, 27, 31, 32, 72, 112, 124, 125, 126, 132, 140, 141, 154], "valid_acc": [3, 5, 9, 10, 11, 26, 28, 29, 30], "valid_accuraci": [3, 27, 28, 29, 30], "valid_bal_acc": [5, 9, 10, 11], "valid_loss": [2, 3, 5, 8, 9, 10, 11, 26, 27, 28, 29, 30, 31], "valid_misclass": [27, 28], "valid_neg_root_mean_squared_error": 31, "valid_pearson_r": 8, "valid_r2": 8, "valid_sampl": [5, 9, 10, 11], "valid_set": [2, 3, 8, 9, 10, 11, 27, 28, 31], "valid_y_pr": 5, "validation_scor": 4, "validsplit": [26, 30, 72, 132], "valu": [2, 4, 5, 8, 9, 10, 11, 12, 26, 27, 28, 30, 31, 32, 43, 47, 66, 72, 75, 76, 83, 86, 90, 98, 104, 107, 115, 120, 121, 123, 124, 125, 126, 132, 141, 142, 143, 154], "valueerror": [14, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 117], "vaquerizo": 97, "var_nam": [3, 4, 11, 26, 27, 28, 29, 32, 99], "variabl": [2, 4, 8, 29, 30, 73, 145], "varianc": [29, 30, 129], "varun": 30, "vazquez": 97, "ve": 148, "vector": [9, 10, 107, 120, 123], "verbos": [2, 3, 4, 8, 29, 30, 72, 73, 118, 120, 121, 123, 124, 125, 126, 127, 132, 154], "veri": [11, 29, 32, 75, 104, 126, 131], "verif": 27, "verifi": 152, "version": [2, 3, 4, 5, 9, 10, 18, 20, 21, 22, 29, 30, 31, 72, 79, 90, 91, 95, 99, 104, 107, 108, 118, 119, 120, 121, 123, 124, 132, 148, 150, 151, 152], "version_0": 32, "versionad": 92, "versu": 31, "vertic": 120, "verticalalign": 29, "via": [5, 26, 28, 29, 30, 117, 120, 150, 151, 154], "view": [2, 4, 8, 22, 73], "villar": 97, "vinai": [28, 29, 30], "viridi": 5, "virtual": 124, "vision": 98, "visit": [26, 29], "visual": [2, 8, 9, 10, 11, 12, 26, 27, 28, 30, 31, 35, 77, 93, 95, 103, 106, 107, 109, 149, 154], "vmax": 147, "vmin": 147, "vol": [10, 112], "volt": 12, "volta": [72, 132], "volum": 35, "volv": 77, "vqsnp": 107, "vytauta": 154, "w": [5, 9, 10, 11, 12, 27, 28, 29, 30, 79, 90, 108], "w_1": 10, "w_2": 10, "wa": [4, 5, 9, 10, 11, 27, 28, 29, 32, 72, 74, 77, 91, 95, 112, 120, 132, 133, 154], "wai": [2, 5, 8, 16, 21, 24, 26, 29, 112, 150, 152], "wainrib": [5, 9, 10, 111], "wake": [9, 10, 11, 80], "wang": [44, 63, 105], "want": [12, 14, 18, 21, 22, 24, 28, 29, 30, 32, 72, 132, 149, 152], "warm": [72, 132], "warm_start": [72, 132], "warn": [2, 3, 4, 5, 8, 9, 10, 12, 14, 16, 18, 19, 27, 28, 29, 30, 31, 32, 74, 112, 119, 125, 126, 145, 154], "wave": [5, 9, 10, 11], "wavelet": 113, "waytowich": [101, 102], "we": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 21, 22, 24, 26, 27, 28, 29, 30, 32, 35, 77, 91, 95, 132, 145, 148, 151, 152], "websit": 4, "wei": 107, "weight": [5, 9, 10, 11, 29, 30, 32, 89, 91, 105, 107, 147], "weight_decai": [2, 3, 4, 8, 27, 28, 29, 32], "weights_onli": 5, "welcom": 22, "well": [2, 5, 8, 12, 26, 27, 28, 29, 32, 86, 126, 149, 154], "wenlong": 46, "were": [2, 8, 9, 11, 14, 19, 26, 30, 74, 75, 77, 95, 110, 120, 154], "westov": [40, 59, 91, 92, 108], "what": [26, 29, 72, 89, 125, 126, 132], "whatev": [72, 132], "whats_new": 154, "when": [5, 9, 10, 11, 14, 16, 22, 27, 29, 32, 35, 41, 42, 49, 50, 51, 52, 56, 62, 68, 72, 73, 78, 84, 85, 86, 89, 91, 95, 117, 119, 120, 121, 123, 124, 125, 126, 131, 132, 145, 148, 154], "whenev": 16, "where": [2, 4, 5, 8, 9, 10, 22, 27, 28, 29, 37, 46, 47, 49, 54, 57, 65, 66, 68, 70, 72, 73, 75, 84, 104, 107, 113, 131, 132, 143, 145, 154], "whether": [5, 14, 26, 38, 39, 40, 42, 48, 49, 50, 51, 52, 53, 55, 56, 62, 68, 72, 75, 83, 84, 85, 86, 87, 89, 90, 93, 95, 96, 97, 98, 99, 101, 103, 106, 107, 108, 109, 110, 114, 115, 117, 125, 130, 131, 132, 135, 140, 145, 148], "which": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 19, 20, 21, 24, 26, 27, 29, 30, 32, 35, 36, 39, 42, 48, 49, 60, 62, 67, 68, 72, 75, 76, 77, 83, 99, 104, 112, 116, 120, 123, 124, 126, 132, 134, 135, 136, 148], "while": [4, 5, 14, 29, 32, 77, 89, 90, 95, 98, 104, 110, 144], "white": [44, 63], "whitespac": 154, "who": 149, "whole": [2, 8, 9, 10], "whose": [72, 86, 126, 132], "wide": 98, "width": [12, 30, 100, 104, 113, 115, 120], "wil": 20, "wild": [91, 92, 108], "wilson": [20, 154], "wimpff": [90, 154], "win_len_": 14, "winddow_size_sampl": 125, "window": [14, 16, 18, 19, 21, 26, 72, 75, 83, 84, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 120, 123, 125, 126, 132, 133, 134, 135, 136, 143, 144, 154], "window_ind": 17, "window_kwarg": [27, 28, 75], "window_len": 141, "window_len_": 14, "window_len_sampl": 14, "window_preproc_kwarg": 75, "window_s": 154, "window_size_": [5, 9, 10, 11], "window_size_sampl": [2, 5, 8, 9, 10, 11, 12, 14, 17, 19, 22, 27, 31, 84, 85, 86, 125, 126, 127], "window_stride_sampl": [2, 5, 9, 10, 11, 12, 14, 17, 19, 22, 27, 31, 84, 85, 86, 125, 126], "windows_d": [14, 16], "windows_dataset": [3, 4, 5, 8, 9, 10, 11, 17, 18, 19, 27, 28, 29, 30, 31, 32, 84, 85, 86, 125, 126], "windows_dataset_load": 18, "windowsattentionblock": 107, "windowsdataset": [3, 18, 26, 75, 84, 85, 86, 87, 125, 126, 131, 132, 154], "winner": 97, "wise": [3, 4, 5, 9, 10, 11], "with_f1_scor": 147, "with_skip_connect": [11, 117], "within": [3, 4, 77, 89, 90, 95, 98, 104, 115, 135, 154], "withinconsist": 86, "without": [16, 26, 27, 29, 30, 32, 72, 132, 142, 154], "wolfram": 35, "work": [2, 3, 4, 5, 8, 9, 10, 12, 16, 18, 19, 20, 22, 24, 27, 28, 29, 30, 31, 32, 72, 92, 99, 117, 118, 132, 140, 149, 151, 154], "worker": [14, 32, 143, 154], "worker_init_fn": 14, "world": [32, 92], "wors": 140, "would": [3, 26, 27, 29, 32, 72, 93, 109, 132], "wrap": [5, 26, 32, 75, 123], "wrapper": [26, 28, 29, 91], "write": [16, 18], "written": [11, 131, 150], "wrong": 154, "wspace": 12, "wu": 94, "www": [12, 14, 35, 73, 81, 82], "x": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 20, 22, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 84, 85, 86, 89, 90, 91, 92, 94, 95, 98, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 117, 123, 128, 129, 132, 137, 140, 141, 143], "x1": [5, 135], "x2": [5, 135], "x27": 4, "x_i": 17, "x_t": [128, 129], "x_tr": 3, "x_train": 29, "xiao": 92, "xlabel": [3, 12, 29, 30], "xlim": 12, "xxx": 14, "y": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 20, 22, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 51, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 84, 85, 86, 94, 95, 98, 100, 113, 123, 132, 140], "y1": 5, "y2": 5, "y_estim": 31, "y_gt": 31, "y_hat": 32, "y_i": 17, "y_pred": [5, 9, 10, 11, 27, 28, 72, 117, 139], "y_proba": [72, 132], "y_test": [2, 8, 29], "y_train": [2, 8, 9, 10, 11, 29], "y_true": [5, 9, 10, 11, 27, 28, 72], "y_valid": [2, 8], "yang": [90, 91, 92, 108], "yang2021": 92, "yang2023": 91, "yann": [47, 66, 142], "yao2001": 124, "yassin": [104, 154], "yassine2023": 104, "yassine2023cod": 104, "ycq091044": [91, 92, 108], "ye": 107, "year": [12, 35], "yerr": 4, "yet": [17, 19, 99, 152], "yield": [5, 14, 20, 74, 115, 148], "ylabel": [3, 12, 30], "ylgnbu": 30, "ylim": 12, "yml": 154, "yonghao": 154, "you": [2, 3, 4, 5, 8, 9, 11, 12, 16, 17, 18, 19, 21, 22, 24, 27, 28, 29, 32, 35, 72, 132, 140, 148, 150, 151, 152], "your": [2, 8, 14, 16, 21, 24, 25, 27, 28, 30, 33, 35, 72, 75, 78, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 117, 122, 126, 129, 131, 132, 145, 148, 150, 153], "ys1": 5, "ys2": 5, "ytick": 12, "z": [5, 9, 10, 31, 49, 52, 68, 108, 114], "z1": 5, "z2": 5, "zachari": 30, "zamboni": 154, "zeghidour": [38, 39, 58, 60], "zenodo": 35, "zerfowski": 90, "zero": [11, 16, 46, 54, 65, 70, 90, 120, 123, 126, 129, 154], "zero_divis": 10, "zero_grad": [14, 32], "zhang": [47, 66, 98, 142], "zhao": 107, "zheng": 95, "zhiliang": 107, "zhong": [44, 63], "zip": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "zipbal": 152, "zk881ps0522": [2, 8, 73], "zscore": 154, "zwinderman": [5, 9, 10, 11], "\u015bliwowski": 154, "\u03bcv": 74, "\u03c6max": 4}, "titles": ["API Reference", "Advanced neural network training strategies", "Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset", "Data Augmentation on BCIC IV 2a Dataset", "Searching the best data augmentation on BCIC IV 2a Dataset", "Self-supervised learning on EEG with relative positioning", "Computation times", "Applied examples on real-world datasets", "Fingers flexion decoding on BCIC IV 4 ECoG Dataset", "Sleep staging on the Sleep Physionet dataset using Chambon2018 network", "Sleep staging on the Sleep Physionet dataset using Eldele2021", "Sleep staging on the Sleep Physionet dataset using U-Sleep network", "Process a big data EEG resource (TUH EEG Corpus)", "Computation times", "Benchmarking eager and lazy loading", "Loading and organizing data", "Benchmarking preprocessing with parallelization and serialization", "Custom Dataset Example", "Load and save dataset example", "MNE Dataset Example", "MOABB Dataset Example", "Split Dataset Example", "Multiple discrete targets with the TUH EEG Corpus", "Computation times", "Examples", "Basic model building and training", "Simple training on MNE epochs", "Cropped Decoding on BCIC IV 2a Dataset", "Basic Brain Decoding on EEG Data", "How to train, test and tune your model?", "Hyperparameter tuning with scikit-learn", "Convolutional neural network regression model on fake data.", "Training a Braindecode model in PyTorch", "Computation times", "Computation times", "How to cite Braindecode", "braindecode.augmentation.AugmentedDataLoader", "braindecode.augmentation.BandstopFilter", "braindecode.augmentation.ChannelsDropout", "braindecode.augmentation.ChannelsShuffle", "braindecode.augmentation.ChannelsSymmetry", "braindecode.augmentation.Compose", "braindecode.augmentation.FTSurrogate", "braindecode.augmentation.FrequencyShift", "braindecode.augmentation.GaussianNoise", "braindecode.augmentation.IdentityTransform", "braindecode.augmentation.MaskEncoding", "braindecode.augmentation.Mixup", "braindecode.augmentation.SegmentationReconstruction", "braindecode.augmentation.SensorsRotation", "braindecode.augmentation.SensorsXRotation", "braindecode.augmentation.SensorsYRotation", "braindecode.augmentation.SensorsZRotation", "braindecode.augmentation.SignFlip", "braindecode.augmentation.SmoothTimeMask", "braindecode.augmentation.TimeReverse", "braindecode.augmentation.Transform", "braindecode.augmentation.functional.bandstop_filter", "braindecode.augmentation.functional.channels_dropout", "braindecode.augmentation.functional.channels_permute", "braindecode.augmentation.functional.channels_shuffle", "braindecode.augmentation.functional.frequency_shift", "braindecode.augmentation.functional.ft_surrogate", "braindecode.augmentation.functional.gaussian_noise", "braindecode.augmentation.functional.identity", "braindecode.augmentation.functional.mask_encoding", "braindecode.augmentation.functional.mixup", "braindecode.augmentation.functional.segmentation_reconstruction", "braindecode.augmentation.functional.sensors_rotation", "braindecode.augmentation.functional.sign_flip", "braindecode.augmentation.functional.smooth_time_mask", "braindecode.augmentation.functional.time_reverse", "braindecode.classifier.EEGClassifier", "braindecode.datasets.BCICompetitionIVDataset4", "braindecode.datasets.BNCI2014001", "braindecode.datasets.BaseConcatDataset", "braindecode.datasets.BaseDataset", "braindecode.datasets.HGD", "braindecode.datasets.MOABBDataset", "braindecode.datasets.NMT", "braindecode.datasets.SleepPhysionet", "braindecode.datasets.TUH", "braindecode.datasets.TUHAbnormal", "braindecode.datasets.WindowsDataset", "braindecode.datasets.create_from_X_y", "braindecode.datasets.create_from_mne_epochs", "braindecode.datasets.create_from_mne_raw", "braindecode.datautil.load_concat_dataset", "braindecode.datautil.save_concat_dataset", "braindecode.models.ATCNet", "braindecode.models.AttentionBaseNet", "braindecode.models.BIOT", "braindecode.models.ContraWR", "braindecode.models.Deep4Net", "braindecode.models.DeepSleepNet", "braindecode.models.EEGConformer", "braindecode.models.EEGITNet", "braindecode.models.EEGInceptionERP", "braindecode.models.EEGInceptionMI", "braindecode.models.EEGModuleMixin", "braindecode.models.EEGNeX", "braindecode.models.EEGNetv1", "braindecode.models.EEGNetv4", "braindecode.models.EEGResNet", "braindecode.models.EEGSimpleConv", "braindecode.models.EEGTCNet", "braindecode.models.HybridNet", "braindecode.models.Labram", "braindecode.models.SPARCNet", "braindecode.models.ShallowFBCSPNet", "braindecode.models.SleepStagerBlanco2020", "braindecode.models.SleepStagerChambon2018", "braindecode.models.SleepStagerEldele2021", "braindecode.models.SyncNet", "braindecode.models.TCN", "braindecode.models.TIDNet", "braindecode.models.TimeDistributed", "braindecode.models.USleep", "braindecode.preprocessing.Crop", "braindecode.preprocessing.DropChannels", "braindecode.preprocessing.Filter", "braindecode.preprocessing.Pick", "braindecode.preprocessing.Preprocessor", "braindecode.preprocessing.Resample", "braindecode.preprocessing.SetEEGReference", "braindecode.preprocessing.create_fixed_length_windows", "braindecode.preprocessing.create_windows_from_events", "braindecode.preprocessing.create_windows_from_target_channels", "braindecode.preprocessing.exponential_moving_demean", "braindecode.preprocessing.exponential_moving_standardize", "braindecode.preprocessing.filterbank", "braindecode.preprocessing.preprocess", "braindecode.regressor.EEGRegressor", "braindecode.samplers.BalancedSequenceSampler", "braindecode.samplers.RecordingSampler", "braindecode.samplers.RelativePositioningSampler", "braindecode.samplers.SequenceSampler", "braindecode.training.CroppedLoss", "braindecode.training.CroppedTimeSeriesEpochScoring", "braindecode.training.CroppedTrialEpochScoring", "braindecode.training.PostEpochTrainScoring", "braindecode.training.TimeSeriesLoss", "braindecode.training.mixup_criterion", "braindecode.training.predict_trials", "braindecode.training.trial_preds_from_window_preds", "braindecode.util.set_random_seeds", "braindecode.visualization.compute_amplitude_gradients", "braindecode.visualization.plot_confusion_matrix", "Frequently Asked Questions (FAQ)", "Braindecode", "Installation", "Installing from PyPI", "Installing from sources", "Computation times", "What\u2019s new"], "titleterms": {"": [29, 154], "0": 154, "06": 154, "07": 154, "1": [29, 32, 154], "10": 154, "11": 154, "12": 154, "14": 154, "2": [29, 32], "2021": 154, "2022": 154, "2a": [3, 4, 27], "3": 29, "4": [2, 8], "5": 154, "6": 154, "7": 154, "8": 154, "9": 154, "By": 21, "about": [29, 32], "advanc": [1, 24], "algorithm": 35, "an": [3, 4], "analys": 4, "api": [0, 154], "appli": [7, 24], "ask": 148, "atcnet": 89, "attentionbasenet": 90, "augment": [0, 3, 4, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71], "augmenteddataload": 36, "author": 154, "balancedsequencesampl": 133, "bandstop_filt": 57, "bandstopfilt": 37, "baseconcatdataset": 75, "basedataset": 76, "basic": [24, 25, 28], "bcic": [2, 3, 4, 8, 27], "bcicompetitionivdataset4": 73, "benchmark": [14, 16], "best": [4, 30], "between": 31, "big": 12, "biot": 91, "bnci2014001": 74, "brain": 28, "braindecod": [26, 32, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 152], "bug": [148, 154], "build": [24, 25], "can": 148, "care": [29, 32], "chambon2018": 9, "chang": 154, "channels_dropout": 58, "channels_permut": 59, "channels_shuffl": 60, "channelsdropout": 38, "channelsshuffl": 39, "channelssymmetri": 40, "choos": 31, "cite": [35, 148], "classifi": [0, 72], "clone": 152, "cnn": 31, "combin": 12, "compat": 26, "compos": [3, 41], "comput": [2, 6, 8, 12, 13, 23, 27, 28, 30, 32, 33, 34, 153], "compute_amplitude_gradi": 146, "conclus": 5, "confus": [27, 28], "contrawr": 92, "convolut": 31, "corpu": [12, 22], "cover": [3, 4, 5, 12, 21, 26, 27, 28, 29, 30, 32], "cpu": 31, "creat": [2, 3, 4, 5, 8, 9, 10, 11, 12, 22, 27, 28, 29, 30, 32], "create_fixed_length_window": 125, "create_from_mne_epoch": 85, "create_from_mne_raw": 86, "create_from_x_i": 84, "create_windows_from_ev": 126, "create_windows_from_target_channel": 127, "crop": [2, 27, 118], "croppedloss": 137, "croppedtimeseriesepochscor": 138, "croppedtrialepochscor": 139, "cross": 29, "current": 154, "custom": 17, "cut": [2, 8, 12, 27, 32], "data": [0, 3, 4, 12, 15, 22, 24, 26, 27, 28, 29, 31], "dataload": 22, "dataset": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 17, 18, 19, 20, 21, 22, 24, 27, 28, 29, 30, 31, 32, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86], "datautil": [87, 88], "decod": [2, 8, 27, 28], "deep4net": 93, "deepsleepnet": 94, "defin": [3, 4, 29, 31, 32], "descript": 21, "desir": [3, 4], "dev0": 154, "discret": 22, "do": [30, 148], "document": 26, "dropchannel": 119, "eager": 14, "ecog": [2, 8], "eeg": [5, 12, 22, 28], "eegclassifi": [3, 4, 72], "eegconform": 95, "eeginceptionerp": 97, "eeginceptionmi": 98, "eegitnet": 96, "eegmodulemixin": 99, "eegnetv1": 101, "eegnetv4": 102, "eegnex": 100, "eegregressor": 132, "eegresnet": 103, "eegsimpleconv": 104, "eegtcnet": 105, "eldele2021": 10, "enhanc": 154, "epoch": 26, "etc": [29, 32], "evalu": [29, 31, 32], "examin": 26, "exampl": [3, 4, 5, 7, 12, 17, 18, 19, 20, 21, 24, 26, 27, 28, 29, 30, 32, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 76, 78, 80, 81, 82, 84, 85, 86, 87, 93, 99, 109, 111, 112, 116, 117, 122, 125, 126, 127, 129, 131, 134, 135, 136, 137, 138, 139, 141, 145, 147], "explor": [22, 26], "exponential_moving_demean": 128, "exponential_moving_standard": 129, "extract": [3, 4, 5, 9, 10, 11, 28, 29, 30], "fake": 31, "faq": 148, "filter": 120, "filterbank": 130, "find": 26, "finger": [2, 8], "first": 29, "fit": 4, "flexion": [2, 8], "fold": 29, "found": 148, "frequency_shift": 61, "frequencyshift": 43, "frequent": 148, "from": [151, 152], "ft_surrog": 62, "ftsurrog": 42, "function": [29, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71], "gaussian_nois": 63, "gaussiannois": 44, "gener": 31, "get": [30, 148], "github": 152, "gpu": 31, "help": 148, "hgd": 77, "homepag": 149, "hospit": 22, "how": [29, 32, 35, 148], "hybridnet": 106, "hyperparamet": [29, 30], "i": [29, 32, 148, 152], "ident": 64, "identitytransform": 45, "index": 21, "inform": 21, "inspect": 5, "instal": [150, 151, 152], "iv": [2, 3, 4, 8, 27], "k": 29, "labram": 107, "lazi": 14, "learn": [5, 26, 30], "let": 29, "level": 3, "lightn": 32, "list": 4, "load": [2, 3, 4, 5, 8, 9, 10, 11, 14, 15, 18, 21, 24, 26, 27, 28, 29, 30, 32], "load_concat_dataset": 87, "loop": 32, "manipul": 3, "manual": 3, "mask_encod": 65, "maskencod": 46, "matrix": [27, 28], "mixup": [47, 66], "mixup_criterion": 142, "mne": [19, 26, 35], "moabb": 20, "moabbdataset": 78, "model": [0, 2, 3, 4, 5, 8, 9, 10, 11, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117], "multipl": 22, "need": 30, "network": [1, 9, 11, 24, 30, 31], "neural": [1, 24, 30, 31], "new": 154, "nmt": 79, "observ": 21, "offlin": 32, "one": 3, "onlin": 26, "option": [29, 32], "organ": [15, 24], "other": 35, "own": 26, "parallel": 16, "paramet": 27, "perform": 5, "physionet": [9, 10, 11], "pick": 121, "plot": [2, 4, 8, 9, 10, 11, 27, 28, 30], "plot_confusion_matrix": 147, "posit": 5, "postepochtrainscor": 140, "predict_tri": 143, "prepar": [2, 8, 28], "preprocess": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 32, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131], "preprocessor": 122, "pretext": 5, "process": 12, "processor": 31, "pure": 32, "pypi": 151, "python": 148, "pytorch": 32, "question": 148, "raw": [5, 32], "real": [7, 24], "record": [5, 12], "recordingsampl": 134, "refer": [0, 4, 5, 9, 10, 11, 26, 27, 28, 29, 30, 31, 148], "regress": 31, "regressor": [0, 132], "rel": 5, "relativepositioningsampl": 135, "repositori": 152, "represent": 5, "resampl": 123, "resourc": 12, "result": [2, 4, 5, 8, 9, 10, 11, 27, 28, 30], "row": 21, "sampler": [0, 5, 9, 10, 11, 133, 134, 135, 136], "save": 18, "save_concat_dataset": 88, "scikit": [26, 30], "search": 4, "second": 29, "segmentation_reconstruct": 67, "segmentationreconstruct": 48, "select": 12, "self": 5, "sensors_rot": 68, "sensorsrot": 49, "sensorsxrot": 50, "sensorsyrot": 51, "sensorszrot": 52, "sequenc": [9, 10, 11], "sequencesampl": 136, "serial": 16, "session": 3, "set": [3, 5, 28], "set_random_se": 145, "seteegrefer": 124, "shallowfbcspnet": 109, "should": [29, 32], "sign_flip": 69, "signflip": 53, "simpl": [26, 29], "sleep": [5, 9, 10, 11], "sleepphysionet": 80, "sleepstagerblanco2020": 110, "sleepstagerchambon2018": 111, "sleepstagereldele2021": 112, "smooth_time_mask": 70, "smoothtimemask": 54, "sourc": 152, "sparcnet": 108, "split": [2, 3, 4, 5, 8, 9, 10, 11, 21, 27, 28, 29, 30, 32], "stage": [5, 9, 10, 11], "step": 12, "still": 148, "strategi": [1, 24], "structur": 32, "summari": [74, 77], "supervis": 5, "syncnet": 113, "t": 148, "target": 22, "task": 5, "tcn": 114, "templ": 22, "test": [2, 5, 8, 29, 31, 32, 152], "thi": [3, 4, 5, 12, 21, 26, 27, 28, 29, 30, 32], "think": 148, "third": 29, "tidnet": 115, "time": [6, 13, 23, 33, 34, 153], "time_revers": 71, "timedistribut": 116, "timerevers": 55, "timeseriesloss": 141, "train": [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 137, 138, 139, 140, 141, 142, 143, 144], "transform": [3, 4, 32, 56], "trial_preds_from_window_pr": 144, "tuh": [12, 22, 81], "tuhabnorm": 82, "tuhmock": 12, "tune": [29, 30], "u": 11, "univers": 22, "us": [5, 9, 10, 11, 12, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 76, 78, 80, 81, 82, 84, 85, 86, 87, 93, 99, 109, 111, 112, 116, 117, 122, 125, 126, 127, 129, 131, 134, 135, 136, 137, 138, 139, 141, 145, 147], "usleep": 117, "util": [0, 29, 145], "val": 29, "valid": [3, 4, 5, 8, 9, 10, 11, 28, 29, 30], "version": 154, "visual": [0, 3, 5, 29, 146, 147], "want": 26, "what": [148, 154], "why": [29, 30, 32], "window": [2, 3, 4, 5, 8, 9, 10, 11, 12, 22, 27, 28, 29, 30, 31, 32], "windowsdataset": 83, "work": [148, 152], "world": [7, 24], "you": [26, 30], "your": [26, 29, 32, 152]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"API Reference": [[0, null]], "API changes": [[153, "api-changes"], [153, "id3"], [153, "id6"], [153, "id9"], [153, "id12"]], "Advanced neural network training strategies": [[1, null], [24, "advanced-neural-network-training-strategies"]], "Analysing the best fit": [[4, "analysing-the-best-fit"]], "Applied examples on real-world datasets": [[7, null], [24, "applied-examples-on-real-world-datasets"]], "Augmentation": [[0, "augmentation"]], "Authors": [[153, "authors"]], "Basic Brain Decoding on EEG Data": [[28, null]], "Basic model building and training": [[24, "basic-model-building-and-training"], [25, null]], "Benchmarking eager and lazy loading": [[14, null]], "Benchmarking preprocessing with parallelization and serialization": [[16, null]], "Braindecode Homepage": [[148, null]], "Bugs": [[153, "bugs"], [153, "id2"], [153, "id5"], [153, "id8"], [153, "id11"]], "By description information": [[21, "by-description-information"]], "By row index": [[21, "by-row-index"]], "Choosing between GPU and CPU processors": [[31, "choosing-between-gpu-and-cpu-processors"]], "Citing other algorithms": [[35, "citing-other-algorithms"]], "Citing the Braindecode": [[35, "citing-the-braindecode"]], "Citing the MNE": [[35, "citing-the-mne"]], "Classifier": [[0, "classifier"]], "Clone the repository from GitHub": [[151, "clone-the-repository-from-github"]], "Combining preprocessing steps": [[12, "combining-preprocessing-steps"]], "Computation times": [[6, null], [13, null], [23, null], [33, null], [34, null], [152, null]], "Conclusion": [[5, "conclusion"]], "Convolutional neural network regression model on fake data.": [[31, null]], "Create Pytorch model": [[32, "create-pytorch-model"]], "Create an EEGClassifier with the desired augmentation": [[3, "create-an-eegclassifier-with-the-desired-augmentation"], [4, "create-an-eegclassifier-with-the-desired-augmentation"]], "Create model": [[2, "create-model"], [3, "create-model"], [4, "create-model"], [8, "create-model"], [9, "create-model"], [10, "create-model"], [11, "create-model"], [29, "create-model"], [30, "create-model"]], "Create model and compute windowing parameters": [[27, "create-model-and-compute-windowing-parameters"]], "Create sequence samplers": [[9, "create-sequence-samplers"], [10, "create-sequence-samplers"], [11, "create-sequence-samplers"]], "Creating Temple University Hospital (TUH) EEG Corpus Dataset": [[22, "creating-temple-university-hospital-tuh-eeg-corpus-dataset"]], "Creating Windows": [[22, "creating-windows"]], "Creating a model": [[28, "creating-a-model"]], "Creating samplers": [[5, "creating-samplers"]], "Creating the dataset using TUHMock": [[12, "creating-the-dataset-using-tuhmock"]], "Creating the model": [[5, "creating-the-model"]], "Cropped Decoding on BCIC IV 2a Dataset": [[27, null]], "Current 0.7 (10-2022)": [[153, "current-0-7-10-2022"]], "Current 0.8 (11-2022)": [[153, "current-0-8-11-2022"]], "Current 0.9 (dev0)": [[153, "current-0-9-dev0"]], "Custom Dataset Example": [[17, null]], "Cut Compute Windows": [[2, "cut-compute-windows"], [8, "cut-compute-windows"], [12, "cut-compute-windows"], [32, "cut-compute-windows"]], "Cut the data into windows": [[27, "cut-the-data-into-windows"]], "Data Augmentation": [[4, null]], "Data Augmentation on BCIC IV 2a Dataset": [[3, null]], "Data Utils": [[0, "data-utils"]], "Data windowing": [[31, "data-windowing"]], "DataLoader for Model Training": [[22, "dataloader-for-model-training"]], "Dataset summary": [[74, null], [77, null]], "Datasets": [[0, "datasets"]], "Defining a CNN regression model": [[31, "defining-a-cnn-regression-model"]], "Defining a Transform": [[3, "defining-a-transform"]], "Defining a list of transforms": [[4, "defining-a-list-of-transforms"]], "Enhancements": [[153, "enhancements"], [153, "id1"], [153, "id4"], [153, "id7"], [153, "id10"]], "Examining the model": [[26, "examining-the-model"]], "Examples": [[24, null]], "Examples using braindecode.augmentation.AugmentedDataLoader": [[36, "examples-using-braindecode-augmentation-augmenteddataloader"]], "Examples using braindecode.augmentation.ChannelsDropout": [[38, "examples-using-braindecode-augmentation-channelsdropout"]], "Examples using braindecode.augmentation.Compose": [[41, "examples-using-braindecode-augmentation-compose"]], "Examples using braindecode.augmentation.FTSurrogate": [[42, "examples-using-braindecode-augmentation-ftsurrogate"]], "Examples using braindecode.augmentation.FrequencyShift": [[43, "examples-using-braindecode-augmentation-frequencyshift"]], "Examples using braindecode.augmentation.SignFlip": [[53, "examples-using-braindecode-augmentation-signflip"]], "Examples using braindecode.augmentation.SmoothTimeMask": [[54, "examples-using-braindecode-augmentation-smoothtimemask"]], "Examples using braindecode.augmentation.Transform": [[56, "examples-using-braindecode-augmentation-transform"]], "Examples using braindecode.datasets.BCICompetitionIVDataset4": [[73, "examples-using-braindecode-datasets-bcicompetitionivdataset4"]], "Examples using braindecode.datasets.BaseConcatDataset": [[75, "examples-using-braindecode-datasets-baseconcatdataset"]], "Examples using braindecode.datasets.BaseDataset": [[76, "examples-using-braindecode-datasets-basedataset"]], "Examples using braindecode.datasets.MOABBDataset": [[78, "examples-using-braindecode-datasets-moabbdataset"]], "Examples using braindecode.datasets.SleepPhysionet": [[80, "examples-using-braindecode-datasets-sleepphysionet"]], "Examples using braindecode.datasets.TUH": [[81, "examples-using-braindecode-datasets-tuh"]], "Examples using braindecode.datasets.TUHAbnormal": [[82, "examples-using-braindecode-datasets-tuhabnormal"]], "Examples using braindecode.datasets.create_from_X_y": [[84, "examples-using-braindecode-datasets-create-from-x-y"]], "Examples using braindecode.datasets.create_from_mne_epochs": [[85, "examples-using-braindecode-datasets-create-from-mne-epochs"]], "Examples using braindecode.datasets.create_from_mne_raw": [[86, "examples-using-braindecode-datasets-create-from-mne-raw"]], "Examples using braindecode.datautil.load_concat_dataset": [[87, "examples-using-braindecode-datautil-load-concat-dataset"]], "Examples using braindecode.models.Deep4Net": [[93, "examples-using-braindecode-models-deep4net"]], "Examples using braindecode.models.EEGModuleMixin": [[99, "examples-using-braindecode-models-eegmodulemixin"]], "Examples using braindecode.models.ShallowFBCSPNet": [[109, "examples-using-braindecode-models-shallowfbcspnet"]], "Examples using braindecode.models.SleepStagerChambon2018": [[111, "examples-using-braindecode-models-sleepstagerchambon2018"]], "Examples using braindecode.models.SleepStagerEldele2021": [[112, "examples-using-braindecode-models-sleepstagereldele2021"]], "Examples using braindecode.models.USleep": [[116, "examples-using-braindecode-models-usleep"]], "Examples using braindecode.preprocessing.Preprocessor": [[121, "examples-using-braindecode-preprocessing-preprocessor"]], "Examples using braindecode.preprocessing.create_fixed_length_windows": [[124, "examples-using-braindecode-preprocessing-create-fixed-length-windows"]], "Examples using braindecode.preprocessing.create_windows_from_events": [[125, "examples-using-braindecode-preprocessing-create-windows-from-events"]], "Examples using braindecode.preprocessing.create_windows_from_target_channels": [[126, "examples-using-braindecode-preprocessing-create-windows-from-target-channels"]], "Examples using braindecode.preprocessing.exponential_moving_standardize": [[128, "examples-using-braindecode-preprocessing-exponential-moving-standardize"]], "Examples using braindecode.preprocessing.preprocess": [[130, "examples-using-braindecode-preprocessing-preprocess"]], "Examples using braindecode.samplers.RecordingSampler": [[133, "examples-using-braindecode-samplers-recordingsampler"]], "Examples using braindecode.samplers.RelativePositioningSampler": [[134, "examples-using-braindecode-samplers-relativepositioningsampler"]], "Examples using braindecode.samplers.SequenceSampler": [[135, "examples-using-braindecode-samplers-sequencesampler"]], "Examples using braindecode.training.CroppedLoss": [[136, "examples-using-braindecode-training-croppedloss"]], "Examples using braindecode.training.CroppedTimeSeriesEpochScoring": [[137, "examples-using-braindecode-training-croppedtimeseriesepochscoring"]], "Examples using braindecode.training.CroppedTrialEpochScoring": [[138, "examples-using-braindecode-training-croppedtrialepochscoring"]], "Examples using braindecode.training.TimeSeriesLoss": [[140, "examples-using-braindecode-training-timeseriesloss"]], "Examples using braindecode.util.set_random_seeds": [[144, "examples-using-braindecode-util-set-random-seeds"]], "Examples using braindecode.visualization.plot_confusion_matrix": [[146, "examples-using-braindecode-visualization-plot-confusion-matrix"]], "Exploring Data": [[22, "exploring-data"]], "Exploring DataLoader": [[22, "exploring-dataloader"]], "Exploring Windows": [[22, "exploring-windows"]], "Exploring the braindecode online documentation": [[26, "exploring-the-braindecode-online-documentation"]], "Extract windows": [[9, "extract-windows"], [10, "extract-windows"], [11, "extract-windows"]], "Extracting Compute Windows": [[28, "extracting-compute-windows"]], "Extracting windows": [[3, "extracting-windows"], [4, "extracting-windows"], [5, "extracting-windows"]], "Extraction of the Compute Windows": [[30, "extraction-of-the-compute-windows"]], "Extraction of the Windows": [[29, "extraction-of-the-windows"], [30, "extraction-of-the-windows"]], "Fake regression data": [[31, "fake-regression-data"]], "Finding the model you want": [[26, "finding-the-model-you-want"]], "Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset": [[2, null]], "Fingers flexion decoding on BCIC IV 4 ECoG Dataset": [[8, null]], "Frequently Asked Questions (FAQ)": [[147, null]], "Generating fake regression dataset": [[31, "generating-fake-regression-dataset"]], "Get the best hyperparameters": [[30, "get-the-best-hyperparameters"]], "Help! I can\u2019t get Python and Braindecode working!": [[147, "help-i-can-t-get-python-and-braindecode-working"]], "How do I cite Braindecode?": [[147, "how-do-i-cite-braindecode"]], "How to cite Braindecode": [[35, null]], "How to train and evaluate your model": [[29, "how-to-train-and-evaluate-your-model"], [32, "how-to-train-and-evaluate-your-model"]], "How to train, test and tune your model?": [[29, null]], "How to tune your hyperparameters": [[29, "how-to-tune-your-hyperparameters"]], "Hyperparameter tuning with scikit-learn": [[30, null]], "I still can\u2019t get it to work!": [[147, "i-still-can-t-get-it-to-work"]], "I think I found a bug, what do I do?": [[147, "i-think-i-found-a-bug-what-do-i-do"]], "Inspecting pretext task performance": [[5, "inspecting-pretext-task-performance"]], "Installation": [[149, null]], "Installing Braindecode from the source": [[151, "installing-braindecode-from-the-source"]], "Installing from PyPI": [[150, null]], "Installing from sources": [[151, null]], "Let\u2019s visualize the first option with a util function.": [[29, "let-s-visualize-the-first-option-with-a-util-function"]], "Let\u2019s visualize the second option with a util function.": [[29, "let-s-visualize-the-second-option-with-a-util-function"]], "Let\u2019s visualize the third option with a util function.": [[29, "let-s-visualize-the-third-option-with-a-util-function"]], "Load and save dataset example": [[18, null]], "Loading": [[2, "loading"], [3, "loading"], [4, "loading"], [8, "loading"], [9, "loading"], [10, "loading"], [11, "loading"], [30, "loading"]], "Loading and organizing data": [[15, null], [24, "loading-and-organizing-data"]], "Loading and preparing the data": [[28, "loading-and-preparing-the-data"]], "Loading and preparing the dataset": [[2, "loading-and-preparing-the-dataset"], [8, "loading-and-preparing-the-dataset"]], "Loading and preprocessing of data, defining a model, etc.": [[29, "loading-and-preprocessing-of-data-defining-a-model-etc"]], "Loading and preprocessing the dataset": [[3, "loading-and-preprocessing-the-dataset"], [4, "loading-and-preprocessing-the-dataset"], [5, "loading-and-preprocessing-the-dataset"], [9, "loading-and-preprocessing-the-dataset"], [10, "loading-and-preprocessing-the-dataset"], [11, "loading-and-preprocessing-the-dataset"], [27, "loading-and-preprocessing-the-dataset"], [30, "loading-and-preprocessing-the-dataset"]], "Loading data": [[29, "loading-data"]], "Loading the Dataset Structure": [[32, "loading-the-dataset-structure"]], "Loading the dataset": [[21, "loading-the-dataset"], [28, "loading-the-dataset"]], "Loading the raw recordings": [[5, "loading-the-raw-recordings"]], "Loading your own data with MNE": [[26, "loading-your-own-data-with-mne"]], "Loading, preprocessing, defining a model, etc.": [[32, "loading-preprocessing-defining-a-model-etc"]], "MNE Dataset Example": [[19, null]], "MOABB Dataset Example": [[20, null]], "Manipulating one session and visualizing the transformed data": [[3, "manipulating-one-session-and-visualizing-the-transformed-data"]], "Manually composing Transforms": [[3, "manually-composing-transforms"]], "Model Training": [[28, "model-training"]], "Model evaluation": [[31, "model-evaluation"]], "Model testing": [[31, "model-testing"]], "Model training": [[31, "model-training"]], "Models": [[0, "models"]], "Multiple discrete targets with the TUH EEG Corpus": [[22, null]], "Observation": [[21, "observation"]], "Option 1: Pure PyTorch training loop": [[32, "option-1-pure-pytorch-training-loop"]], "Option 1: Simple Train-Test Split": [[29, "option-1-simple-train-test-split"]], "Option 1: Train-Val-Test Split": [[29, "option-1-train-val-test-split"]], "Option 2: Train it with PyTorch Lightning": [[32, "option-2-train-it-with-pytorch-lightning"]], "Option 2: Train-Val-Test Split": [[29, "option-2-train-val-test-split"]], "Option 2: k-Fold Cross Validation": [[29, "option-2-k-fold-cross-validation"]], "Option 3: k-Fold Cross Validation": [[29, "option-3-k-fold-cross-validation"]], "Plot Confusion Matrix": [[27, "plot-confusion-matrix"]], "Plot Results": [[2, "plot-results"], [8, "plot-results"], [27, "plot-results"]], "Plot results": [[4, "plot-results"], [9, "plot-results"], [10, "plot-results"], [11, "plot-results"]], "Plotting Results": [[28, "plotting-results"]], "Plotting a  Confusion Matrix": [[28, "plotting-a-confusion-matrix"]], "Plotting the results": [[30, "plotting-the-results"]], "Preprocessing": [[0, "preprocessing"], [2, "preprocessing"], [3, "preprocessing"], [4, "preprocessing"], [5, "preprocessing"], [8, "preprocessing"], [9, "preprocessing"], [10, "preprocessing"], [11, "preprocessing"], [12, "preprocessing"], [28, "preprocessing"], [30, "preprocessing"]], "Preprocessing data": [[29, "preprocessing-data"]], "Preprocessing windows": [[5, "preprocessing-windows"]], "Preprocessing, the offline transformation of the raw dataset": [[32, "preprocessing-the-offline-transformation-of-the-raw-dataset"]], "Process a big data EEG resource (TUH EEG Corpus)": [[12, null]], "References": [[4, "references"], [5, "references"], [9, "references"], [10, "references"], [11, "references"], [26, "references"], [27, "references"], [28, "references"], [29, "references"], [30, "references"], [31, "references"], [147, "references"]], "Regressor": [[0, "regressor"]], "Samplers": [[0, "samplers"]], "Searching the best data augmentation on BCIC IV 2a Dataset": [[4, null]], "Selecting recordings": [[12, "selecting-recordings"]], "Self-supervised learning": [[5, null]], "Self-supervised learning on EEG with relative positioning": [[5, null]], "Setting the data augmentation at the Dataset level": [[3, "setting-the-data-augmentation-at-the-dataset-level"]], "Simple training on MNE epochs": [[26, null]], "Sleep staging on the Sleep Physionet dataset using Chambon2018 network": [[9, null]], "Sleep staging on the Sleep Physionet dataset using Eldele2021": [[10, null]], "Sleep staging on the Sleep Physionet dataset using U-Sleep network": [[11, null]], "Split Dataset Example": [[21, null]], "Split dataset into train and test": [[2, "split-dataset-into-train-and-test"], [29, "split-dataset-into-train-and-test"], [32, "split-dataset-into-train-and-test"]], "Split dataset into train and valid": [[3, "split-dataset-into-train-and-valid"], [4, "split-dataset-into-train-and-valid"], [9, "split-dataset-into-train-and-valid"], [10, "split-dataset-into-train-and-valid"], [11, "split-dataset-into-train-and-valid"], [30, "split-dataset-into-train-and-valid"]], "Split dataset into train, valid, and test": [[8, "split-dataset-into-train-valid-and-test"]], "Split the dataset": [[27, "split-the-dataset"]], "Splitting": [[21, "splitting"]], "Splitting dataset into train, valid and test sets": [[5, "splitting-dataset-into-train-valid-and-test-sets"]], "Splitting the dataset into training and validation sets": [[28, "splitting-the-dataset-into-training-and-validation-sets"]], "Testing if your installation is working": [[151, "testing-if-your-installation-is-working"]], "This example covers:": [[3, "this-example-covers"], [4, "this-example-covers"], [5, "this-example-covers"], [12, "this-example-covers"], [21, "this-example-covers"], [26, "this-example-covers"], [27, "this-example-covers"], [28, "this-example-covers"], [29, "this-example-covers"], [30, "this-example-covers"], [32, "this-example-covers"]], "Training": [[0, "training"], [2, "training"], [5, "training"], [8, "training"], [9, "training"], [10, "training"], [11, "training"], [27, "training"], [30, "training"]], "Training a Braindecode model in PyTorch": [[32, null]], "Training a model with data augmentation": [[3, "training-a-model-with-data-augmentation"], [4, "training-a-model-with-data-augmentation"]], "Training your model (scikit-learn compatible)": [[26, "training-your-model-scikit-learn-compatible"]], "Using the learned representation for sleep staging": [[5, "using-the-learned-representation-for-sleep-staging"]], "Utils": [[0, "utils"]], "Version 0.5.1 (2021-07-14)": [[153, "version-0-5-1-2021-07-14"]], "Version 0.6 (2021-12-06)": [[153, "version-0-6-2021-12-06"]], "Visualization": [[0, "visualization"]], "Visualizing the results": [[5, "visualizing-the-results"]], "What\u2019s new": [[153, null]], "Why do you need to tune the neural networks model?": [[30, null]], "Why should I care about model evaluation?": [[29, "why-should-i-care-about-model-evaluation"], [32, "why-should-i-care-about-model-evaluation"]], "Window preprocessing": [[9, "window-preprocessing"], [10, "window-preprocessing"]], "braindecode.augmentation.AugmentedDataLoader": [[36, null]], "braindecode.augmentation.BandstopFilter": [[37, null]], "braindecode.augmentation.ChannelsDropout": [[38, null]], "braindecode.augmentation.ChannelsShuffle": [[39, null]], "braindecode.augmentation.ChannelsSymmetry": [[40, null]], "braindecode.augmentation.Compose": [[41, null]], "braindecode.augmentation.FTSurrogate": [[42, null]], "braindecode.augmentation.FrequencyShift": [[43, null]], "braindecode.augmentation.GaussianNoise": [[44, null]], "braindecode.augmentation.IdentityTransform": [[45, null]], "braindecode.augmentation.MaskEncoding": [[46, null]], "braindecode.augmentation.Mixup": [[47, null]], "braindecode.augmentation.SegmentationReconstruction": [[48, null]], "braindecode.augmentation.SensorsRotation": [[49, null]], "braindecode.augmentation.SensorsXRotation": [[50, null]], "braindecode.augmentation.SensorsYRotation": [[51, null]], "braindecode.augmentation.SensorsZRotation": [[52, null]], "braindecode.augmentation.SignFlip": [[53, null]], "braindecode.augmentation.SmoothTimeMask": [[54, null]], "braindecode.augmentation.TimeReverse": [[55, null]], "braindecode.augmentation.Transform": [[56, null]], "braindecode.augmentation.functional.bandstop_filter": [[57, null]], "braindecode.augmentation.functional.channels_dropout": [[58, null]], "braindecode.augmentation.functional.channels_permute": [[59, null]], "braindecode.augmentation.functional.channels_shuffle": [[60, null]], "braindecode.augmentation.functional.frequency_shift": [[61, null]], "braindecode.augmentation.functional.ft_surrogate": [[62, null]], "braindecode.augmentation.functional.gaussian_noise": [[63, null]], "braindecode.augmentation.functional.identity": [[64, null]], "braindecode.augmentation.functional.mask_encoding": [[65, null]], "braindecode.augmentation.functional.mixup": [[66, null]], "braindecode.augmentation.functional.segmentation_reconstruction": [[67, null]], "braindecode.augmentation.functional.sensors_rotation": [[68, null]], "braindecode.augmentation.functional.sign_flip": [[69, null]], "braindecode.augmentation.functional.smooth_time_mask": [[70, null]], "braindecode.augmentation.functional.time_reverse": [[71, null]], "braindecode.classifier.EEGClassifier": [[72, null]], "braindecode.datasets.BCICompetitionIVDataset4": [[73, null]], "braindecode.datasets.BNCI2014001": [[74, null]], "braindecode.datasets.BaseConcatDataset": [[75, null]], "braindecode.datasets.BaseDataset": [[76, null]], "braindecode.datasets.HGD": [[77, null]], "braindecode.datasets.MOABBDataset": [[78, null]], "braindecode.datasets.NMT": [[79, null]], "braindecode.datasets.SleepPhysionet": [[80, null]], "braindecode.datasets.TUH": [[81, null]], "braindecode.datasets.TUHAbnormal": [[82, null]], "braindecode.datasets.WindowsDataset": [[83, null]], "braindecode.datasets.create_from_X_y": [[84, null]], "braindecode.datasets.create_from_mne_epochs": [[85, null]], "braindecode.datasets.create_from_mne_raw": [[86, null]], "braindecode.datautil.load_concat_dataset": [[87, null]], "braindecode.datautil.save_concat_dataset": [[88, null]], "braindecode.models.ATCNet": [[89, null]], "braindecode.models.AttentionBaseNet": [[90, null]], "braindecode.models.BIOT": [[91, null]], "braindecode.models.ContraWR": [[92, null]], "braindecode.models.Deep4Net": [[93, null]], "braindecode.models.DeepSleepNet": [[94, null]], "braindecode.models.EEGConformer": [[95, null]], "braindecode.models.EEGITNet": [[96, null]], "braindecode.models.EEGInceptionERP": [[97, null]], "braindecode.models.EEGInceptionMI": [[98, null]], "braindecode.models.EEGModuleMixin": [[99, null]], "braindecode.models.EEGNeX": [[100, null]], "braindecode.models.EEGNetv1": [[101, null]], "braindecode.models.EEGNetv4": [[102, null]], "braindecode.models.EEGResNet": [[103, null]], "braindecode.models.EEGSimpleConv": [[104, null]], "braindecode.models.EEGTCNet": [[105, null]], "braindecode.models.HybridNet": [[106, null]], "braindecode.models.Labram": [[107, null]], "braindecode.models.SPARCNet": [[108, null]], "braindecode.models.ShallowFBCSPNet": [[109, null]], "braindecode.models.SleepStagerBlanco2020": [[110, null]], "braindecode.models.SleepStagerChambon2018": [[111, null]], "braindecode.models.SleepStagerEldele2021": [[112, null]], "braindecode.models.SyncNet": [[113, null]], "braindecode.models.TCN": [[114, null]], "braindecode.models.TIDNet": [[115, null]], "braindecode.models.USleep": [[116, null]], "braindecode.preprocessing.Crop": [[117, null]], "braindecode.preprocessing.DropChannels": [[118, null]], "braindecode.preprocessing.Filter": [[119, null]], "braindecode.preprocessing.Pick": [[120, null]], "braindecode.preprocessing.Preprocessor": [[121, null]], "braindecode.preprocessing.Resample": [[122, null]], "braindecode.preprocessing.SetEEGReference": [[123, null]], "braindecode.preprocessing.create_fixed_length_windows": [[124, null]], "braindecode.preprocessing.create_windows_from_events": [[125, null]], "braindecode.preprocessing.create_windows_from_target_channels": [[126, null]], "braindecode.preprocessing.exponential_moving_demean": [[127, null]], "braindecode.preprocessing.exponential_moving_standardize": [[128, null]], "braindecode.preprocessing.filterbank": [[129, null]], "braindecode.preprocessing.preprocess": [[130, null]], "braindecode.regressor.EEGRegressor": [[131, null]], "braindecode.samplers.BalancedSequenceSampler": [[132, null]], "braindecode.samplers.RecordingSampler": [[133, null]], "braindecode.samplers.RelativePositioningSampler": [[134, null]], "braindecode.samplers.SequenceSampler": [[135, null]], "braindecode.training.CroppedLoss": [[136, null]], "braindecode.training.CroppedTimeSeriesEpochScoring": [[137, null]], "braindecode.training.CroppedTrialEpochScoring": [[138, null]], "braindecode.training.PostEpochTrainScoring": [[139, null]], "braindecode.training.TimeSeriesLoss": [[140, null]], "braindecode.training.mixup_criterion": [[141, null]], "braindecode.training.predict_trials": [[142, null]], "braindecode.training.trial_preds_from_window_preds": [[143, null]], "braindecode.util.set_random_seeds": [[144, null]], "braindecode.visualization.compute_amplitude_gradients": [[145, null]], "braindecode.visualization.plot_confusion_matrix": [[146, null]]}, "docnames": ["api", "auto_examples/advanced_training/index", "auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped", "auto_examples/advanced_training/plot_data_augmentation", "auto_examples/advanced_training/plot_data_augmentation_search", "auto_examples/advanced_training/plot_relative_positioning", "auto_examples/advanced_training/sg_execution_times", "auto_examples/applied_examples/index", "auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial", "auto_examples/applied_examples/plot_sleep_staging_chambon2018", "auto_examples/applied_examples/plot_sleep_staging_eldele2021", "auto_examples/applied_examples/plot_sleep_staging_usleep", "auto_examples/applied_examples/plot_tuh_eeg_corpus", "auto_examples/applied_examples/sg_execution_times", "auto_examples/datasets_io/benchmark_lazy_eager_loading", "auto_examples/datasets_io/index", "auto_examples/datasets_io/plot_benchmark_preprocessing", "auto_examples/datasets_io/plot_custom_dataset_example", "auto_examples/datasets_io/plot_load_save_datasets", "auto_examples/datasets_io/plot_mne_dataset_example", "auto_examples/datasets_io/plot_moabb_dataset_example", "auto_examples/datasets_io/plot_split_dataset", "auto_examples/datasets_io/plot_tuh_discrete_multitarget", "auto_examples/datasets_io/sg_execution_times", "auto_examples/index", "auto_examples/model_building/index", "auto_examples/model_building/plot_basic_training_epochs", "auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped", "auto_examples/model_building/plot_bcic_iv_2a_moabb_trial", "auto_examples/model_building/plot_how_train_test_and_tune", "auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn", "auto_examples/model_building/plot_regression", "auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning", "auto_examples/model_building/sg_execution_times", "auto_examples/sg_execution_times", "cite", "generated/braindecode.augmentation.AugmentedDataLoader", "generated/braindecode.augmentation.BandstopFilter", "generated/braindecode.augmentation.ChannelsDropout", "generated/braindecode.augmentation.ChannelsShuffle", "generated/braindecode.augmentation.ChannelsSymmetry", "generated/braindecode.augmentation.Compose", "generated/braindecode.augmentation.FTSurrogate", "generated/braindecode.augmentation.FrequencyShift", "generated/braindecode.augmentation.GaussianNoise", "generated/braindecode.augmentation.IdentityTransform", "generated/braindecode.augmentation.MaskEncoding", "generated/braindecode.augmentation.Mixup", "generated/braindecode.augmentation.SegmentationReconstruction", "generated/braindecode.augmentation.SensorsRotation", "generated/braindecode.augmentation.SensorsXRotation", "generated/braindecode.augmentation.SensorsYRotation", "generated/braindecode.augmentation.SensorsZRotation", "generated/braindecode.augmentation.SignFlip", "generated/braindecode.augmentation.SmoothTimeMask", "generated/braindecode.augmentation.TimeReverse", "generated/braindecode.augmentation.Transform", "generated/braindecode.augmentation.functional.bandstop_filter", "generated/braindecode.augmentation.functional.channels_dropout", "generated/braindecode.augmentation.functional.channels_permute", "generated/braindecode.augmentation.functional.channels_shuffle", "generated/braindecode.augmentation.functional.frequency_shift", "generated/braindecode.augmentation.functional.ft_surrogate", "generated/braindecode.augmentation.functional.gaussian_noise", "generated/braindecode.augmentation.functional.identity", "generated/braindecode.augmentation.functional.mask_encoding", "generated/braindecode.augmentation.functional.mixup", "generated/braindecode.augmentation.functional.segmentation_reconstruction", "generated/braindecode.augmentation.functional.sensors_rotation", "generated/braindecode.augmentation.functional.sign_flip", "generated/braindecode.augmentation.functional.smooth_time_mask", "generated/braindecode.augmentation.functional.time_reverse", "generated/braindecode.classifier.EEGClassifier", "generated/braindecode.datasets.BCICompetitionIVDataset4", "generated/braindecode.datasets.BNCI2014001", "generated/braindecode.datasets.BaseConcatDataset", "generated/braindecode.datasets.BaseDataset", "generated/braindecode.datasets.HGD", "generated/braindecode.datasets.MOABBDataset", "generated/braindecode.datasets.NMT", "generated/braindecode.datasets.SleepPhysionet", "generated/braindecode.datasets.TUH", "generated/braindecode.datasets.TUHAbnormal", "generated/braindecode.datasets.WindowsDataset", "generated/braindecode.datasets.create_from_X_y", "generated/braindecode.datasets.create_from_mne_epochs", "generated/braindecode.datasets.create_from_mne_raw", "generated/braindecode.datautil.load_concat_dataset", "generated/braindecode.datautil.save_concat_dataset", "generated/braindecode.models.ATCNet", "generated/braindecode.models.AttentionBaseNet", "generated/braindecode.models.BIOT", "generated/braindecode.models.ContraWR", "generated/braindecode.models.Deep4Net", "generated/braindecode.models.DeepSleepNet", "generated/braindecode.models.EEGConformer", "generated/braindecode.models.EEGITNet", "generated/braindecode.models.EEGInceptionERP", "generated/braindecode.models.EEGInceptionMI", "generated/braindecode.models.EEGModuleMixin", "generated/braindecode.models.EEGNeX", "generated/braindecode.models.EEGNetv1", "generated/braindecode.models.EEGNetv4", "generated/braindecode.models.EEGResNet", "generated/braindecode.models.EEGSimpleConv", "generated/braindecode.models.EEGTCNet", "generated/braindecode.models.HybridNet", "generated/braindecode.models.Labram", "generated/braindecode.models.SPARCNet", "generated/braindecode.models.ShallowFBCSPNet", "generated/braindecode.models.SleepStagerBlanco2020", "generated/braindecode.models.SleepStagerChambon2018", "generated/braindecode.models.SleepStagerEldele2021", "generated/braindecode.models.SyncNet", "generated/braindecode.models.TCN", "generated/braindecode.models.TIDNet", "generated/braindecode.models.USleep", "generated/braindecode.preprocessing.Crop", "generated/braindecode.preprocessing.DropChannels", "generated/braindecode.preprocessing.Filter", "generated/braindecode.preprocessing.Pick", "generated/braindecode.preprocessing.Preprocessor", "generated/braindecode.preprocessing.Resample", "generated/braindecode.preprocessing.SetEEGReference", "generated/braindecode.preprocessing.create_fixed_length_windows", "generated/braindecode.preprocessing.create_windows_from_events", "generated/braindecode.preprocessing.create_windows_from_target_channels", "generated/braindecode.preprocessing.exponential_moving_demean", "generated/braindecode.preprocessing.exponential_moving_standardize", "generated/braindecode.preprocessing.filterbank", "generated/braindecode.preprocessing.preprocess", "generated/braindecode.regressor.EEGRegressor", "generated/braindecode.samplers.BalancedSequenceSampler", "generated/braindecode.samplers.RecordingSampler", "generated/braindecode.samplers.RelativePositioningSampler", "generated/braindecode.samplers.SequenceSampler", "generated/braindecode.training.CroppedLoss", "generated/braindecode.training.CroppedTimeSeriesEpochScoring", "generated/braindecode.training.CroppedTrialEpochScoring", "generated/braindecode.training.PostEpochTrainScoring", "generated/braindecode.training.TimeSeriesLoss", "generated/braindecode.training.mixup_criterion", "generated/braindecode.training.predict_trials", "generated/braindecode.training.trial_preds_from_window_preds", "generated/braindecode.util.set_random_seeds", "generated/braindecode.visualization.compute_amplitude_gradients", "generated/braindecode.visualization.plot_confusion_matrix", "help", "index", "install/install", "install/install_pip", "install/install_source", "sg_execution_times", "whats_new"], "envversion": {"sphinx": 62, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.todo": 2}, "filenames": ["api.rst", "auto_examples/advanced_training/index.rst", "auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.rst", "auto_examples/advanced_training/plot_data_augmentation.rst", "auto_examples/advanced_training/plot_data_augmentation_search.rst", "auto_examples/advanced_training/plot_relative_positioning.rst", "auto_examples/advanced_training/sg_execution_times.rst", "auto_examples/applied_examples/index.rst", "auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.rst", "auto_examples/applied_examples/plot_sleep_staging_chambon2018.rst", "auto_examples/applied_examples/plot_sleep_staging_eldele2021.rst", "auto_examples/applied_examples/plot_sleep_staging_usleep.rst", "auto_examples/applied_examples/plot_tuh_eeg_corpus.rst", "auto_examples/applied_examples/sg_execution_times.rst", "auto_examples/datasets_io/benchmark_lazy_eager_loading.rst", "auto_examples/datasets_io/index.rst", "auto_examples/datasets_io/plot_benchmark_preprocessing.rst", "auto_examples/datasets_io/plot_custom_dataset_example.rst", "auto_examples/datasets_io/plot_load_save_datasets.rst", "auto_examples/datasets_io/plot_mne_dataset_example.rst", "auto_examples/datasets_io/plot_moabb_dataset_example.rst", "auto_examples/datasets_io/plot_split_dataset.rst", "auto_examples/datasets_io/plot_tuh_discrete_multitarget.rst", "auto_examples/datasets_io/sg_execution_times.rst", "auto_examples/index.rst", "auto_examples/model_building/index.rst", "auto_examples/model_building/plot_basic_training_epochs.rst", "auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.rst", "auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.rst", "auto_examples/model_building/plot_how_train_test_and_tune.rst", "auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.rst", "auto_examples/model_building/plot_regression.rst", "auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.rst", "auto_examples/model_building/sg_execution_times.rst", "auto_examples/sg_execution_times.rst", "cite.rst", "generated/braindecode.augmentation.AugmentedDataLoader.rst", "generated/braindecode.augmentation.BandstopFilter.rst", "generated/braindecode.augmentation.ChannelsDropout.rst", "generated/braindecode.augmentation.ChannelsShuffle.rst", "generated/braindecode.augmentation.ChannelsSymmetry.rst", "generated/braindecode.augmentation.Compose.rst", "generated/braindecode.augmentation.FTSurrogate.rst", "generated/braindecode.augmentation.FrequencyShift.rst", "generated/braindecode.augmentation.GaussianNoise.rst", "generated/braindecode.augmentation.IdentityTransform.rst", "generated/braindecode.augmentation.MaskEncoding.rst", "generated/braindecode.augmentation.Mixup.rst", "generated/braindecode.augmentation.SegmentationReconstruction.rst", "generated/braindecode.augmentation.SensorsRotation.rst", "generated/braindecode.augmentation.SensorsXRotation.rst", "generated/braindecode.augmentation.SensorsYRotation.rst", "generated/braindecode.augmentation.SensorsZRotation.rst", "generated/braindecode.augmentation.SignFlip.rst", "generated/braindecode.augmentation.SmoothTimeMask.rst", "generated/braindecode.augmentation.TimeReverse.rst", "generated/braindecode.augmentation.Transform.rst", "generated/braindecode.augmentation.functional.bandstop_filter.rst", "generated/braindecode.augmentation.functional.channels_dropout.rst", "generated/braindecode.augmentation.functional.channels_permute.rst", "generated/braindecode.augmentation.functional.channels_shuffle.rst", "generated/braindecode.augmentation.functional.frequency_shift.rst", "generated/braindecode.augmentation.functional.ft_surrogate.rst", "generated/braindecode.augmentation.functional.gaussian_noise.rst", "generated/braindecode.augmentation.functional.identity.rst", "generated/braindecode.augmentation.functional.mask_encoding.rst", "generated/braindecode.augmentation.functional.mixup.rst", "generated/braindecode.augmentation.functional.segmentation_reconstruction.rst", "generated/braindecode.augmentation.functional.sensors_rotation.rst", "generated/braindecode.augmentation.functional.sign_flip.rst", "generated/braindecode.augmentation.functional.smooth_time_mask.rst", "generated/braindecode.augmentation.functional.time_reverse.rst", "generated/braindecode.classifier.EEGClassifier.rst", "generated/braindecode.datasets.BCICompetitionIVDataset4.rst", "generated/braindecode.datasets.BNCI2014001.rst", "generated/braindecode.datasets.BaseConcatDataset.rst", "generated/braindecode.datasets.BaseDataset.rst", "generated/braindecode.datasets.HGD.rst", "generated/braindecode.datasets.MOABBDataset.rst", "generated/braindecode.datasets.NMT.rst", "generated/braindecode.datasets.SleepPhysionet.rst", "generated/braindecode.datasets.TUH.rst", "generated/braindecode.datasets.TUHAbnormal.rst", "generated/braindecode.datasets.WindowsDataset.rst", "generated/braindecode.datasets.create_from_X_y.rst", "generated/braindecode.datasets.create_from_mne_epochs.rst", "generated/braindecode.datasets.create_from_mne_raw.rst", "generated/braindecode.datautil.load_concat_dataset.rst", "generated/braindecode.datautil.save_concat_dataset.rst", "generated/braindecode.models.ATCNet.rst", "generated/braindecode.models.AttentionBaseNet.rst", "generated/braindecode.models.BIOT.rst", "generated/braindecode.models.ContraWR.rst", "generated/braindecode.models.Deep4Net.rst", "generated/braindecode.models.DeepSleepNet.rst", "generated/braindecode.models.EEGConformer.rst", "generated/braindecode.models.EEGITNet.rst", "generated/braindecode.models.EEGInceptionERP.rst", "generated/braindecode.models.EEGInceptionMI.rst", "generated/braindecode.models.EEGModuleMixin.rst", "generated/braindecode.models.EEGNeX.rst", "generated/braindecode.models.EEGNetv1.rst", "generated/braindecode.models.EEGNetv4.rst", "generated/braindecode.models.EEGResNet.rst", "generated/braindecode.models.EEGSimpleConv.rst", "generated/braindecode.models.EEGTCNet.rst", "generated/braindecode.models.HybridNet.rst", "generated/braindecode.models.Labram.rst", "generated/braindecode.models.SPARCNet.rst", "generated/braindecode.models.ShallowFBCSPNet.rst", "generated/braindecode.models.SleepStagerBlanco2020.rst", "generated/braindecode.models.SleepStagerChambon2018.rst", "generated/braindecode.models.SleepStagerEldele2021.rst", "generated/braindecode.models.SyncNet.rst", "generated/braindecode.models.TCN.rst", "generated/braindecode.models.TIDNet.rst", "generated/braindecode.models.USleep.rst", "generated/braindecode.preprocessing.Crop.rst", "generated/braindecode.preprocessing.DropChannels.rst", "generated/braindecode.preprocessing.Filter.rst", "generated/braindecode.preprocessing.Pick.rst", "generated/braindecode.preprocessing.Preprocessor.rst", "generated/braindecode.preprocessing.Resample.rst", "generated/braindecode.preprocessing.SetEEGReference.rst", "generated/braindecode.preprocessing.create_fixed_length_windows.rst", "generated/braindecode.preprocessing.create_windows_from_events.rst", "generated/braindecode.preprocessing.create_windows_from_target_channels.rst", "generated/braindecode.preprocessing.exponential_moving_demean.rst", "generated/braindecode.preprocessing.exponential_moving_standardize.rst", "generated/braindecode.preprocessing.filterbank.rst", "generated/braindecode.preprocessing.preprocess.rst", "generated/braindecode.regressor.EEGRegressor.rst", "generated/braindecode.samplers.BalancedSequenceSampler.rst", "generated/braindecode.samplers.RecordingSampler.rst", "generated/braindecode.samplers.RelativePositioningSampler.rst", "generated/braindecode.samplers.SequenceSampler.rst", "generated/braindecode.training.CroppedLoss.rst", "generated/braindecode.training.CroppedTimeSeriesEpochScoring.rst", "generated/braindecode.training.CroppedTrialEpochScoring.rst", "generated/braindecode.training.PostEpochTrainScoring.rst", "generated/braindecode.training.TimeSeriesLoss.rst", "generated/braindecode.training.mixup_criterion.rst", "generated/braindecode.training.predict_trials.rst", "generated/braindecode.training.trial_preds_from_window_preds.rst", "generated/braindecode.util.set_random_seeds.rst", "generated/braindecode.visualization.compute_amplitude_gradients.rst", "generated/braindecode.visualization.plot_confusion_matrix.rst", "help.rst", "index.rst", "install/install.rst", "install/install_pip.rst", "install/install_source.rst", "sg_execution_times.rst", "whats_new.rst"], "indexentries": {"_criteria (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier._criteria", false]], "_criteria (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor._criteria", false]], "_modules (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier._modules", false]], "_modules (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor._modules", false]], "_optimizers (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier._optimizers", false]], "_optimizers (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor._optimizers", false]], "apply() (braindecode.preprocessing.preprocessor method)": [[121, "braindecode.preprocessing.Preprocessor.apply", false]], "atcnet (class in braindecode.models)": [[89, "braindecode.models.ATCNet", false]], "attentionbasenet (class in braindecode.models)": [[90, "braindecode.models.AttentionBaseNet", false]], "augmenteddataloader (class in braindecode.augmentation)": [[36, "braindecode.augmentation.AugmentedDataLoader", false]], "balancedsequencesampler (class in braindecode.samplers)": [[132, "braindecode.samplers.BalancedSequenceSampler", false]], "bandstop_filter() (in module braindecode.augmentation.functional)": [[57, "braindecode.augmentation.functional.bandstop_filter", false]], "bandstopfilter (class in braindecode.augmentation)": [[37, "braindecode.augmentation.BandstopFilter", false]], "baseconcatdataset (class in braindecode.datasets)": [[75, "braindecode.datasets.BaseConcatDataset", false]], "basedataset (class in braindecode.datasets)": [[76, "braindecode.datasets.BaseDataset", false]], "bcicompetitionivdataset4 (class in braindecode.datasets)": [[73, "braindecode.datasets.BCICompetitionIVDataset4", false]], "biot (class in braindecode.models)": [[91, "braindecode.models.BIOT", false]], "bnci2014001 (class in braindecode.datasets)": [[74, "braindecode.datasets.BNCI2014001", false]], "braindecode": [[0, "module-braindecode", false]], "calc_padding() (braindecode.models.eegnex static method)": [[100, "braindecode.models.EEGNeX.calc_padding", false]], "callbacks_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.callbacks_", false]], "callbacks_ (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor.callbacks_", false]], "channels_dropout() (in module braindecode.augmentation.functional)": [[58, "braindecode.augmentation.functional.channels_dropout", false]], "channels_permute() (in module braindecode.augmentation.functional)": [[59, "braindecode.augmentation.functional.channels_permute", false]], "channels_shuffle() (in module braindecode.augmentation.functional)": [[60, "braindecode.augmentation.functional.channels_shuffle", false]], "channelsdropout (class in braindecode.augmentation)": [[38, "braindecode.augmentation.ChannelsDropout", false]], "channelsshuffle (class in braindecode.augmentation)": [[39, "braindecode.augmentation.ChannelsShuffle", false]], "channelssymmetry (class in braindecode.augmentation)": [[40, "braindecode.augmentation.ChannelsSymmetry", false]], "classes_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.classes_", false]], "compose (class in braindecode.augmentation)": [[41, "braindecode.augmentation.Compose", false]], "compute_amplitude_gradients() (in module braindecode.visualization)": [[145, "braindecode.visualization.compute_amplitude_gradients", false]], "contrawr (class in braindecode.models)": [[92, "braindecode.models.ContraWR", false]], "create_fixed_length_windows() (in module braindecode.preprocessing)": [[124, "braindecode.preprocessing.create_fixed_length_windows", false]], "create_from_mne_epochs() (in module braindecode.datasets)": [[85, "braindecode.datasets.create_from_mne_epochs", false]], "create_from_mne_raw() (in module braindecode.datasets)": [[86, "braindecode.datasets.create_from_mne_raw", false]], "create_from_x_y() (in module braindecode.datasets)": [[84, "braindecode.datasets.create_from_X_y", false]], "create_windows_from_events() (in module braindecode.preprocessing)": [[125, "braindecode.preprocessing.create_windows_from_events", false]], "create_windows_from_target_channels() (in module braindecode.preprocessing)": [[126, "braindecode.preprocessing.create_windows_from_target_channels", false]], "criterion_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.criterion_", false]], "criterion_ (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor.criterion_", false]], "crop (class in braindecode.preprocessing)": [[117, "braindecode.preprocessing.Crop", false]], "croppedloss (class in braindecode.training)": [[136, "braindecode.training.CroppedLoss", false]], "croppedtimeseriesepochscoring (class in braindecode.training)": [[137, "braindecode.training.CroppedTimeSeriesEpochScoring", false]], "croppedtrialepochscoring (class in braindecode.training)": [[138, "braindecode.training.CroppedTrialEpochScoring", false]], "cuda_dependent_attributes_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.cuda_dependent_attributes_", false]], "cuda_dependent_attributes_ (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor.cuda_dependent_attributes_", false]], "deep4net (class in braindecode.models)": [[93, "braindecode.models.Deep4Net", false]], "deepsleepnet (class in braindecode.models)": [[94, "braindecode.models.DeepSleepNet", false]], "download() (braindecode.datasets.bcicompetitionivdataset4 static method)": [[73, "braindecode.datasets.BCICompetitionIVDataset4.download", false]], "dropchannels (class in braindecode.preprocessing)": [[118, "braindecode.preprocessing.DropChannels", false]], "eegclassifier (class in braindecode.classifier)": [[72, "braindecode.classifier.EEGClassifier", false]], "eegconformer (class in braindecode.models)": [[95, "braindecode.models.EEGConformer", false]], "eeginceptionerp (class in braindecode.models)": [[97, "braindecode.models.EEGInceptionERP", false]], "eeginceptionmi (class in braindecode.models)": [[98, "braindecode.models.EEGInceptionMI", false]], "eegitnet (class in braindecode.models)": [[96, "braindecode.models.EEGITNet", false]], "eegmodulemixin (class in braindecode.models)": [[99, "braindecode.models.EEGModuleMixin", false]], "eegnetv1 (class in braindecode.models)": [[101, "braindecode.models.EEGNetv1", false]], "eegnetv4 (class in braindecode.models)": [[102, "braindecode.models.EEGNetv4", false]], "eegnex (class in braindecode.models)": [[100, "braindecode.models.EEGNeX", false]], "eegregressor (class in braindecode.regressor)": [[131, "braindecode.regressor.EEGRegressor", false]], "eegresnet (class in braindecode.models)": [[103, "braindecode.models.EEGResNet", false]], "eegsimpleconv (class in braindecode.models)": [[104, "braindecode.models.EEGSimpleConv", false]], "eegtcnet (class in braindecode.models)": [[105, "braindecode.models.EEGTCNet", false]], "exponential_moving_demean() (in module braindecode.preprocessing)": [[127, "braindecode.preprocessing.exponential_moving_demean", false]], "exponential_moving_standardize() (in module braindecode.preprocessing)": [[128, "braindecode.preprocessing.exponential_moving_standardize", false]], "file_ids (braindecode.samplers.sequencesampler attribute)": [[135, "braindecode.samplers.SequenceSampler.file_ids", false]], "filter (class in braindecode.preprocessing)": [[119, "braindecode.preprocessing.Filter", false]], "filterbank() (in module braindecode.preprocessing)": [[129, "braindecode.preprocessing.filterbank", false]], "fit() (braindecode.regressor.eegregressor method)": [[131, "braindecode.regressor.EEGRegressor.fit", false]], "fix_init_weight_and_init_embedding() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.fix_init_weight_and_init_embedding", false]], "forward() (braindecode.augmentation.compose method)": [[41, "braindecode.augmentation.Compose.forward", false]], "forward() (braindecode.augmentation.transform method)": [[56, "braindecode.augmentation.Transform.forward", false]], "forward() (braindecode.models.atcnet method)": [[89, "braindecode.models.ATCNet.forward", false]], "forward() (braindecode.models.attentionbasenet method)": [[90, "braindecode.models.AttentionBaseNet.forward", false]], "forward() (braindecode.models.biot method)": [[91, "braindecode.models.BIOT.forward", false]], "forward() (braindecode.models.contrawr method)": [[92, "braindecode.models.ContraWR.forward", false]], "forward() (braindecode.models.deepsleepnet method)": [[94, "braindecode.models.DeepSleepNet.forward", false]], "forward() (braindecode.models.eegconformer method)": [[95, "braindecode.models.EEGConformer.forward", false]], "forward() (braindecode.models.eeginceptionmi method)": [[98, "braindecode.models.EEGInceptionMI.forward", false]], "forward() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.forward", false]], "forward() (braindecode.models.eegnex method)": [[100, "braindecode.models.EEGNeX.forward", false]], "forward() (braindecode.models.eegsimpleconv method)": [[104, "braindecode.models.EEGSimpleConv.forward", false]], "forward() (braindecode.models.eegtcnet method)": [[105, "braindecode.models.EEGTCNet.forward", false]], "forward() (braindecode.models.hybridnet method)": [[106, "braindecode.models.HybridNet.forward", false]], "forward() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.forward", false]], "forward() (braindecode.models.sleepstagerblanco2020 method)": [[110, "braindecode.models.SleepStagerBlanco2020.forward", false]], "forward() (braindecode.models.sleepstagerchambon2018 method)": [[111, "braindecode.models.SleepStagerChambon2018.forward", false]], "forward() (braindecode.models.sleepstagereldele2021 method)": [[112, "braindecode.models.SleepStagerEldele2021.forward", false]], "forward() (braindecode.models.sparcnet method)": [[108, "braindecode.models.SPARCNet.forward", false]], "forward() (braindecode.models.syncnet method)": [[113, "braindecode.models.SyncNet.forward", false]], "forward() (braindecode.models.tcn method)": [[114, "braindecode.models.TCN.forward", false]], "forward() (braindecode.models.tidnet method)": [[115, "braindecode.models.TIDNet.forward", false]], "forward() (braindecode.models.usleep method)": [[116, "braindecode.models.USleep.forward", false]], "forward() (braindecode.training.croppedloss method)": [[136, "braindecode.training.CroppedLoss.forward", false]], "forward() (braindecode.training.timeseriesloss method)": [[140, "braindecode.training.TimeSeriesLoss.forward", false]], "forward_features() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.forward_features", false]], "frequency_shift() (in module braindecode.augmentation.functional)": [[61, "braindecode.augmentation.functional.frequency_shift", false]], "frequencyshift (class in braindecode.augmentation)": [[43, "braindecode.augmentation.FrequencyShift", false]], "ft_surrogate() (in module braindecode.augmentation.functional)": [[62, "braindecode.augmentation.functional.ft_surrogate", false]], "ftsurrogate (class in braindecode.augmentation)": [[42, "braindecode.augmentation.FTSurrogate", false]], "gaussian_noise() (in module braindecode.augmentation.functional)": [[63, "braindecode.augmentation.functional.gaussian_noise", false]], "gaussiannoise (class in braindecode.augmentation)": [[44, "braindecode.augmentation.GaussianNoise", false]], "get_augmentation_params() (braindecode.augmentation.bandstopfilter method)": [[37, "braindecode.augmentation.BandstopFilter.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.channelsdropout method)": [[38, "braindecode.augmentation.ChannelsDropout.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.channelsshuffle method)": [[39, "braindecode.augmentation.ChannelsShuffle.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.channelssymmetry method)": [[40, "braindecode.augmentation.ChannelsSymmetry.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.frequencyshift method)": [[43, "braindecode.augmentation.FrequencyShift.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.ftsurrogate method)": [[42, "braindecode.augmentation.FTSurrogate.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.gaussiannoise method)": [[44, "braindecode.augmentation.GaussianNoise.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.maskencoding method)": [[46, "braindecode.augmentation.MaskEncoding.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.mixup method)": [[47, "braindecode.augmentation.Mixup.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.segmentationreconstruction method)": [[48, "braindecode.augmentation.SegmentationReconstruction.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.sensorsrotation method)": [[49, "braindecode.augmentation.SensorsRotation.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.smoothtimemask method)": [[54, "braindecode.augmentation.SmoothTimeMask.get_augmentation_params", false]], "get_augmentation_params() (braindecode.augmentation.transform method)": [[56, "braindecode.augmentation.Transform.get_augmentation_params", false]], "get_classifier() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.get_classifier", false]], "get_fc_size() (braindecode.models.eegconformer method)": [[95, "braindecode.models.EEGConformer.get_fc_size", false]], "get_iterator() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.get_iterator", false]], "get_iterator() (braindecode.regressor.eegregressor method)": [[131, "braindecode.regressor.EEGRegressor.get_iterator", false]], "get_loss() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.get_loss", false]], "get_metadata() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.get_metadata", false]], "get_num_layers() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.get_num_layers", false]], "get_output_shape() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.get_output_shape", false]], "get_torchinfo_statistics() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.get_torchinfo_statistics", false]], "hgd (class in braindecode.datasets)": [[77, "braindecode.datasets.HGD", false]], "hybridnet (class in braindecode.models)": [[106, "braindecode.models.HybridNet", false]], "identity() (in module braindecode.augmentation.functional)": [[64, "braindecode.augmentation.functional.identity", false]], "identitytransform (class in braindecode.augmentation)": [[45, "braindecode.augmentation.IdentityTransform", false]], "info (braindecode.samplers.recordingsampler attribute)": [[133, "braindecode.samplers.RecordingSampler.info", false]], "info (braindecode.samplers.sequencesampler attribute)": [[135, "braindecode.samplers.SequenceSampler.info", false]], "initialized_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.initialized_", false]], "initialized_ (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor.initialized_", false]], "labram (class in braindecode.models)": [[107, "braindecode.models.Labram", false]], "load_concat_dataset() (in module braindecode.datautil)": [[87, "braindecode.datautil.load_concat_dataset", false]], "load_state_dict() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.load_state_dict", false]], "mask_encoding() (in module braindecode.augmentation.functional)": [[65, "braindecode.augmentation.functional.mask_encoding", false]], "maskencoding (class in braindecode.augmentation)": [[46, "braindecode.augmentation.MaskEncoding", false]], "mixup (class in braindecode.augmentation)": [[47, "braindecode.augmentation.Mixup", false]], "mixup() (in module braindecode.augmentation.functional)": [[66, "braindecode.augmentation.functional.mixup", false]], "mixup_criterion() (in module braindecode.training)": [[141, "braindecode.training.mixup_criterion", false]], "moabbdataset (class in braindecode.datasets)": [[78, "braindecode.datasets.MOABBDataset", false]], "module": [[0, "module-braindecode", false]], "module_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.module_", false]], "module_ (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor.module_", false]], "modules() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.modules", false]], "n_recordings (braindecode.samplers.recordingsampler attribute)": [[133, "braindecode.samplers.RecordingSampler.n_recordings", false]], "nmt (class in braindecode.datasets)": [[79, "braindecode.datasets.NMT", false]], "on_batch_end() (braindecode.training.croppedtrialepochscoring method)": [[138, "braindecode.training.CroppedTrialEpochScoring.on_batch_end", false]], "on_epoch_end() (braindecode.training.croppedtimeseriesepochscoring method)": [[137, "braindecode.training.CroppedTimeSeriesEpochScoring.on_epoch_end", false]], "on_epoch_end() (braindecode.training.croppedtrialepochscoring method)": [[138, "braindecode.training.CroppedTrialEpochScoring.on_epoch_end", false]], "on_epoch_end() (braindecode.training.postepochtrainscoring method)": [[139, "braindecode.training.PostEpochTrainScoring.on_epoch_end", false]], "operation() (braindecode.augmentation.bandstopfilter static method)": [[37, "braindecode.augmentation.BandstopFilter.operation", false]], "operation() (braindecode.augmentation.channelsdropout static method)": [[38, "braindecode.augmentation.ChannelsDropout.operation", false]], "operation() (braindecode.augmentation.channelsshuffle static method)": [[39, "braindecode.augmentation.ChannelsShuffle.operation", false]], "operation() (braindecode.augmentation.channelssymmetry static method)": [[40, "braindecode.augmentation.ChannelsSymmetry.operation", false]], "operation() (braindecode.augmentation.frequencyshift static method)": [[43, "braindecode.augmentation.FrequencyShift.operation", false]], "operation() (braindecode.augmentation.ftsurrogate static method)": [[42, "braindecode.augmentation.FTSurrogate.operation", false]], "operation() (braindecode.augmentation.gaussiannoise static method)": [[44, "braindecode.augmentation.GaussianNoise.operation", false]], "operation() (braindecode.augmentation.identitytransform static method)": [[45, "braindecode.augmentation.IdentityTransform.operation", false]], "operation() (braindecode.augmentation.maskencoding static method)": [[46, "braindecode.augmentation.MaskEncoding.operation", false]], "operation() (braindecode.augmentation.mixup static method)": [[47, "braindecode.augmentation.Mixup.operation", false]], "operation() (braindecode.augmentation.segmentationreconstruction static method)": [[48, "braindecode.augmentation.SegmentationReconstruction.operation", false]], "operation() (braindecode.augmentation.sensorsrotation static method)": [[49, "braindecode.augmentation.SensorsRotation.operation", false]], "operation() (braindecode.augmentation.signflip static method)": [[53, "braindecode.augmentation.SignFlip.operation", false]], "operation() (braindecode.augmentation.smoothtimemask static method)": [[54, "braindecode.augmentation.SmoothTimeMask.operation", false]], "operation() (braindecode.augmentation.timereverse static method)": [[55, "braindecode.augmentation.TimeReverse.operation", false]], "parameters() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.parameters", false]], "pick (class in braindecode.preprocessing)": [[120, "braindecode.preprocessing.Pick", false]], "plot_confusion_matrix() (in module braindecode.visualization)": [[146, "braindecode.visualization.plot_confusion_matrix", false]], "postepochtrainscoring (class in braindecode.training)": [[139, "braindecode.training.PostEpochTrainScoring", false]], "predict() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.predict", false]], "predict_proba() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.predict_proba", false]], "predict_proba() (braindecode.regressor.eegregressor method)": [[131, "braindecode.regressor.EEGRegressor.predict_proba", false]], "predict_trials() (braindecode.classifier.eegclassifier method)": [[72, "braindecode.classifier.EEGClassifier.predict_trials", false]], "predict_trials() (braindecode.regressor.eegregressor method)": [[131, "braindecode.regressor.EEGRegressor.predict_trials", false]], "predict_trials() (in module braindecode.training)": [[142, "braindecode.training.predict_trials", false]], "prefixes_ (braindecode.classifier.eegclassifier attribute)": [[72, "braindecode.classifier.EEGClassifier.prefixes_", false]], "prefixes_ (braindecode.regressor.eegregressor attribute)": [[131, "braindecode.regressor.EEGRegressor.prefixes_", false]], "preprocess() (in module braindecode.preprocessing)": [[130, "braindecode.preprocessing.preprocess", false]], "preprocessor (class in braindecode.preprocessing)": [[121, "braindecode.preprocessing.Preprocessor", false]], "presample() (braindecode.samplers.relativepositioningsampler method)": [[134, "braindecode.samplers.RelativePositioningSampler.presample", false]], "recordingsampler (class in braindecode.samplers)": [[133, "braindecode.samplers.RecordingSampler", false]], "relativepositioningsampler (class in braindecode.samplers)": [[134, "braindecode.samplers.RelativePositioningSampler", false]], "resample (class in braindecode.preprocessing)": [[122, "braindecode.preprocessing.Resample", false]], "reset_classifier() (braindecode.models.labram method)": [[107, "braindecode.models.Labram.reset_classifier", false]], "sample_class() (braindecode.samplers.balancedsequencesampler method)": [[132, "braindecode.samplers.BalancedSequenceSampler.sample_class", false]], "sample_recording() (braindecode.samplers.recordingsampler method)": [[133, "braindecode.samplers.RecordingSampler.sample_recording", false]], "sample_window() (braindecode.samplers.recordingsampler method)": [[133, "braindecode.samplers.RecordingSampler.sample_window", false]], "save() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.save", false]], "save_concat_dataset() (in module braindecode.datautil)": [[88, "braindecode.datautil.save_concat_dataset", false]], "segmentation_reconstruction() (in module braindecode.augmentation.functional)": [[67, "braindecode.augmentation.functional.segmentation_reconstruction", false]], "segmentationreconstruction (class in braindecode.augmentation)": [[48, "braindecode.augmentation.SegmentationReconstruction", false]], "sensors_rotation() (in module braindecode.augmentation.functional)": [[68, "braindecode.augmentation.functional.sensors_rotation", false]], "sensorsrotation (class in braindecode.augmentation)": [[49, "braindecode.augmentation.SensorsRotation", false]], "sensorsxrotation (class in braindecode.augmentation)": [[50, "braindecode.augmentation.SensorsXRotation", false]], "sensorsyrotation (class in braindecode.augmentation)": [[51, "braindecode.augmentation.SensorsYRotation", false]], "sensorszrotation (class in braindecode.augmentation)": [[52, "braindecode.augmentation.SensorsZRotation", false]], "sequencesampler (class in braindecode.samplers)": [[135, "braindecode.samplers.SequenceSampler", false]], "set_description() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.set_description", false]], "set_description() (braindecode.datasets.basedataset method)": [[76, "braindecode.datasets.BaseDataset.set_description", false]], "set_description() (braindecode.datasets.windowsdataset method)": [[83, "braindecode.datasets.WindowsDataset.set_description", false]], "set_random_seeds() (in module braindecode.util)": [[144, "braindecode.util.set_random_seeds", false]], "seteegreference (class in braindecode.preprocessing)": [[123, "braindecode.preprocessing.SetEEGReference", false]], "shallowfbcspnet (class in braindecode.models)": [[109, "braindecode.models.ShallowFBCSPNet", false]], "sign_flip() (in module braindecode.augmentation.functional)": [[69, "braindecode.augmentation.functional.sign_flip", false]], "signflip (class in braindecode.augmentation)": [[53, "braindecode.augmentation.SignFlip", false]], "sleepphysionet (class in braindecode.datasets)": [[80, "braindecode.datasets.SleepPhysionet", false]], "sleepstagerblanco2020 (class in braindecode.models)": [[110, "braindecode.models.SleepStagerBlanco2020", false]], "sleepstagerchambon2018 (class in braindecode.models)": [[111, "braindecode.models.SleepStagerChambon2018", false]], "sleepstagereldele2021 (class in braindecode.models)": [[112, "braindecode.models.SleepStagerEldele2021", false]], "smooth_time_mask() (in module braindecode.augmentation.functional)": [[70, "braindecode.augmentation.functional.smooth_time_mask", false]], "smoothtimemask (class in braindecode.augmentation)": [[54, "braindecode.augmentation.SmoothTimeMask", false]], "sparcnet (class in braindecode.models)": [[108, "braindecode.models.SPARCNet", false]], "split() (braindecode.datasets.baseconcatdataset method)": [[75, "braindecode.datasets.BaseConcatDataset.split", false]], "syncnet (class in braindecode.models)": [[113, "braindecode.models.SyncNet", false]], "tcn (class in braindecode.models)": [[114, "braindecode.models.TCN", false]], "tidnet (class in braindecode.models)": [[115, "braindecode.models.TIDNet", false]], "time_reverse() (in module braindecode.augmentation.functional)": [[71, "braindecode.augmentation.functional.time_reverse", false]], "timereverse (class in braindecode.augmentation)": [[55, "braindecode.augmentation.TimeReverse", false]], "timeseriesloss (class in braindecode.training)": [[140, "braindecode.training.TimeSeriesLoss", false]], "to_dense_prediction_model() (braindecode.models.eegmodulemixin method)": [[99, "braindecode.models.EEGModuleMixin.to_dense_prediction_model", false]], "torch_stft() (braindecode.models.contrawr method)": [[92, "braindecode.models.ContraWR.torch_stft", false]], "transform (class in braindecode.augmentation)": [[56, "braindecode.augmentation.Transform", false]], "trial_preds_from_window_preds() (in module braindecode.training)": [[143, "braindecode.training.trial_preds_from_window_preds", false]], "tuh (class in braindecode.datasets)": [[81, "braindecode.datasets.TUH", false]], "tuhabnormal (class in braindecode.datasets)": [[82, "braindecode.datasets.TUHAbnormal", false]], "usleep (class in braindecode.models)": [[116, "braindecode.models.USleep", false]], "windowsdataset (class in braindecode.datasets)": [[83, "braindecode.datasets.WindowsDataset", false]]}, "objects": {"": [[0, 0, 0, "-", "braindecode"]], "braindecode.augmentation": [[36, 1, 1, "", "AugmentedDataLoader"], [37, 1, 1, "", "BandstopFilter"], [38, 1, 1, "", "ChannelsDropout"], [39, 1, 1, "", "ChannelsShuffle"], [40, 1, 1, "", "ChannelsSymmetry"], [41, 1, 1, "", "Compose"], [42, 1, 1, "", "FTSurrogate"], [43, 1, 1, "", "FrequencyShift"], [44, 1, 1, "", "GaussianNoise"], [45, 1, 1, "", "IdentityTransform"], [46, 1, 1, "", "MaskEncoding"], [47, 1, 1, "", "Mixup"], [48, 1, 1, "", "SegmentationReconstruction"], [49, 1, 1, "", "SensorsRotation"], [50, 1, 1, "", "SensorsXRotation"], [51, 1, 1, "", "SensorsYRotation"], [52, 1, 1, "", "SensorsZRotation"], [53, 1, 1, "", "SignFlip"], [54, 1, 1, "", "SmoothTimeMask"], [55, 1, 1, "", "TimeReverse"], [56, 1, 1, "", "Transform"]], "braindecode.augmentation.BandstopFilter": [[37, 2, 1, "", "get_augmentation_params"], [37, 2, 1, "", "operation"]], "braindecode.augmentation.ChannelsDropout": [[38, 2, 1, "", "get_augmentation_params"], [38, 2, 1, "", "operation"]], "braindecode.augmentation.ChannelsShuffle": [[39, 2, 1, "", "get_augmentation_params"], [39, 2, 1, "", "operation"]], "braindecode.augmentation.ChannelsSymmetry": [[40, 2, 1, "", "get_augmentation_params"], [40, 2, 1, "", "operation"]], "braindecode.augmentation.Compose": [[41, 2, 1, "", "forward"]], "braindecode.augmentation.FTSurrogate": [[42, 2, 1, "", "get_augmentation_params"], [42, 2, 1, "", "operation"]], "braindecode.augmentation.FrequencyShift": [[43, 2, 1, "", "get_augmentation_params"], [43, 2, 1, "", "operation"]], "braindecode.augmentation.GaussianNoise": [[44, 2, 1, "", "get_augmentation_params"], [44, 2, 1, "", "operation"]], "braindecode.augmentation.IdentityTransform": [[45, 2, 1, "", "operation"]], "braindecode.augmentation.MaskEncoding": [[46, 2, 1, "", "get_augmentation_params"], [46, 2, 1, "", "operation"]], "braindecode.augmentation.Mixup": [[47, 2, 1, "", "get_augmentation_params"], [47, 2, 1, "", "operation"]], "braindecode.augmentation.SegmentationReconstruction": [[48, 2, 1, "", "get_augmentation_params"], [48, 2, 1, "", "operation"]], "braindecode.augmentation.SensorsRotation": [[49, 2, 1, "", "get_augmentation_params"], [49, 2, 1, "", "operation"]], "braindecode.augmentation.SignFlip": [[53, 2, 1, "", "operation"]], "braindecode.augmentation.SmoothTimeMask": [[54, 2, 1, "", "get_augmentation_params"], [54, 2, 1, "", "operation"]], "braindecode.augmentation.TimeReverse": [[55, 2, 1, "", "operation"]], "braindecode.augmentation.Transform": [[56, 2, 1, "", "forward"], [56, 2, 1, "", "get_augmentation_params"]], "braindecode.augmentation.functional": [[57, 3, 1, "", "bandstop_filter"], [58, 3, 1, "", "channels_dropout"], [59, 3, 1, "", "channels_permute"], [60, 3, 1, "", "channels_shuffle"], [61, 3, 1, "", "frequency_shift"], [62, 3, 1, "", "ft_surrogate"], [63, 3, 1, "", "gaussian_noise"], [64, 3, 1, "", "identity"], [65, 3, 1, "", "mask_encoding"], [66, 3, 1, "", "mixup"], [67, 3, 1, "", "segmentation_reconstruction"], [68, 3, 1, "", "sensors_rotation"], [69, 3, 1, "", "sign_flip"], [70, 3, 1, "", "smooth_time_mask"], [71, 3, 1, "", "time_reverse"]], "braindecode.classifier": [[72, 1, 1, "", "EEGClassifier"]], "braindecode.classifier.EEGClassifier": [[72, 4, 1, "", "_criteria"], [72, 4, 1, "", "_modules"], [72, 4, 1, "", "_optimizers"], [72, 4, 1, "", "callbacks_"], [72, 4, 1, "", "classes_"], [72, 4, 1, "", "criterion_"], [72, 4, 1, "", "cuda_dependent_attributes_"], [72, 2, 1, "", "get_iterator"], [72, 2, 1, "", "get_loss"], [72, 4, 1, "", "initialized_"], [72, 4, 1, "", "module_"], [72, 2, 1, "", "predict"], [72, 2, 1, "", "predict_proba"], [72, 2, 1, "", "predict_trials"], [72, 4, 1, "", "prefixes_"]], "braindecode.datasets": [[73, 1, 1, "", "BCICompetitionIVDataset4"], [74, 1, 1, "", "BNCI2014001"], [75, 1, 1, "", "BaseConcatDataset"], [76, 1, 1, "", "BaseDataset"], [77, 1, 1, "", "HGD"], [78, 1, 1, "", "MOABBDataset"], [79, 1, 1, "", "NMT"], [80, 1, 1, "", "SleepPhysionet"], [81, 1, 1, "", "TUH"], [82, 1, 1, "", "TUHAbnormal"], [83, 1, 1, "", "WindowsDataset"], [84, 3, 1, "", "create_from_X_y"], [85, 3, 1, "", "create_from_mne_epochs"], [86, 3, 1, "", "create_from_mne_raw"]], "braindecode.datasets.BCICompetitionIVDataset4": [[73, 2, 1, "", "download"]], "braindecode.datasets.BaseConcatDataset": [[75, 2, 1, "", "get_metadata"], [75, 2, 1, "", "save"], [75, 2, 1, "", "set_description"], [75, 2, 1, "", "split"]], "braindecode.datasets.BaseDataset": [[76, 2, 1, "", "set_description"]], "braindecode.datasets.WindowsDataset": [[83, 2, 1, "", "set_description"]], "braindecode.datautil": [[87, 3, 1, "", "load_concat_dataset"], [88, 3, 1, "", "save_concat_dataset"]], "braindecode.models": [[89, 1, 1, "", "ATCNet"], [90, 1, 1, "", "AttentionBaseNet"], [91, 1, 1, "", "BIOT"], [92, 1, 1, "", "ContraWR"], [93, 1, 1, "", "Deep4Net"], [94, 1, 1, "", "DeepSleepNet"], [95, 1, 1, "", "EEGConformer"], [96, 1, 1, "", "EEGITNet"], [97, 1, 1, "", "EEGInceptionERP"], [98, 1, 1, "", "EEGInceptionMI"], [99, 1, 1, "", "EEGModuleMixin"], [100, 1, 1, "", "EEGNeX"], [101, 1, 1, "", "EEGNetv1"], [102, 1, 1, "", "EEGNetv4"], [103, 1, 1, "", "EEGResNet"], [104, 1, 1, "", "EEGSimpleConv"], [105, 1, 1, "", "EEGTCNet"], [106, 1, 1, "", "HybridNet"], [107, 1, 1, "", "Labram"], [108, 1, 1, "", "SPARCNet"], [109, 1, 1, "", "ShallowFBCSPNet"], [110, 1, 1, "", "SleepStagerBlanco2020"], [111, 1, 1, "", "SleepStagerChambon2018"], [112, 1, 1, "", "SleepStagerEldele2021"], [113, 1, 1, "", "SyncNet"], [114, 1, 1, "", "TCN"], [115, 1, 1, "", "TIDNet"], [116, 1, 1, "", "USleep"]], "braindecode.models.ATCNet": [[89, 2, 1, "", "forward"]], "braindecode.models.AttentionBaseNet": [[90, 2, 1, "", "forward"]], "braindecode.models.BIOT": [[91, 2, 1, "", "forward"]], "braindecode.models.ContraWR": [[92, 2, 1, "", "forward"], [92, 2, 1, "", "torch_stft"]], "braindecode.models.DeepSleepNet": [[94, 2, 1, "", "forward"]], "braindecode.models.EEGConformer": [[95, 2, 1, "", "forward"], [95, 2, 1, "", "get_fc_size"]], "braindecode.models.EEGInceptionMI": [[98, 2, 1, "", "forward"]], "braindecode.models.EEGModuleMixin": [[99, 2, 1, "", "forward"], [99, 2, 1, "", "get_output_shape"], [99, 2, 1, "", "get_torchinfo_statistics"], [99, 2, 1, "", "load_state_dict"], [99, 2, 1, "", "modules"], [99, 2, 1, "", "parameters"], [99, 2, 1, "", "to_dense_prediction_model"]], "braindecode.models.EEGNeX": [[100, 2, 1, "", "calc_padding"], [100, 2, 1, "", "forward"]], "braindecode.models.EEGSimpleConv": [[104, 2, 1, "", "forward"]], "braindecode.models.EEGTCNet": [[105, 2, 1, "", "forward"]], "braindecode.models.HybridNet": [[106, 2, 1, "", "forward"]], "braindecode.models.Labram": [[107, 2, 1, "", "fix_init_weight_and_init_embedding"], [107, 2, 1, "", "forward"], [107, 2, 1, "", "forward_features"], [107, 2, 1, "", "get_classifier"], [107, 2, 1, "", "get_num_layers"], [107, 2, 1, "", "reset_classifier"]], "braindecode.models.SPARCNet": [[108, 2, 1, "", "forward"]], "braindecode.models.SleepStagerBlanco2020": [[110, 2, 1, "", "forward"]], "braindecode.models.SleepStagerChambon2018": [[111, 2, 1, "", "forward"]], "braindecode.models.SleepStagerEldele2021": [[112, 2, 1, "", "forward"]], "braindecode.models.SyncNet": [[113, 2, 1, "", "forward"]], "braindecode.models.TCN": [[114, 2, 1, "", "forward"]], "braindecode.models.TIDNet": [[115, 2, 1, "", "forward"]], "braindecode.models.USleep": [[116, 2, 1, "", "forward"]], "braindecode.preprocessing": [[117, 1, 1, "", "Crop"], [118, 1, 1, "", "DropChannels"], [119, 1, 1, "", "Filter"], [120, 1, 1, "", "Pick"], [121, 1, 1, "", "Preprocessor"], [122, 1, 1, "", "Resample"], [123, 1, 1, "", "SetEEGReference"], [124, 3, 1, "", "create_fixed_length_windows"], [125, 3, 1, "", "create_windows_from_events"], [126, 3, 1, "", "create_windows_from_target_channels"], [127, 3, 1, "", "exponential_moving_demean"], [128, 3, 1, "", "exponential_moving_standardize"], [129, 3, 1, "", "filterbank"], [130, 3, 1, "", "preprocess"]], "braindecode.preprocessing.Preprocessor": [[121, 2, 1, "", "apply"]], "braindecode.regressor": [[131, 1, 1, "", "EEGRegressor"]], "braindecode.regressor.EEGRegressor": [[131, 4, 1, "", "_criteria"], [131, 4, 1, "", "_modules"], [131, 4, 1, "", "_optimizers"], [131, 4, 1, "", "callbacks_"], [131, 4, 1, "", "criterion_"], [131, 4, 1, "", "cuda_dependent_attributes_"], [131, 2, 1, "", "fit"], [131, 2, 1, "", "get_iterator"], [131, 4, 1, "", "initialized_"], [131, 4, 1, "", "module_"], [131, 2, 1, "", "predict_proba"], [131, 2, 1, "", "predict_trials"], [131, 4, 1, "", "prefixes_"]], "braindecode.samplers": [[132, 1, 1, "", "BalancedSequenceSampler"], [133, 1, 1, "", "RecordingSampler"], [134, 1, 1, "", "RelativePositioningSampler"], [135, 1, 1, "", "SequenceSampler"]], "braindecode.samplers.BalancedSequenceSampler": [[132, 2, 1, "", "sample_class"]], "braindecode.samplers.RecordingSampler": [[133, 4, 1, "", "info"], [133, 4, 1, "", "n_recordings"], [133, 2, 1, "", "sample_recording"], [133, 2, 1, "", "sample_window"]], "braindecode.samplers.RelativePositioningSampler": [[134, 2, 1, "", "presample"]], "braindecode.samplers.SequenceSampler": [[135, 4, 1, "", "file_ids"], [135, 4, 1, "", "info"]], "braindecode.training": [[136, 1, 1, "", "CroppedLoss"], [137, 1, 1, "", "CroppedTimeSeriesEpochScoring"], [138, 1, 1, "", "CroppedTrialEpochScoring"], [139, 1, 1, "", "PostEpochTrainScoring"], [140, 1, 1, "", "TimeSeriesLoss"], [141, 3, 1, "", "mixup_criterion"], [142, 3, 1, "", "predict_trials"], [143, 3, 1, "", "trial_preds_from_window_preds"]], "braindecode.training.CroppedLoss": [[136, 2, 1, "", "forward"]], "braindecode.training.CroppedTimeSeriesEpochScoring": [[137, 2, 1, "", "on_epoch_end"]], "braindecode.training.CroppedTrialEpochScoring": [[138, 2, 1, "", "on_batch_end"], [138, 2, 1, "", "on_epoch_end"]], "braindecode.training.PostEpochTrainScoring": [[139, 2, 1, "", "on_epoch_end"]], "braindecode.training.TimeSeriesLoss": [[140, 2, 1, "", "forward"]], "braindecode.util": [[144, 3, 1, "", "set_random_seeds"]], "braindecode.visualization": [[145, 3, 1, "", "compute_amplitude_gradients"], [146, 3, 1, "", "plot_confusion_matrix"]]}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "method", "Python method"], "3": ["py", "function", "Python function"], "4": ["py", "attribute", "Python attribute"]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:method", "3": "py:function", "4": "py:attribute"}, "terms": {"": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 21, 22, 26, 27, 28, 30, 31, 32, 40, 42, 44, 48, 49, 50, 51, 52, 59, 62, 63, 68, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 89, 97, 98, 101, 102, 107, 108, 111, 114, 116, 118, 119, 121, 123, 131, 132, 136, 139, 140], "0": [2, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 34, 37, 38, 39, 42, 44, 45, 46, 47, 56, 58, 60, 62, 66, 72, 74, 75, 79, 80, 81, 82, 86, 89, 90, 91, 92, 93, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 122, 123, 124, 125, 127, 128, 130, 131, 133, 142, 146, 152], "00": [6, 10, 13, 16, 23, 26, 27, 32, 33, 34, 152], "000": [5, 16, 17, 18, 19, 22, 23, 31, 34, 152], "0000": [2, 3, 8, 27, 28, 29, 30, 31], "00000000": 22, "00000058": 22, "0000625": 30, "00009932": 22, "0001": [2, 30, 103, 128], "00012331": 22, "00014928": 22, "0002": [2, 3, 28], "0004": 2, "0005": [2, 3, 22, 28, 31], "000525": 22, "0006": [2, 3, 8, 27, 28, 29], "000625": 29, "001": [3, 4, 18, 20, 21, 27, 28, 29, 30, 31, 74, 107, 127, 128], "0010": 31, "0014": 30, "0019": 29, "00267": 35, "004": 11, "0040": 5, "00622": 105, "00625": [29, 30], "0063": [29, 30], "0082": 26, "0083": 26, "0085": 26, "0086": 26, "0092": 26, "00m": 16, "01": [2, 3, 4, 6, 8, 16, 23, 26, 27, 28, 29, 32, 33, 72, 97, 131, 152], "011": 11, "01271": 114, "0154": 26, "0165": 22, "0168": [22, 29], "0177": 30, "019": [2, 8, 73, 110], "0193": 35, "0194": 16, "01_tcp_ar": 22, "01m": 16, "01m23": 16, "02": [11, 16, 23, 26, 27, 33, 91, 92, 107, 108, 152], "021": [10, 13, 152], "0260": 22, "0261": 8, "0273": 22, "02736802": 22, "0280": 22, "0285": 29, "02_tcp_le": 22, "02m": 16, "03": [6, 9, 10, 11, 13, 16, 23, 27, 90, 107, 152], "0308": 22, "0308012": 22, "0311": 22, "0312": 29, "033339": 32, "037": [8, 13, 152], "0374": 29, "0381": 8, "03_tcp_ar_a": 22, "03it": 32, "03m": 16, "04": [3, 4, 11, 13, 16, 23, 26, 27, 28, 29, 32, 152], "0408": 22, "0410": 27, "04174": 110, "0419": 22, "04194231": 22, "0426": 22, "044": [3, 4, 28, 29, 32], "0445": 29, "0448": 22, "046014": 98, "046020": 4, "0461": 8, "0482": 31, "04871": [37, 44, 54, 57, 63, 70], "05": [6, 10, 11, 12, 16, 23, 30, 81, 82, 113, 115, 152], "0506": 22, "0508": 22, "0517": 29, "0537782": 22, "0538": 22, "05458383": 22, "0546": 22, "0555": 29, "056008": 115, "0593": 22, "05m": 16, "06": [2, 8, 10, 11, 13, 16, 27, 152], "060": 11, "060518": 32, "0613": 31, "0625": [2, 3, 4, 8, 27, 28, 29, 32], "06366": 107, "0641": 29, "066011": [28, 29, 30], "0678": [2, 8, 73], "0679": 30, "0690": 30, "07": [10, 13, 16, 27, 29, 33, 152], "0702": 28, "0703125": 116, "07159": 104, "0739": 31, "0748": 29, "0764": 29, "07m": 16, "08": 16, "08024": [101, 102], "0806": 8, "0815": 30, "0847": 29, "08675": [42, 62], "0888": 9, "08m": 16, "09": [16, 27], "09237": 31, "0927": 2, "09412": [47, 66, 141], "0944": 8, "0966": 9, "0967": 9, "09702": [40, 59], "0981": 29, "099": 22, "09m": 16, "0m": 16, "0mb": 27, "0test": 29, "0train": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32], "0x7f128dada380": 16, "0x7f128dafb400": 9, "0x7f128f2bd690": 27, "0x7f128f2e0f40": 29, "0x7f128f32f9a0": 11, "0x7f128f3e8220": 16, "0x7f128f761480": 9, "0x7f129c845e40": 9, "0x7f129c846ef0": 5, "0x7f129c847820": 5, "0x7f1351a5c850": 10, "0x7f1351a5e9e0": 10, "0x7f135213a620": 4, "0x7f1352141a80": 5, "0x7f13521e10f0": 3, "0x7f1353110c70": 18, "0x7f1353110d60": [16, 21], "0x7f1354160040": 21, "0x7f1354160160": 21, "0x7f1354160190": 21, "0x7f1354160220": 21, "0x7f1354160520": 21, "0x7f1354160760": 21, "0x7f1354160910": 21, "0x7f1354160e50": 21, "0x7f1354161000": 21, "0x7f1354161090": 21, "0x7f13541623b0": 16, "0x7f1354c2c790": 8, "0x7f1354c2e080": 28, "0x7f1354c5c3a0": 32, "0x7f1354cb9870": 30, "0x7f1354d0fac0": 5, "0x7f1354d0fee0": 21, "0x7f1354d80c40": 21, "0x7f1354d9df30": 31, "0x7f136a343dc0": 2, "0x7f136a67cd30": 21, "0x7f136a75c820": 21, "0x7f136a75cd90": 21, "0x7f136a75dc00": 21, "0x7f136a75e5f0": 21, "0x7f136a75f700": 21, "0x7f136a75fac0": 21, "1": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 30, 31, 37, 38, 39, 40, 42, 44, 45, 46, 47, 48, 49, 50, 51, 52, 54, 56, 57, 58, 59, 60, 62, 63, 66, 67, 68, 70, 72, 73, 74, 75, 77, 79, 80, 81, 82, 87, 89, 90, 92, 93, 97, 98, 99, 100, 103, 104, 107, 109, 110, 112, 113, 115, 116, 119, 122, 123, 124, 125, 126, 127, 128, 131, 132, 133, 141, 142, 143, 146], "10": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 35, 40, 49, 50, 51, 52, 68, 72, 73, 81, 82, 89, 93, 95, 96, 97, 103, 105, 106, 107, 109, 110, 112, 115, 119, 123, 131, 132, 146], "100": [3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 20, 26, 27, 28, 29, 30, 31, 32, 37, 54, 74, 91, 93, 104, 108, 116, 122], "1000": [2, 3, 4, 8, 12, 22, 26, 27, 28, 29, 30, 32, 77, 97, 133], "1002": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 146], "1007": 110, "100hz": 112, "101": [5, 9, 10, 11, 12], "102": 11, "1024": 26, "1027": 2, "103": [48, 67], "1031": 11, "1033": 31, "1038": [2, 8, 73], "105": 5, "105475": 100, "105kb": 27, "1064": 27, "107": [5, 26], "107kb": 27, "108": 11, "1088": [5, 115], "109": 5, "1097": 35, "10it": 32, "10m": 16, "11": [2, 3, 4, 5, 8, 10, 11, 12, 13, 16, 17, 18, 19, 20, 21, 27, 28, 29, 31, 32, 33, 73, 94, 152], "110": 11, "1101": [3, 4, 28, 29, 32], "1109": [10, 89, 96, 97, 112], "11198": 90, "1121": 2, "1125": [3, 4, 28, 29, 32], "1131": [3, 6, 152], "1145": 22, "1147": 27, "1149": 9, "115": 11, "1175": 22, "11754766": 22, "1185": [5, 9, 10, 11, 22], "1194": [5, 9, 10, 11], "11m": 16, "12": [4, 5, 11, 16, 17, 18, 19, 27, 29, 30, 32, 74, 104, 105, 107, 116, 146, 152], "120": [10, 77, 112], "1209": 22, "1209397": 22, "121": [5, 12], "122": 12, "1225": [2, 8, 73], "123": 22, "1231": 27, "1235": [2, 8, 73], "124": [17, 19, 27], "1247": 5, "1249": 22, "12493701": 22, "125": [97, 111], "1251": 22, "1255": 2, "125hz": 112, "126": 11, "1276": 29, "128": [5, 10, 11, 72, 77, 92, 97, 104, 111, 116, 131], "1281": 22, "129": [5, 11], "12m": 16, "13": [5, 9, 10, 11, 13, 16, 17, 19, 26, 27, 28, 32, 33, 77, 80, 91, 92, 108, 119, 129, 152], "130": [9, 13, 152], "1319": 22, "1322": 22, "133": [10, 11], "13440": 77, "1350": 22, "13578887": 22, "1360": 22, "13694": [38, 39, 58, 60], "1379": 30, "138": 153, "13m": 16, "14": [2, 5, 8, 9, 11, 16, 17, 19, 27, 28, 32, 77, 119, 144], "1409": 22, "1412": 31, "1415": 8, "142": [5, 153], "1422": 22, "1427": 29, "14345092": 22, "144": [4, 74, 104], "1445": 2, "14483": 4, "145": 32, "146": 153, "1466": [27, 33, 152], "146gb": 16, "147": 153, "1471": 10, "1478": 30, "148": [18, 23, 152, 153], "14827406": 22, "1483": 22, "1486": 22, "1486133": 22, "1488": 30, "149": 22, "15": [5, 9, 10, 11, 12, 14, 16, 26, 27, 28, 29, 30, 49, 50, 51, 52, 79, 90, 95, 109, 115, 119, 122], "150": [9, 10, 11, 77], "1500": [11, 26, 115, 133], "1508": 22, "1512": 2, "152": [11, 153], "1531": 10, "1532": 29, "1535": 22, "15352039": 22, "154": 11, "15447331": 22, "15447332": 22, "1545": 22, "1547": 10, "155": 153, "156": 11, "15756383": 22, "158": 153, "159": 153, "1594": 11, "15m": 16, "16": [5, 9, 10, 11, 16, 27, 30, 89, 90, 100, 102, 108, 111, 119], "160": [11, 77], "16017832": 22, "1602": 22, "1607": 22, "161": [11, 153], "16104": [5, 134], "1611": [101, 102], "163": 11, "164": 153, "166": 153, "1662": 35, "166gb": 27, "167": 153, "1671": 3, "1677": 22, "1687": [2, 6, 152], "169": 153, "16m": 16, "17": [5, 11, 16, 27, 104, 108, 115], "170": [5, 153], "1707": 11, "171": 153, "1710": [47, 66, 141], "1716": 2, "1729": 22, "1741": 115, "174715": 32, "1749": 29, "1753": 31, "1755": 2, "176": [10, 19, 97], "176596": 32, "1768": 22, "178": 153, "1792846": 22, "1793": 22, "1795": 10, "18": [3, 4, 5, 6, 11, 12, 16, 27, 98, 152, 153], "180": 11, "1803": [40, 59, 114], "1806": [42, 62], "1807": 22, "1811": 10, "182": 152, "1829": 28, "185": 153, "1853": 11, "188": 11, "1882": 22, "1885": 10, "189": 32, "18m": 16, "19": [5, 9, 10, 11, 16, 27, 117, 123], "1900": 5, "1904": 31, "1915": 29, "192104": 32, "194": 9, "1941": 3, "195": 11, "1955": 10, "1963": 29, "197": [11, 153], "19750": 16, "1975000": 16, "198": 153, "199": 153, "1990": 2, "1998": 94, "19999": [17, 19], "19k": 27, "19m": 16, "1d": [98, 104], "1e": [2, 3, 4, 8, 9, 10, 11, 27, 28, 29, 30, 32], "1e6": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32], "1f": [12, 32], "1hz": 37, "1m": [16, 27], "1mb": [16, 27], "1test": [3, 4, 20, 21, 27, 28, 29, 30, 32], "2": [2, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 30, 31, 33, 37, 38, 39, 42, 43, 44, 47, 54, 57, 62, 63, 66, 70, 72, 74, 77, 79, 80, 89, 92, 93, 97, 99, 100, 101, 102, 103, 104, 105, 110, 112, 113, 115, 116, 119, 123, 128, 131, 132, 133, 141, 142, 152], "20": [5, 9, 10, 11, 12, 16, 26, 27, 29, 31, 32, 40, 49, 50, 51, 52, 68, 92, 103, 110, 123], "200": [2, 8, 10, 11, 14, 91, 93, 107], "2000": [5, 9, 10, 11, 22, 133], "20000": 17, "2004": 77, "2006": 105, "2007": [5, 37, 44, 54, 57, 63, 70, 134], "2008": [77, 94], "2010": [38, 39, 58, 60, 77], "2012": [27, 28, 29, 30], "2013": 35, "2014": [31, 74], "2015": [48, 67], "2016": 101, "2017": [26, 27, 28, 29, 30, 31, 35, 49, 50, 51, 52, 68, 77, 93, 94, 103, 106, 109, 113, 146], "2018": [5, 9, 10, 28, 29, 30, 40, 42, 44, 47, 59, 62, 63, 66, 102, 111, 114], "2019": [2, 8, 31, 73], "202": 26, "2020": [5, 37, 38, 39, 44, 54, 57, 58, 60, 63, 70, 97, 105, 110, 115, 134], "20200220": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "2021": [4, 10, 11, 92, 97, 98, 112, 116, 132], "2022": [4, 30, 79, 89, 95, 96, 97], "2023": [90, 91, 92, 104, 108], "2024": [46, 65, 90, 91, 92, 100, 107, 108], "2025": 113, "2031": 22, "2036": 9, "2037": 22, "2040": 11, "205": 97, "2058": 2, "2069": 30, "209k": 27, "20it": 32, "21": [5, 9, 10, 11, 16, 27, 31, 123], "2102": 9, "2126": 9, "2136": 9, "2137": 22, "214": 11, "215": [2, 6, 152], "21543634": 22, "216": 11, "2186": 10, "219": 97, "2196f3": 29, "21it": 32, "21m": 16, "22": [3, 4, 5, 9, 11, 16, 17, 19, 27, 28, 29, 32, 74], "2206": 4, "2208": 107, "2217": 29, "22222222222223": [9, 10, 11], "2224": 11, "223": [22, 23, 152, 153], "22477157": 22, "2247716": 22, "2248": 22, "2249": 22, "225": 11, "2275": 29, "227kb": 27, "228": 11, "2295": 10, "229k": 16, "22m": 16, "22mb": 27, "23": [2, 5, 9, 10, 11, 16, 27, 33, 118], "2309": 104, "2310": 90, "232164": 20, "2324": 9, "232kb": 27, "2331": 10, "2348": 30, "236566": 32, "237": 11, "23730": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 146], "2374": 22, "238": [37, 44, 54, 57, 63, 70], "2396": 28, "23m": 16, "24": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31, 32, 110, 115, 120, 152], "240": [3, 4, 17, 26, 27, 28, 29, 32], "2402": 27, "2410": 11, "2414": 30, "243": [17, 23, 152], "2435": 30, "244": [5, 9, 16], "246258": 32, "2465": 9, "249": [27, 33, 152], "24m": 16, "25": [2, 5, 8, 9, 11, 12, 14, 16, 27, 29, 31, 32, 74, 89, 90, 93, 94, 95, 97, 101, 102, 105, 109, 111, 119], "250": [5, 20, 27, 74, 89, 95, 98, 103], "2500": [22, 28, 29, 133], "25070": 16, "2507000": 16, "250hz": 74, "2511": [10, 29], "25153176": 22, "2522": 22, "2526": 22, "253": [37, 44, 54, 57, 63, 70], "254": 153, "2548": 29, "2552": 115, "256": [14, 26, 91, 92, 153], "2569": 27, "256hz": 26, "25829056": 22, "2583": 22, "2586": 30, "25878426": 22, "2588": 22, "2593": 29, "25e": 30, "25it": 32, "26": [5, 8, 9, 10, 11, 13, 16, 20, 23, 27, 111, 152], "260": 77, "2600": 22, "2609": 30, "261": 153, "2625": 2, "2626": 5, "263": 153, "2639": 3, "2657": 22, "267": 35, "269": 153, "2696": 30, "26m": 16, "27": [2, 9, 11, 16, 77], "2731": 2, "273gb": 27, "274": 153, "2742": 22, "2743": 28, "2759": 30, "276": 13, "2768": 9, "277": 153, "2778": 29, "2781": 10, "2783": 30, "2790": 2, "27m": 27, "28": [4, 9, 11, 16, 30, 32, 90, 97], "2818": 8, "282": 153, "28417889": 22, "2847": 27, "287": 153, "2870": 30, "288": [74, 153], "28840": 16, "2884000": 16, "2885": 22, "2888": 9, "2896": 27, "29": [4, 10, 11, 16, 27, 31, 112], "2912": 8, "2919": 22, "292": [31, 33, 152, 153], "294": 153, "2944": 28, "295": 153, "2952": 9, "2957": 30, "2975": 22, "298": 32, "2986": 3, "2997": 22, "2997373": 22, "2999": 31, "29m": 16, "2a": [1, 6, 20, 21, 24, 25, 26, 28, 29, 30, 32, 33, 36, 38, 41, 42, 43, 53, 54, 56, 75, 78, 89, 98, 99, 109, 121, 125, 128, 130, 136, 144, 146, 152, 153], "2d": [5, 146], "2darrai": 143, "2f": [4, 29, 30, 32], "2k": 16, "2m": [16, 27], "2x2": 116, "2\u03c0": 4, "3": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 30, 31, 32, 33, 44, 47, 49, 63, 66, 68, 72, 73, 74, 77, 80, 89, 93, 97, 98, 99, 103, 110, 114, 115, 131, 132, 133, 142, 149, 152, 153], "30": [2, 4, 5, 8, 9, 10, 11, 16, 27, 30, 31, 33, 80, 112, 113, 114, 116, 152], "3000": [11, 22, 31], "30167542": 22, "302": 11, "3025": 3, "302k": 16, "3036": 22, "30362263": 22, "304": [11, 153], "3043": 30, "3048106": 97, "305": 19, "3056": 28, "3076234": [10, 112], "308": 6, "3083": 31, "31": [5, 9, 10, 11, 16, 26, 27, 95], "3119": 3, "312": 153, "3125": 32, "3161489": 96, "31628": 144, "3169": 22, "3174": 30, "318": 153, "3194": 3, "3197419": 89, "31m": 16, "32": [4, 5, 9, 10, 11, 16, 26, 27, 46, 65, 89, 92, 100, 101, 115], "3220": 30, "3224": 8, "323": 11, "324": 11, "3253": 9, "3259": 3, "32600": 16, "3260000": 16, "327": 153, "3299": 3, "3299779": 22, "33": [9, 11, 16], "3300": 22, "3304": 30, "3319": 29, "333": 153, "3333": 3, "3362": 9, "3363": 9, "338": 11, "3380": 9, "3382": 9, "3389": 35, "339": [28, 33, 152], "3394": 9, "33it": 32, "33m": 16, "33mb": 27, "34": [4, 6, 9, 11, 16, 27, 29, 33, 152], "3406": 22, "3407": 9, "341": 153, "3429": 9, "342kb": 16, "3434": 9, "3448": 30, "3450": 9, "3459": 10, "3464": 11, "347": 153, "349": 153, "34m": 16, "35": [3, 4, 11, 16, 27, 28, 29, 31, 32], "350": 5, "3504": 9, "3513": 31, "353": 153, "3557": 30, "357355": 32, "35it": 32, "36": [3, 4, 9, 11, 16, 27, 28, 29, 32], "3600": [22, 80], "3613": 22, "3621": 29, "363": 11, "364": [3, 4, 28, 29, 32], "3644": 29, "3646": 28, "3648": 22, "365": 153, "3654": 2, "365749": 32, "367": 153, "368": 11, "3689": 9, "36it": 32, "36m": 16, "37": [9, 11, 16, 22, 26, 27, 29], "371": 153, "372": 9, "3730": 22, "373041": 22, "3739": 30, "374445": 32, "3746": 26, "375": 11, "375k": 16, "376": 11, "3762": 30, "377": 11, "3777": 30, "378": 153, "3793": 30, "3796": 22, "37m": 16, "38": [3, 4, 11, 16, 27, 28, 29, 30, 31, 32], "3829": 22, "383": 9, "3830": 30, "3850": 31, "3854": 28, "386": 18, "38658058": 22, "3865806": 22, "3866": [22, 30], "3868": 18, "3878": 22, "388": 153, "389": 153, "38m": 16, "39": [11, 16, 22], "390": 153, "391": 153, "3912": 22, "3913": 30, "392kb": 16, "3930": 8, "3931": 28, "3948": 3, "3957": 29, "396": [11, 13, 152], "397": 153, "3977": 30, "397kb": 27, "3986": 22, "399": 11, "3993": 9, "3996": 22, "39m": 16, "39mb": 27, "39th": [49, 50, 51, 52, 68], "3a6190": 29, "3d": [49, 68, 153], "3f": 30, "3h": 80, "3k": [16, 27], "3kb": 27, "3m": [16, 27], "3mb": 27, "4": [1, 3, 4, 5, 6, 7, 9, 10, 11, 13, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 33, 73, 74, 75, 77, 89, 90, 91, 93, 95, 96, 97, 98, 99, 100, 101, 102, 104, 105, 107, 108, 109, 111, 115, 116, 121, 124, 126, 128, 129, 130, 132, 133, 137, 138, 140, 144, 152], "40": [3, 4, 11, 14, 16, 26, 27, 28, 29, 31, 32, 90, 95, 109, 113], "400": [10, 11, 153], "400k": 91, "4013": 9, "402": 153, "4033": 9, "405": 11, "4058": 30, "406": 153, "4067": 110, "406kb": 16, "4076": 9, "4079": 110, "407kb": 27, "4087": 29, "409": 153, "40mb": 27, "41": [5, 11, 16, 27], "4101": 30, "4107": 30, "411": 153, "411kb": 16, "4121": [28, 29], "4122": 22, "412kb": 16, "413": 153, "4138": 30, "415": 153, "416kb": 16, "417": [79, 153], "417750": 32, "4190": 31, "41mb": 27, "42": [9, 11, 16, 27, 30], "4217": 29, "4221": 30, "422kb": 16, "423kb": 16, "424": 32, "424kb": 16, "425kb": 16, "426": [29, 33, 152], "428": [11, 153], "428kb": 16, "429": 153, "429kb": 16, "42m": 16, "43": [5, 10, 11, 16, 27], "431": 153, "4310": 29, "4326": 30, "432k": 27, "4333": 30, "4360": 30, "437836": 32, "438274": 32, "4383": 2, "4398": 22, "43it": 32, "44": [11, 16, 27, 33, 77, 152], "440kb": 16, "4418": 22, "442362": 32, "442473": 32, "4425": 30, "4429": 22, "4429058": 22, "443": 153, "4433": 22, "4455": [2, 30], "446": 153, "446kb": 16, "447": [3, 6, 152], "447024": 32, "4483": 30, "449kb": 16, "44m": 16, "45": [4, 5, 11, 16, 27, 29], "450": 16, "4500": 30, "4502": 2, "451": 153, "4514": 2, "4517": 9, "4518": 10, "452": 11, "4535": 22, "453kb": 16, "453x": 35, "454": 153, "4549": 27, "4564": 22, "456kb": 16, "45m": 16, "46": [5, 11, 16, 26, 27], "460": 153, "4604": 22, "4609": 30, "461": 153, "4621": 2, "4637": 9, "4638": 30, "463kb": 16, "4645": [2, 30], "464kb": 16, "465": 153, "4655": 3, "466": 153, "4660": 22, "4664": 22, "4668": 30, "467": 153, "4671": 2, "468": 153, "4680": 2, "469": 5, "4696": 29, "469kb": 16, "46m": 16, "47": [3, 4, 5, 9, 10, 11, 16, 27, 28, 29, 30, 32], "470": 153, "471": [49, 50, 51, 52, 68], "4712": 30, "472": 153, "473": 153, "4736": 2, "474": [49, 50, 51, 52, 68], "4753": 2, "4757": 3, "475k": 16, "475kb": 16, "4760": 10, "477kb": 16, "478137": 32, "4788": 9, "479": 153, "47it": 32, "48": [5, 10, 11, 16, 18, 20, 21, 27, 28, 29, 30, 32, 74, 98], "481kb": 16, "482": 11, "4822": 30, "4828": 30, "485": 153, "48550": 105, "4859": 30, "487": 153, "4870": 29, "488": 153, "4880": 5, "489": 153, "49": [11, 16, 27, 152], "490": 153, "4904": 30, "490kb": 16, "491": 153, "4919893741607666": 32, "491kb": 16, "4922": 5, "4928": 11, "4929": 10, "492kb": 16, "494": 153, "494kb": 16, "495": 153, "497": 153, "4985": 2, "498kb": 16, "49it": 32, "49m": 16, "4d": 153, "4f": 5, "4m": 16, "4mb": 27, "4th": 119, "5": [2, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 72, 74, 89, 90, 93, 94, 95, 97, 98, 100, 104, 105, 107, 108, 109, 110, 111, 112, 114, 116, 122, 131], "50": [3, 4, 5, 9, 10, 11, 14, 16, 19, 27, 28, 29, 32, 74, 93, 104], "500": [17, 19, 28, 133, 153], "500hz": 77, "500kb": 16, "503": 153, "5030": 5, "5033": 22, "5039": 28, "503kb": 16, "504": 153, "50407195": 22, "5041": 22, "505": 153, "505kb": 16, "5069": 27, "507kb": 16, "509kb": 16, "50it": 32, "50m": 16, "51": [4, 11, 16, 27], "5104": 8, "5111": 28, "511kb": 16, "512": [5, 11], "5120": 5, "513": 153, "5134": 2, "513kb": 16, "514": 153, "515": [11, 19, 23, 152, 153], "516186": 32, "5164": 5, "5169721": 22, "516kb": 16, "517": 153, "5170": 22, "5172": 22, "518kb": 16, "5196": 9, "51it": 32, "51m": 16, "52": [11, 16, 26], "520": [11, 153], "5201": 22, "520kb": 16, "5210943": 22, "5211": [5, 22], "5215": 5, "522": 11, "523": 153, "5234": 5, "52350": 16, "5235000": 16, "524": 153, "5245": 5, "5266": 3, "5269": 9, "5272": 5, "528": 153, "529": 153, "5294": 9, "529kb": 16, "52it": 32, "52m": 16, "53": [16, 22], "5307": 5, "5310": 2, "531kb": 16, "532kb": 16, "5333": 5, "533kb": 16, "534kb": 16, "535": 153, "536": 11, "5369": 30, "536kb": 16, "537kb": 16, "538": 153, "538kb": 16, "539": 153, "5391": [5, 27, 28, 29, 30, 31], "53910": 16, "5391000": 16, "5395": 22, "53it": 32, "54": [6, 16], "5400": 5, "541": 153, "5411": 29, "541kb": 16, "5420": [27, 28, 29, 30, 31], "5430": 11, "543kb": 16, "544kb": 16, "546": 153, "546kb": 16, "5472": 5, "5474": 30, "5478": 29, "547k": 16, "547kb": 16, "5486": 28, "5499": 5, "549kb": 16, "54it": 32, "54m": 16, "55": [5, 6, 11, 16, 27, 28, 29, 30, 152], "5500": 5, "5500m": 119, "5503989": 22, "5504": 22, "5505": 30, "550kb": 16, "551": 153, "5510": 22, "5518": 30, "5528": 30, "552kb": 16, "553": 153, "5536": 30, "5537": 30, "553kb": 16, "5540": 30, "5544": 30, "5547": 28, "5548": 30, "554kb": 16, "5552": 30, "556": 153, "5562": 30, "5565": 29, "556kb": 16, "5572": 30, "5574": 30, "5578": 30, "557kb": 16, "558kb": 16, "5598": 30, "559kb": 16, "55m": 16, "56": [4, 9, 11, 16], "5608": 5, "560kb": 16, "561": 153, "5612": 5, "5619": 22, "561kb": 16, "562": 5, "5625": 3, "562kb": 16, "563599": 32, "5641": 5, "564kb": 16, "565": 11, "5654": 30, "5656": 30, "565kb": 16, "566kb": 16, "5670986": 22, "5671": [9, 22], "5674": 31, "5676": 5, "56835277": 22, "5686": 22, "5686462": 22, "568kb": 16, "569": 153, "5695": 30, "5696": 29, "569kb": 16, "56it": 32, "57": [5, 14, 16, 26, 27], "570": 153, "570kb": 16, "5712": 5, "5714": 29, "571kb": 16, "572": 153, "572kb": 16, "573": 153, "5730": 5, "5739": 29, "573kb": 16, "5746": 5, "574kb": 16, "5755": 9, "575kb": 16, "5763": 30, "5765": 5, "5768": 9, "576kb": 16, "5772": 5, "577kb": 16, "578": 153, "5786": 9, "5787": 5, "578kb": 16, "579": 153, "5790": 5, "5792": 30, "5797": 5, "579kb": 16, "57m": 16, "58": [5, 11, 16], "5801": 30, "5807": 11, "580kb": 16, "581": 153, "5810": 30, "5813": 30, "5819": 30, "581kb": 16, "582": 153, "582kb": 16, "5838": 30, "583kb": 16, "584kb": 16, "585kb": 16, "5866": 11, "5868": 29, "586kb": 16, "5876": 9, "587kb": 16, "5884": 30, "5886": 2, "5889": 30, "588kb": 16, "589kb": 16, "59": [16, 27], "590": 153, "590kb": 16, "591": 153, "591kb": 16, "592": 153, "5920": 5, "5927": 9, "592kb": 16, "593": 153, "5936": 5, "5938": 5, "593kb": 16, "594": 153, "5940": 3, "5949": 30, "594kb": 16, "5950": 5, "5953": 22, "595kb": 16, "596kb": 16, "597": 153, "597kb": 16, "5982": 2, "598kb": 16, "599": 153, "5990": 5, "599kb": 16, "59it": 32, "59m": 16, "5e": 5, "5m": [16, 27, 91], "5mb": 27, "6": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 23, 26, 27, 28, 29, 30, 31, 32, 33, 48, 67, 74, 77, 95, 119, 152], "60": [5, 10, 12, 16, 19, 27, 32], "600": 153, "600kb": 16, "6011": 5, "6018": 30, "601kb": 16, "6026": 11, "602kb": 16, "603kb": 16, "604": 11, "6044": 30, "604kb": 16, "605kb": 16, "606": 153, "606kb": 16, "607": 153, "607kb": 16, "608": 153, "6087": 2, "6089": 22, "608kb": 16, "6090": 2, "6094": 5, "609kb": 16, "60_sleep": 80, "60m": 16, "61": [5, 9, 16, 26, 27], "610kb": 16, "611": 153, "6117": 5, "611kb": 16, "612": 153, "6120": 5, "6129": 11, "612kb": 16, "6134": 31, "613kb": 16, "6143": 30, "614kb": 16, "615": 153, "615kb": 16, "616kb": 16, "6170": 5, "6172": 5, "6175": 3, "6177": 5, "6179": 9, "617kb": 16, "6186": 30, "618kb": 16, "619": 153, "619kb": 16, "61m": 16, "62": [5, 14, 16, 26], "620": 11, "620kb": 16, "621": 153, "6213": 5, "621kb": 16, "62208": 74, "6227": 5, "6229": 22, "622kb": 16, "6235": 9, "6238": 5, "6239": 30, "623kb": 16, "624": 153, "6240": 5, "6246": 22, "624kb": 16, "625": 79, "6250": 5, "6251": 9, "6259": 5, "625kb": 16, "6263": 5, "6267": 22, "626kb": 16, "627": 153, "6272": 5, "6279": 22, "627kb": 16, "6281": 5, "6282": 22, "628kb": 16, "6291": 30, "6299": 30, "629kb": 16, "62m": [16, 27], "63": 16, "6304": 29, "6309": 5, "630kb": 16, "631": 153, "631kb": 16, "632": [13, 23, 152, 153], "6320": 5, "6322": 9, "6323": 5, "6328": 5, "632kb": 16, "633": [9, 12, 13, 17, 18, 19, 20, 21, 23, 33, 152], "6337": 9, "6339": 2, "633kb": 16, "634": [22, 31], "634kb": 16, "635": [10, 11, 13, 152, 153], "635kb": 16, "6368": 27, "636kb": 16, "637": 153, "6372": 9, "637kb": 16, "638": [11, 13, 152], "6389": 29, "638kb": 16, "639k": 16, "639kb": 16, "63m": 16, "64": [2, 3, 4, 8, 10, 11, 14, 16, 17, 19, 27, 28, 29, 32, 89, 92, 102, 104, 105, 111], "640": 153, "6406": 5, "6407": 29, "640kb": 16, "640x480": [27, 28], "641": 11, "641kb": 16, "642": 153, "6422": 5, "642kb": 16, "643": 153, "643kb": 16, "6440": 5, "644kb": 16, "645": 11, "645kb": 16, "646kb": 16, "6471": 28, "6475": 2, "647kb": 16, "6480": 5, "6485": 28, "648kb": 16, "6494": 29, "6496": 3, "649kb": 16, "65": [11, 16], "6509": 22, "650kb": 16, "6515615": 22, "6516": 22, "651kb": 16, "6526": 31, "6529": 2, "652kb": 16, "6533": 22, "653kb": 16, "654kb": 16, "655kb": 16, "6562": 5, "6565": 29, "656kb": 16, "657kb": 16, "658kb": 16, "659": [4, 6, 152], "65902848": 22, "659kb": 16, "65m": 16, "66": [5, 16], "660": 11, "660kb": 16, "661kb": 16, "662kb": 16, "663kb": 16, "6641": 5, "664kb": 16, "6652": 22, "66521484": 22, "665kb": 16, "666kb": 16, "6671": 22, "6676": 9, "667kb": 16, "668": [33, 152], "6680": 5, "6685": 22, "668kb": 16, "669": 26, "669kb": 16, "66it": 32, "67": [16, 116], "670kb": 16, "6719": 5, "671kb": 16, "672kb": 16, "673kb": 16, "674kb": 16, "6751": 5, "675kb": 16, "6760": 5, "676kb": 16, "677kb": 16, "678kb": 16, "6790": 9, "679kb": 16, "67it": 32, "67m": 16, "68": [5, 16], "6800": 5, "68056549": 22, "680kb": 16, "681kb": 16, "682kb": 16, "683e00": 29, "683kb": 16, "6840": 5, "684kb": 16, "685kb": 16, "6860": 9, "686kb": 16, "6875": 5, "6877": 9, "687kb": 16, "6880": 5, "688kb": 16, "6890": 22, "689kb": 16, "68m": 16, "68mb": 27, "69": [2, 3, 4, 5, 8, 9, 10, 12, 16, 27, 28, 29, 30, 32], "690kb": 16, "691kb": 16, "6920": 5, "692kb": 16, "693": [12, 13, 152], "693kb": 16, "695kb": 16, "6960": 5, "696kb": 16, "6978": 22, "697kb": 16, "698": 11, "6980": 31, "698kb": 16, "699kb": 16, "69m": 16, "6f": 32, "6m": [16, 27], "6mb": 27, "7": [2, 3, 4, 5, 6, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 33, 35, 77, 89, 98, 99, 110, 119, 122, 152], "70": [5, 16, 104], "70052629": 22, "700kb": 16, "7013": 5, "701kb": 16, "702kb": 16, "7031": 5, "70380673": 22, "703kb": 16, "7040": 5, "704kb": 16, "705kb": 16, "7063": 2, "706k": 16, "706kb": 16, "707": [6, 152], "7075": 22, "7076": 9, "707kb": 16, "708": 5, "7080": 5, "7085": 11, "7099": 30, "70m": 16, "71": [5, 16], "710": 95, "7109": 5, "710kb": 16, "7120": 5, "712kb": 16, "713kb": 16, "7149": 5, "7154": 9, "716": [30, 33, 152], "7160": 5, "718kb": 16, "719": 95, "72": [11, 16, 116, 132], "7200": [5, 10], "720kb": 16, "7216": 22, "725kb": 27, "726": 11, "727": 11, "7276": 22, "7280": 5, "73": 16, "733kb": 16, "7360": 5, "737kb": 16, "739kb": 27, "73m": 16, "73mb": 27, "74": [5, 16], "7400": 5, "7404": 22, "7419": 2, "7422": 5, "7427": 30, "7429778": 22, "7430": 22, "7443": 22, "7443461": 22, "7449": 9, "74m": 16, "75": [3, 4, 5, 9, 14, 16, 26, 27, 28, 29, 32, 90, 95, 109, 115], "750": 11, "7556": 30, "755817": 79, "7578": 5, "758": [5, 9, 10, 111], "75m": 16, "76": 16, "7629": 30, "7638324": 22, "7656": 5, "7664": 22, "7666": 22, "7673": 22, "769": [5, 9, 10, 111], "77": [5, 11, 16], "770": [32, 33, 152], "770k": 16, "7734": 5, "774": 23, "7754": 22, "7760": 11, "777": [16, 18], "77m": 16, "78": [16, 27, 80], "7808": 5, "7826": 2, "786": 11, "788": [16, 18], "7896": 5, "7898": 5, "78m": 16, "79": [5, 16], "7904": 5, "7910": 5, "7929": 31, "7944": 5, "7964": 5, "7965": 3, "797205": 32, "7993": 5, "7994": 5, "79it": 32, "7kb": 27, "7m": [16, 27], "7mb": 27, "8": [2, 3, 4, 5, 8, 9, 10, 11, 13, 14, 16, 17, 18, 19, 20, 21, 23, 26, 27, 28, 29, 30, 31, 32, 33, 89, 90, 91, 95, 97, 100, 101, 102, 104, 105, 107, 111, 129, 149, 152], "80": [3, 4, 5, 10, 11, 16, 19, 26, 27, 28, 29, 32, 77, 104, 112], "800": [12, 18], "8000": 22, "8001": 5, "8004": 5, "8022": 5, "8024": 22, "8036": 22, "804": 27, "8053": 5, "8059": 5, "8070": 5, "8078": 5, "8087": 5, "809": [10, 112], "8097": [5, 22], "80m": [16, 27], "81": [5, 16, 19, 27], "8100": 5, "8105": 5, "811": [21, 23, 152], "8122": 5, "8143": 5, "8148": 9, "816": 9, "8165": 5, "8174": 22, "818": [10, 112], "81m": 16, "82": [16, 44, 63], "8206": 22, "8218": 22, "822": 33, "8225": 2, "8263": [5, 31], "827": [26, 33, 152], "829": [6, 152], "82m": 16, "83": [11, 16, 22], "830": 4, "8304": 8, "8358": 5, "836k": 16, "837": [8, 13, 152], "83it": 32, "84": [11, 16], "840": 26, "8419": 22, "844": 26, "85": [16, 27, 28, 29], "8501": 29, "8516": 22, "855": [20, 23, 152], "8585": 22, "8587": 30, "85m": 16, "86": [5, 11, 16, 27], "86039335": 22, "8604": 22, "863": [11, 30, 33, 152], "864": 29, "865": [28, 33, 152], "8677": 30, "8693": 29, "86it": 32, "87": [2, 5, 16, 31, 100], "871": [48, 67], "8740": 29, "875": [46, 65], "8757": 29, "876": 11, "8772": 29, "8782": 29, "87it": 32, "87m": 16, "88": [5, 16, 27], "880": 77, "8815": 10, "882": 26, "8839": 29, "8858": 29, "886": [46, 65], "8881": 8, "889k": 27, "88m": 16, "89": [10, 16], "890": [48, 67], "8904": 9, "8922": 29, "8924": 5, "8943": 22, "898": 11, "8k": 27, "8m": [16, 27], "8mb": 27, "9": [2, 3, 4, 5, 6, 8, 9, 10, 11, 16, 17, 18, 19, 20, 21, 26, 27, 28, 29, 32, 74, 77, 79, 90, 91, 92, 98, 104, 107, 108, 116, 123, 152], "90": [5, 16, 29, 30, 146], "901k": 16, "902958": 32, "90it": 32, "90k": 16, "90m": 16, "91": [11, 16, 27], "912": 11, "912368": 32, "9132": 22, "92": 16, "921907": 32, "9222": 29, "9235": 29, "9237": 31, "924": 26, "9252": 29, "9266": 22, "9292": 22, "92922518": 22, "9292252": 22, "92m": 16, "93": [11, 16, 27, 44, 63], "9305": 29, "9309": 30, "9353": 22, "935963004": 107, "936484": 32, "939559": 22, "9396": 22, "93it": 32, "93m": 16, "94": [11, 16, 29], "940": [16, 23, 152], "9404": 10, "9406": 22, "9423": 30, "9438": 2, "9481": 22, "94m": 16, "95": [12, 16, 27, 72, 131], "9512": 30, "9570": 30, "95m": 16, "96": [16, 27], "960": 11, "9618": 2, "963": 77, "96330007": 22, "9662": 9, "967k": 16, "96it": 32, "96m": 16, "97": 16, "9711": 22, "972": [32, 33, 152], "9752": 10, "976": [26, 27], "978": 31, "98": 16, "980": [16, 23, 152], "9819": 28, "9825": 22, "9858": 29, "9859": 8, "988": [5, 6, 152], "9883": 22, "98m": 16, "99": 16, "990": 31, "994": [17, 19], "9942": 22, "996": 26, "9991178": 95, "99it": 32, "9m": [16, 27], "9mb": 27, "A": [2, 3, 4, 5, 8, 9, 10, 16, 27, 28, 29, 30, 31, 34, 36, 38, 39, 42, 46, 56, 58, 60, 62, 65, 72, 73, 75, 78, 79, 81, 82, 90, 94, 96, 97, 98, 100, 101, 102, 104, 110, 111, 115, 119, 123, 124, 125, 130, 131, 134, 142, 146, 153], "And": [26, 27], "As": [5, 16, 26, 27, 29, 72, 131], "At": [27, 74], "But": [29, 32], "By": [29, 30, 31, 47, 72, 131], "For": [2, 4, 5, 8, 14, 26, 27, 28, 29, 32, 72, 116, 119, 123, 131, 133, 139, 141, 144, 148, 149, 150, 151], "If": [2, 8, 14, 18, 19, 22, 26, 29, 30, 32, 35, 37, 47, 48, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 120, 121, 122, 123, 124, 125, 129, 130, 131, 132, 134, 135, 139, 140, 141, 142, 147, 151], "In": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 18, 20, 21, 26, 27, 28, 29, 30, 32, 37, 44, 47, 49, 50, 51, 52, 54, 57, 63, 66, 68, 70, 72, 74, 91, 119, 120, 123, 131, 144], "It": [2, 3, 4, 5, 8, 9, 10, 11, 18, 27, 28, 29, 30, 32, 42, 48, 62, 72, 75, 83, 86, 91, 112, 125, 131, 148], "NO": 5, "No": [11, 19, 26, 29, 32, 74], "Not": [19, 26], "On": [4, 27, 30, 31, 76, 83], "One": [29, 30, 74, 97], "The": [2, 3, 4, 5, 8, 10, 11, 12, 14, 16, 18, 20, 21, 26, 27, 29, 30, 31, 32, 36, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 54, 61, 72, 74, 75, 76, 77, 79, 83, 89, 90, 91, 92, 95, 97, 98, 101, 102, 103, 104, 105, 106, 107, 108, 110, 112, 113, 116, 117, 118, 119, 120, 122, 123, 129, 131, 141, 142, 146, 149, 151], "Then": 128, "There": [4, 24, 26, 93, 109, 149, 151], "These": [2, 5, 8, 26, 27, 28, 30, 122], "To": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 17, 22, 26, 27, 28, 29, 30, 31, 32, 107, 119, 150, 151], "Will": 54, "With": [10, 112], "_": [3, 5, 14, 16, 17, 26, 27, 28, 31, 32], "__doc__": 26, "__getitem__": [5, 72, 131], "__init__": [5, 32], "__len__": [72, 131], "__name__": 12, "__str__": 26, "__version__": [147, 151], "_causalconv1d": 10, "_check_optimize_result": 5, "_classif": 10, "_criteria": [72, 131], "_data": 31, "_decoderblock": 11, "_encoderblock": 11, "_encoderlay": 10, "_frequency_shift": 153, "_lazydatafram": 124, "_logist": 5, "_modul": [72, 131], "_mrcnn": 10, "_multiheadedattent": 10, "_nestedsequ": [84, 124, 125], "_optim": [72, 131], "_path": 73, "_positionwisefeedforward": 10, "_return_pair": 5, "_scalartype_co": [84, 127, 128], "_sebasicblock": 10, "_selay": 10, "_sublayeroutput": 10, "_supportsarrai": [84, 124, 125], "_t": [127, 128], "_tce": 10, "_tuhmock": [12, 22], "_warn_prf": 10, "a1": 12, "a2": 12, "a_max": 12, "a_min": 12, "aasm": [5, 9, 10, 11], "ab": [4, 5, 47, 66, 104, 141], "abb7a7": 115, "abbassalami": 96, "abbrevi": [3, 4, 18, 20, 21, 29, 30], "abl": [2, 3, 4, 5, 8, 9, 10, 11, 12, 27, 28, 30, 72, 131, 147], "ablat": 104, "abnorm": [14, 79, 82, 91], "about": [8, 9, 10, 12, 26, 30, 76, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 144, 147], "abov": [3, 14, 16, 22, 27, 29, 147, 149], "absolut": [43, 107], "acc": [5, 29, 32], "acceler": [72, 131], "accept": [72, 86, 125, 131], "accepted_bads_ratio": [86, 125], "access": [5, 9, 10, 11, 12, 14, 26, 90, 91, 92, 96, 107, 108, 124, 133, 149], "accident": 153, "accommod": 14, "accord": [40, 59, 123], "accordingli": [9, 26, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 117], "account": [5, 75, 124, 130], "accumul": 32, "accur": [98, 105], "accuraci": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 139, 153], "accuracyof": 4, "achiev": [5, 9, 10, 11, 104], "acoust": 74, "acquir": 77, "acquisit": 119, "across": [113, 115, 123, 132, 136], "act": [16, 123], "action": 153, "activ": [4, 10, 19, 26, 48, 67, 72, 77, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 153], "activation_first_conv_nonlin": 93, "activation_larg": 94, "activation_later_conv_nonlin": 93, "activation_mrcnn": 112, "activation_pool_nonlin": [26, 109], "activation_smal": 94, "activation_transfor": 95, "actual": [3, 5, 12, 14, 22], "ad": [19, 27, 75, 79, 81, 82, 90, 91, 95, 104, 107, 108, 115, 116, 117, 118, 119, 120, 122, 123, 130, 153], "adam": [5, 9, 10, 11, 14, 31], "adamo": 97, "adamw": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "adapt": [9, 11, 16, 96, 97, 107, 112, 114, 115], "adaptiveavgpool1d": [10, 115], "add": [3, 4, 5, 11, 26, 27, 28, 29, 32, 43, 44, 61, 63, 72, 75, 76, 83, 107, 119, 131, 139, 153], "add_log_softmax": [2, 8, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "add_physician_report": [12, 22, 81, 82], "add_safe_glob": 5, "addit": [2, 8, 12, 17, 20, 21, 26, 28, 29, 30, 32, 44, 63, 72, 74, 75, 76, 83, 86, 90, 125, 131, 146], "addition": [12, 18, 26, 35, 72, 131, 142], "address": [42, 62], "adjust": [4, 26, 29, 32, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116], "adjustmenty": 32, "admiss": 37, "advanc": [27, 97, 113, 149], "advanced_train": [6, 152], "advantag": [16, 29, 97], "advis": [3, 27, 30, 42, 62, 131], "aertsen": [27, 28, 29, 30], "affect": [14, 27, 139], "affin": 10, "afr": [10, 112], "after": [5, 12, 16, 21, 26, 28, 29, 32, 74, 80, 90, 93, 109, 110, 111, 113, 122, 136, 139, 153], "after_reduced_cnn_s": 112, "afterward": [27, 29, 89, 90, 95, 98, 123], "ag": [5, 12, 18, 22, 74, 77, 79, 81, 82], "again": [18, 22, 29], "agcl": 74, "aggreg": [4, 90, 95], "aggregate_predict": [2, 72, 131], "aggregate_proba": 153, "ah": [9, 10, 11], "ai": [92, 144], "aim": [21, 22, 104], "ain": 79, "al": [9, 10, 11, 26, 46, 65, 77, 89, 90, 91, 92, 93, 94, 95, 96, 98, 100, 101, 102, 103, 104, 105, 106, 108, 109, 110, 111, 112, 114, 115, 116, 139], "alamgir": 79, "alex": 153, "alexandr": [28, 29, 30, 35], "algorithm": [14, 26, 28, 29, 30, 32], "alia": [26, 89, 93, 94, 95, 96, 97, 98, 101, 102, 103, 109, 110, 111, 112, 114, 115, 116], "all": [2, 3, 4, 8, 12, 14, 16, 24, 26, 27, 28, 29, 30, 32, 43, 44, 46, 54, 61, 63, 65, 70, 72, 73, 74, 77, 78, 80, 89, 90, 95, 97, 98, 99, 107, 117, 119, 120, 122, 123, 124, 125, 131, 139, 152, 153], "all_dataset": 29, "all_n_job": 16, "all_n_rec": 16, "all_result": 14, "allow": [3, 5, 14, 26, 29, 30, 32, 41, 72, 78, 86, 97, 104, 107, 125, 131, 153], "allowlist": 5, "almost": 79, "along": [26, 76, 83, 122, 150, 153], "alpha": [5, 9, 10, 11, 12, 47], "alreadi": [2, 3, 5, 8, 9, 10, 11, 14, 19, 27, 28, 29, 75, 76, 83, 130, 131, 147, 149], "also": [3, 4, 5, 9, 10, 11, 12, 14, 18, 21, 26, 28, 35, 72, 83, 95, 97, 112, 119, 120, 122, 131, 142, 147, 150, 151], "alsulaiman": 89, "altaheri": 89, "altern": [5, 26, 32, 72, 131], "although": [3, 72, 89, 90, 95, 98, 131], "alwai": [5, 29, 32, 35, 56, 72, 131], "amar": [5, 9, 10, 11], "among": 112, "amount": [9, 10, 11, 16, 122], "amp": 97, "amper": [72, 131], "ampli_init_valu": 113, "amplifi": 74, "amplitud": [43, 61, 113, 124, 125, 153], "amplitude_c": 113, "amplitur": 107, "an": [2, 5, 8, 9, 10, 12, 14, 16, 18, 19, 20, 21, 22, 26, 27, 29, 30, 32, 41, 49, 50, 51, 52, 56, 72, 74, 76, 77, 79, 83, 86, 89, 90, 91, 93, 94, 96, 97, 98, 99, 103, 104, 105, 106, 107, 109, 110, 111, 112, 114, 116, 118, 119, 121, 122, 123, 125, 131, 133, 139, 147, 148, 153], "analaysi": [7, 24], "analog": [29, 139], "analys": [2, 8, 29, 30, 73], "analysi": [4, 5, 9, 10, 11, 26, 35, 90, 148], "analyz": 30, "andreu": 96, "angl": [49, 50, 51, 52, 68, 146], "ani": [5, 17, 18, 26, 27, 29, 32, 72, 78, 84, 92, 108, 112, 119, 123, 124, 125, 127, 128, 131, 151], "ann": 153, "annot": [9, 10, 11, 18, 19, 21, 27, 28, 29, 30, 32, 79, 119, 153], "annual": [49, 50, 51, 52, 68], "anonym": 147, "anoth": [5, 21, 29, 32, 134], "answer": [29, 32], "anyth": [27, 72], "anywher": [72, 131], "apart": 5, "api": [26, 151], "appear": [9, 10, 11, 74], "append": [2, 8, 12, 14, 16, 27, 28, 31, 72, 119, 131], "appli": [2, 3, 4, 5, 8, 9, 10, 12, 16, 18, 19, 20, 26, 27, 28, 29, 30, 32, 36, 37, 38, 39, 40, 42, 43, 44, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 72, 76, 83, 90, 91, 92, 94, 95, 96, 101, 103, 104, 107, 108, 110, 111, 112, 113, 114, 115, 116, 119, 121, 123, 129, 130, 131, 141, 153], "applic": [83, 119], "applied_exampl": [13, 152], "apply_batch_norm": [5, 110, 111], "apply_funct": 121, "apply_on_arrai": [9, 10, 12, 121], "apply_proj": 123, "approach": [4, 5, 9, 10, 11, 16, 24, 30, 46, 48, 65, 67, 112, 132], "appropri": [35, 150], "approv": 77, "approx": 77, "approxim": [10, 50, 51, 52], "ar": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 19, 20, 22, 24, 26, 27, 28, 29, 30, 31, 32, 35, 37, 47, 66, 72, 75, 83, 84, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 123, 124, 125, 129, 131, 134, 136, 140, 147, 149, 150, 151, 153], "arang": [2, 8], "arbitrari": 5, "architectur": [2, 5, 8, 9, 10, 11, 26, 27, 28, 30, 72, 90, 91, 94, 95, 104, 107, 108, 110, 111, 112, 116, 131, 148], "arg": [72, 99, 131, 153], "argmax": 32, "argument": [3, 4, 16, 19, 26, 29, 32, 36, 38, 39, 40, 42, 48, 53, 55, 56, 72, 78, 117, 119, 120, 121, 122, 123, 129, 131, 139, 153], "aris": 16, "aristimunha": [4, 153], "armchair": 74, "arnal": [5, 9, 10, 111], "around": [4, 10, 32, 49, 50, 51, 52, 68, 91, 125, 132], "arrai": [2, 4, 8, 11, 17, 22, 26, 28, 29, 30, 37, 48, 49, 56, 57, 67, 68, 72, 84, 85, 86, 119, 120, 121, 122, 131, 135, 142, 146], "arrow": [74, 77], "articl": [26, 35], "artifici": 4, "arxiv": [4, 5, 31, 37, 38, 39, 40, 42, 44, 47, 54, 57, 58, 59, 60, 62, 63, 66, 70, 90, 101, 102, 104, 105, 107, 114, 134, 141], "as_tensor": 3, "ascend": [79, 81, 82], "ask": [35, 74], "assert": [2, 3, 4, 8, 14, 27, 28, 29, 30, 32], "assign": [27, 28, 143], "assist": 97, "associ": 97, "assum": [14, 26, 72, 117, 131, 136, 140, 153], "astyp": [9, 10], "asynchron": [46, 65], "atcnet": [26, 153], "aten": 11, "att_depth": 95, "att_drop_prob": 95, "att_dropout": 89, "att_head": 95, "att_head_dim": 89, "att_num_head": [89, 91, 107], "attempt": [26, 89, 90, 91, 93, 94, 99, 103, 105, 106, 107, 109, 110, 111, 112, 114, 116, 123], "attent": [10, 89, 90, 91, 95, 107, 112], "attention_mod": 90, "attentionbasenet": [26, 153], "attenu": [16, 119], "attn_drop_r": 107, "attn_head_dim": 107, "attnsleep": 112, "attribut": [2, 8, 26, 28, 29, 30, 32, 72, 76, 83, 121, 131, 153], "attributeerror": 72, "aug": [26, 35, 93, 103, 106, 109, 146], "augment": [1, 6, 24, 75, 78, 95, 99, 109, 121, 125, 128, 130, 144, 148, 152, 153], "augmenteddataload": [3, 4, 153], "author": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31, 35, 92, 95, 96, 97, 98, 100, 101, 102, 104, 108, 113], "auto": [3, 4, 8, 14, 17, 19, 26, 28, 29, 30, 32, 72, 93, 95, 101, 102, 103, 109, 119, 122, 123, 131, 153], "auto_exampl": [6, 13, 23, 33, 34], "auto_examples_jupyt": 24, "auto_examples_python": 24, "auto_tutori": 80, "autocorrel": 5, "autoencod": 116, "autom": [14, 29], "automat": [12, 14, 26, 48, 73, 92, 94, 115, 123, 153], "avail": [2, 3, 4, 8, 9, 10, 11, 12, 14, 16, 19, 22, 26, 27, 28, 29, 30, 32, 73, 80, 90, 91, 95, 97, 104, 112, 124, 125, 132, 133], "avenu": 5, "averag": [10, 12, 27, 29, 31, 32, 72, 89, 90, 99, 104, 123, 131, 136], "avg": [5, 9, 10, 11], "avg_pool": 10, "avg_pool_block4": 100, "avg_pool_block5": 100, "avgpool1d": 11, "avgpool2d": [3, 4, 26, 27, 28, 29, 32], "avoid": [5, 9, 10, 11, 12, 14, 16, 22, 27, 29, 80, 153], "awar": [37, 44, 54, 57, 63, 70], "ax": [2, 3, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 31, 99], "ax1": [2, 5, 8, 9, 10, 11, 27, 28], "ax2": [2, 5, 8, 9, 10, 11, 27, 28], "axhlin": 12, "axi": [2, 3, 5, 8, 27, 28, 31, 49, 50, 51, 52, 53, 55, 68, 69, 71, 99, 122, 143], "azemi": [37, 44, 54, 57, 63, 70], "b": [5, 9, 10, 11, 16, 27, 40, 59, 90, 91, 92, 95, 101, 102, 104, 108, 116], "ba": 31, "back": 77, "backend": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 144, 153], "backtick": 147, "backward": [3, 4, 11, 14, 26, 27, 28, 29, 32, 99, 119], "bad": [10, 14, 19, 119, 120, 123, 147], "bad_acq_skip": 119, "bahri": 97, "bai": 114, "bai2018": 114, "baka": 97, "bal": 5, "balanc": [5, 9, 10, 11, 132, 153], "balanced_accuraci": [9, 10], "balanced_accuracy_multi": 11, "balanced_accuracy_scor": [5, 11], "balancedsequencesampl": 153, "ball": [26, 27, 28, 29, 30, 31, 35, 77, 93, 103, 106, 109, 146], "band": [37, 57, 119, 129, 153], "bandpass": [2, 3, 4, 8, 20, 27, 28, 29, 30, 32, 74, 119, 129], "bandwidth": [16, 37, 57], "bang": 107, "banvil": [4, 5, 9, 14, 16, 20, 134, 153], "banville2020": 134, "bao": 107, "bar": 4, "barach": [28, 29, 30], "barh": [12, 29], "barmpa": 97, "base": [0, 2, 3, 4, 5, 8, 9, 10, 12, 16, 18, 20, 21, 27, 28, 29, 30, 31, 32, 36, 44, 46, 47, 48, 63, 65, 66, 67, 72, 74, 75, 89, 90, 91, 94, 95, 96, 97, 98, 101, 102, 108, 112, 113, 117, 119, 120, 122, 124, 125, 131, 133, 141, 153], "baseconcatdataset": [2, 5, 9, 10, 12, 14, 16, 21, 31, 72, 84, 85, 86, 87, 124, 125, 130, 131, 133, 142, 153], "basedataset": [31, 36, 75, 83, 87, 130, 153], "baseepoch": [83, 85, 121], "baselin": [19, 26, 104, 113], "baseraw": [76, 86, 121, 129], "basic": [15, 27, 29, 32, 33, 56, 75, 78, 98, 99, 109, 121, 125, 128, 130, 144, 146, 152, 153], "batch": [3, 4, 5, 26, 30, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 68, 69, 70, 71, 72, 93, 94, 99, 104, 106, 107, 108, 109, 110, 111, 112, 114, 115, 131, 138, 142, 153], "batch_i": 22, "batch_idx": 32, "batch_ind": 22, "batch_loss": 32, "batch_norm": [14, 26, 93, 108, 109], "batch_norm_alpha": [14, 26, 93, 97, 103, 109], "batch_norm_epsilon": 103, "batch_siz": [2, 3, 4, 5, 8, 9, 10, 11, 14, 22, 27, 28, 29, 30, 31, 32, 37, 47, 49, 57, 66, 68, 72, 91, 92, 94, 95, 99, 100, 104, 105, 106, 108, 110, 111, 112, 113, 114, 115, 131, 136, 140, 142, 145], "batch_x": [5, 22], "batchnorm1d": [10, 11], "batchnorm2d": [3, 4, 26, 27, 28, 29, 32, 93, 97, 109], "batchscor": [72, 131], "bbci": 73, "bbox_to_anchor": 29, "bcewithlogitsloss": [5, 72, 131], "bci": [2, 4, 8, 21, 26, 27, 28, 29, 30, 42, 46, 62, 65, 73, 74, 89, 98, 104, 107, 115], "bci2000": 77, "bcic": [1, 6, 7, 13, 20, 24, 25, 29, 32, 33, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 78, 99, 109, 121, 124, 125, 126, 128, 130, 136, 137, 138, 140, 144, 146, 152, 153], "bcicomp": 8, "bcicompetitionivdataset4": [2, 8, 153], "bd_cmap": 29, "bear": 147, "becaus": [2, 16, 26, 27, 29, 30, 147, 153], "becom": [14, 16, 29], "been": [2, 3, 4, 8, 10, 14, 16, 18, 20, 21, 27, 28, 29, 30, 32, 92, 96, 97, 98, 99, 100, 101, 102, 108, 113, 141, 147, 151, 153], "beetl": 97, "befor": [2, 11, 16, 27, 28, 29, 30, 32, 72, 75, 76, 80, 83, 89, 93, 94, 95, 110, 111, 112, 127, 128, 131, 139, 144, 150, 153], "beforehand": 19, "begin": [2, 27, 29, 30, 74, 110, 119, 124], "beginn": 149, "behavior": [10, 32, 72, 119, 131, 153], "behaviour": [2, 8, 73], "behind": [29, 32], "being": [4, 10, 14, 27, 72, 77, 131], "beit": 107, "beitv2": 107, "below": [3, 5, 35, 37, 147, 150], "benchmark": [2, 3, 4, 5, 8, 9, 10, 11, 15, 23, 24, 27, 28, 29, 30, 31, 32, 75, 80, 82, 93, 100, 109, 121, 124, 130, 144, 152, 153], "benchmark_lazy_eager_load": [14, 23, 152], "benefici": 28, "benini": 105, "best": [1, 6, 24, 32, 36, 38, 42, 54, 56, 75, 78, 99, 109, 121, 125, 128, 130, 144, 152], "best_aug": 4, "best_estimator_": 4, "best_paramet": 29, "best_run": [4, 29, 30], "beta": [47, 113], "beta_init_valu": 113, "beta_per_sampl": 47, "better": [2, 5, 8, 10, 14, 16, 27, 28, 29, 32, 95, 139, 153], "between": [2, 3, 4, 5, 8, 9, 11, 26, 27, 28, 29, 37, 38, 39, 42, 43, 47, 49, 50, 51, 52, 56, 57, 58, 60, 62, 66, 74, 84, 85, 86, 90, 93, 95, 104, 109, 110, 117, 124, 125, 135, 140], "beyond": [31, 47, 66, 141], "bia": [9, 10, 11, 107, 108], "bias": 29, "bidirect": 94, "big": [7, 13, 24, 75, 81, 121, 124, 130, 152, 153], "bigger": 12, "bin": 12, "biologi": [49, 50, 51, 52, 68], "biomed": [5, 100], "biosign": [37, 44, 54, 57, 63, 70, 91, 92, 108], "biot": [26, 92, 108, 153], "biotencod": 91, "bipolar": 123, "birbaum": [27, 28, 29, 30], "biswal": [40, 59], "black": [2, 8, 12, 27, 28, 74, 77, 146, 153], "blackman": 119, "blanco": 110, "blanco2020": 110, "blob": 5, "block": [89, 90, 92, 97, 98, 100, 104, 105, 107, 108, 114, 116], "block_lay": 108, "block_postskip": 11, "block_prepool": 11, "block_preskip": 11, "blue": [2, 5, 8, 16, 27, 28], "bme": [9, 10, 11], "bn1": 10, "bn2": 10, "bnci": [4, 74], "bnci2014": [3, 4, 18, 20, 21, 29, 30, 74], "bnci2014001": [3, 4, 18, 20, 21, 29, 30], "bnci2014_001": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32], "bnorm": [3, 4, 26, 27, 28, 29, 32], "bold": 146, "bonsmann": 153, "bool": [14, 26, 42, 47, 49, 50, 51, 52, 62, 68, 72, 73, 75, 76, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 93, 94, 95, 96, 97, 98, 99, 101, 103, 106, 107, 108, 109, 110, 111, 112, 114, 115, 116, 117, 119, 120, 121, 122, 123, 124, 125, 129, 130, 131, 134, 135, 139, 142, 144, 146], "boost": 5, "bose": 98, "both": [4, 5, 16, 22, 30, 74, 77, 110, 111, 116], "bottleneck": [16, 32, 97, 115], "bottleneck_s": 108, "bottom": 11, "bouallegu": [104, 153], "box": [72, 131], "boxcar": 122, "br": 4, "brain": [4, 24, 25, 26, 27, 29, 30, 31, 33, 35, 48, 67, 75, 78, 79, 93, 97, 99, 101, 102, 103, 105, 106, 107, 109, 121, 125, 128, 130, 144, 146, 148, 152], "braincod": 150, "braindecod": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 33, 149, 150, 152, 153], "branch": 98, "brandt": [3, 20, 153], "braun": [27, 28, 29, 30], "break": [20, 74], "brodbeck": 35, "brook": 35, "bruna": 153, "brunner": [27, 28, 29, 30], "bruno": [4, 153], "bsd": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31], "bug": 99, "build": [12, 27, 32, 149, 151], "built": [35, 147], "bundl": 14, "burgard": [27, 28, 29, 30, 35], "butt": 79, "butterworth": 119, "byte": [84, 124, 125], "c": [4, 5, 9, 10, 11, 20, 27, 28, 29, 30, 42, 62, 91, 92, 94, 97, 98, 101, 102, 107, 108, 113, 116, 132, 147], "c0": 4, "c1": 4, "c2": 4, "c3": [12, 26], "c4": [12, 26], "c_tuab": 82, "c_tueg": [12, 81], "ca": 115, "cach": [72, 131, 153], "cache_config": 78, "cagig": 97, "cakmak": [42, 62], "cal": 26, "calc_pad": 100, "calcul": [2, 3, 4, 27, 28, 29, 30, 32, 72, 100, 115, 131], "calibr": [48, 67], "call": [3, 16, 26, 27, 29, 32, 72, 75, 83, 86, 89, 90, 95, 98, 117, 121, 124, 125, 131, 137, 138, 139], "callabl": [3, 26, 41, 56, 72, 75, 76, 83, 93, 109, 121, 131, 139], "callback": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 72, 131, 139], "callbacks_": [72, 131], "callbacks__print_log__keys_ignor": [72, 131], "callbacks__valid_acc": 11, "camelcas": 0, "can": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 21, 22, 26, 27, 28, 29, 30, 32, 35, 43, 49, 68, 72, 75, 79, 80, 81, 82, 83, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 118, 119, 120, 122, 123, 131, 142, 149, 150, 153], "candid": [4, 29, 30], "cannot": [2, 3, 4, 5, 8, 9, 10, 11, 12, 27, 28, 29, 30, 32, 72, 117, 131], "canon": 35, "capabl": [12, 16, 29, 32, 72, 131], "capac": [29, 30, 90], "capit": 10, "captur": 112, "care": [89, 90, 95, 98], "carin": 113, "carlson": 113, "carri": [39, 60, 74], "cartesian": [49, 68], "case": [2, 5, 8, 16, 21, 26, 27, 28, 29, 30, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 123, 131, 144, 150, 153], "cast": [4, 41], "cat": 90, "categor": [4, 132], "categori": [2, 4, 31], "catlit": 90, "catplot": 14, "caus": [2, 8], "causal": [16, 119], "cavigelli": 105, "cbam": 90, "cbar": 30, "cd": 151, "cdot": [127, 128], "cedric": [3, 4, 153], "ceil": [9, 10, 115], "ceil_mod": [9, 10], "cell": 4, "center": [2, 8, 9, 10, 29, 37, 57], "certain": [72, 90, 131], "certif": 27, "ch": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "ch_dim": 90, "ch_name": [12, 14, 17, 26, 84, 118, 129], "ch_po": [49, 68], "ch_type": [12, 26, 123], "challeng": 113, "chambon": [5, 9, 10, 111], "chambon2018": [7, 13, 24, 75, 80, 99, 111, 121, 125, 130, 133, 135, 144, 146, 152], "chan": [2, 3, 4, 8, 27, 28, 29, 30, 32, 74, 77], "chanc": [5, 9, 10], "chang": [2, 5, 8, 14, 18, 31, 45, 72, 91, 119, 123, 131, 139, 151], "channel": [2, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 38, 39, 40, 42, 43, 44, 46, 47, 49, 50, 51, 52, 54, 58, 59, 60, 61, 62, 63, 65, 66, 68, 70, 80, 81, 82, 83, 84, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 118, 119, 120, 123, 124, 125, 129, 153], "channel_indep": [42, 62], "channel_wis": [5, 9, 10, 11, 16], "channelsdropout": 4, "character": 16, "characterist": 113, "chat": 147, "check": [2, 3, 4, 8, 9, 10, 11, 26, 27, 28, 29, 30, 32, 35, 89, 92, 93, 95, 96, 97, 98, 99, 100, 101, 102, 103, 106, 108, 109, 110, 113, 114, 115, 116, 147, 150, 153], "checker": 153, "checkpoint": [5, 32], "checkpoint_connector": 32, "chehab": [4, 5, 11, 134, 153], "chen": 100, "cheng": [37, 44, 54, 57, 63, 70], "chenxiachan": 100, "chevalli": [97, 153], "choic": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32, 90, 95, 104, 153], "choos": [2, 3, 4, 8, 18, 27, 28, 29, 30, 32], "chose": 3, "chosen": [2, 16, 18, 27, 32, 46, 54, 72, 119, 131, 142], "christian": 35, "christoph": 30, "chronolog": [12, 79, 81, 82], "chs_info": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131], "ci": 153, "cifar10": [47, 66, 141], "circl": 16, "circul": [5, 9, 10, 11], "ciss": [47, 66, 141], "cite": [2, 8, 73], "ckpt": 32, "ckpt_path": 32, "cl": 107, "clariti": 153, "class": [0, 3, 4, 5, 9, 10, 11, 12, 14, 18, 20, 21, 26, 27, 28, 29, 30, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 62, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 146, 153], "class_nam": [9, 10, 11, 27, 28, 146], "class_names_fonts": 146, "class_weight": [5, 9, 10, 11], "classes_": 72, "classic": 28, "classif": [5, 9, 10, 11, 26, 27, 30, 37, 42, 44, 54, 57, 62, 63, 70, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115], "classifi": [3, 4, 5, 9, 10, 11, 26, 29, 31, 107, 153], "classification_report": [5, 9, 10, 11], "classificationhead": [90, 91, 95], "claus": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26], "clear": 16, "clench": 77, "clf": [3, 4, 5, 9, 10, 11, 27, 28, 29, 30], "clf_pipe": 5, "clifford": [42, 62], "cliffordlab": [42, 62], "clinic": [4, 5, 7, 24, 80, 134], "clip": 12, "clone": [112, 153], "cloneabl": 153, "close": [5, 16, 18, 134, 147], "cluster": 90, "cm": [74, 146], "cmap": 30, "cmsaugment": [38, 39, 58, 60], "cnn": [108, 112], "cnosid": 8, "co": [40, 59, 113], "code": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 95, 96, 97, 100, 104, 107, 112, 113, 114, 115, 147, 149, 151, 153], "code2023": [91, 92, 108], "code2024": 107, "codebas": 153, "codeicassp2025": 113, "codeword": 90, "coeffici": [2, 8, 47, 66, 141], "cognit": [7, 24], "coil_typ": 26, "col": 14, "col_nam": 99, "cold": [72, 131], "collabor": 90, "collect": [26, 72, 77, 131], "color": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 146], "colormap": [5, 146, 153], "column": [2, 8, 19, 21, 22, 27, 28, 29, 30, 32, 75, 83, 87, 99, 132, 133, 146], "com": [2, 3, 5, 8, 9, 10, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31, 74, 77, 81, 82, 151], "combin": [14, 16, 75, 105], "combinedconv": [3, 4, 26, 27, 28, 29, 32], "come": [2, 8, 14, 28, 30, 32, 135, 144], "comfort": 74, "command": [150, 151], "commit": 153, "committe": 77, "common": [12, 14, 123, 150, 153], "commonli": 3, "compact": [29, 101, 102], "compar": [5, 14, 16, 22, 27, 29, 32, 90], "comparison": [4, 14, 27, 28], "compat": [3, 14, 17, 19, 30, 72, 84, 85, 86, 119, 131, 153], "compens": [29, 119], "competit": [2, 4, 8, 11, 14, 21, 26, 27, 28, 29, 30, 73, 74, 97, 104], "compil": [72, 131], "compile__dynam": [72, 131], "complet": [12, 14, 16, 27, 72, 131], "complex": [5, 9, 10, 11, 29, 32, 77, 84, 90, 110, 124, 125], "complexity_factor": 116, "complianc": 18, "compon": [5, 9, 10, 11, 77, 97], "compos": [90, 95], "composed_transform": 3, "composit": [3, 41], "compris": 74, "comput": [3, 4, 5, 9, 10, 11, 18, 22, 35, 48, 50, 51, 52, 67, 72, 74, 86, 89, 90, 92, 95, 97, 98, 101, 102, 110, 123, 124, 125, 127, 128, 131, 136, 137, 138, 140, 144, 147, 151, 153], "compute_amplitude_gradi": 153, "compute_class_weight": [9, 10, 11], "concat": [18, 75, 89, 124, 125, 130], "concat_d": [12, 16, 18, 124, 125, 126, 130], "concat_dataset": [87, 88], "concatdataset": 124, "concaten": [5, 9, 10, 75, 89, 119, 124, 125], "concatenate_raw": 119, "conda": 153, "condit": 153, "conf": [27, 28], "confer": [44, 47, 49, 50, 51, 52, 63, 66, 68, 91, 107], "config": [27, 73], "configur": [12, 16, 27, 29, 32], "configure_optim": 32, "conflict": [32, 72, 131], "conform": 95, "conformercod": 95, "confus": [5, 9, 10, 11, 146, 153], "confusion_mat": [9, 10, 11, 27, 28, 146], "confusion_matrix": [5, 9, 10, 11, 27, 28, 146], "connect": [29, 30, 89, 95, 98, 105, 110, 116], "connectionpool": 27, "connector": 32, "consecut": [9, 10, 11, 54, 70, 125, 132, 135], "consid": [2, 4, 29, 32, 50, 51, 52, 72, 131, 139], "consider": 16, "consist": [2, 3, 4, 5, 8, 9, 11, 27, 28, 50, 51, 52, 74, 77, 153], "constant": 2, "constant_valu": 2, "constantpad1d": 11, "constraint": [89, 105, 153], "construct": [5, 119, 123], "construct_iir_filt": 119, "contain": [2, 5, 8, 12, 14, 16, 18, 21, 22, 26, 31, 36, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 57, 65, 66, 68, 70, 72, 73, 75, 78, 79, 80, 83, 100, 123, 124, 125, 131, 132, 133, 134, 140, 141, 147, 153], "content": 80, "context": [4, 5, 29, 35, 90, 112, 134], "contigu": [16, 46, 54, 65, 70], "continu": [14, 16, 20, 76, 77, 84, 85, 86, 124, 125, 150, 153], "continuum": 108, "contrari": 89, "contrast": [2, 4, 5, 27, 37, 44, 54, 57, 63, 70, 91, 92], "contrastivenet": 5, "contrawr": [26, 153], "contribut": [149, 151], "contributor": [147, 151], "control": [4, 5, 10, 29, 72, 90, 100, 110, 113, 117, 119, 120, 122, 123, 124, 125, 130, 131, 153], "conv": [10, 11, 116], "conv1": 10, "conv1d": [10, 11, 116], "conv2": 10, "conv2d": [3, 4, 9, 26, 27, 28, 29, 32], "conv_bia": 108, "conv_block_depth_mult": 89, "conv_block_dropout": 89, "conv_block_kernel_length_1": 89, "conv_block_kernel_length_2": 89, "conv_block_n_filt": 89, "conv_block_pool_size_1": 89, "conv_block_pool_size_2": 89, "conv_classifi": [3, 4, 26, 27, 28, 29, 32], "conv_nonlin": [26, 109], "conv_nonlin_exp": [3, 4, 26, 27, 28, 29, 32], "conv_time_spat": [3, 4, 26, 27, 28, 29, 32], "conv_weight_init_fn": 103, "conveni": [5, 107, 123], "converg": [5, 29, 31], "convergencewarn": 5, "convert": [2, 3, 4, 5, 8, 9, 10, 12, 17, 19, 27, 28, 29, 30, 31, 32, 119], "convnet": [2, 8, 26, 27, 28, 93, 106, 109], "convolut": [2, 5, 8, 9, 11, 24, 25, 26, 27, 28, 29, 30, 33, 35, 42, 44, 62, 63, 75, 76, 89, 90, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 116, 124, 136, 144, 146, 152, 153], "coord_fram": 26, "coordin": [49, 68], "copi": [2, 11, 16, 42, 62, 73, 117, 147], "core": [12, 16, 32], "corpu": [7, 13, 14, 15, 23, 24, 75, 81, 82, 91, 121, 124, 130, 152, 153], "corr_coeff": [2, 8], "corrcoef": [2, 8], "correct": [19, 26, 32, 72, 92, 96, 97, 98, 100, 101, 102, 108, 113, 131, 153], "correctli": [9, 10, 11, 99, 151, 153], "correl": [2, 8, 27, 29], "correspond": [2, 5, 8, 12, 21, 29, 30, 31, 37, 40, 72, 73, 74, 75, 83, 84, 86, 123, 125, 130, 131, 132, 140], "corrupt": 147, "cortex": 77, "cosineannealinglr": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "cost": [2, 3, 4, 5, 8, 9, 11, 27, 28], "could": [4, 5, 14, 29, 32, 75, 99, 151], "count": [12, 72, 131], "cours": [16, 73], "cover": [77, 146], "coverag": 153, "cp": 5, "cpp": 11, "cpu": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 72, 131], "creat": [14, 16, 17, 18, 19, 20, 21, 31, 72, 75, 83, 84, 85, 86, 123, 124, 125, 131, 142, 153], "create_example_model": 14, "create_filt": 119, "create_fixed_length_window": [2, 5, 12, 14, 16, 22, 31, 153], "create_from_mne_epoch": 19, "create_from_mne_raw": 19, "create_from_x_i": 17, "create_info": 26, "create_mne_dummy_raw": 31, "create_windows_from_ev": [3, 4, 5, 9, 10, 11, 18, 21, 27, 28, 29, 30, 32, 153], "create_windows_from_target_channel": [8, 153], "creation": [12, 22], "credibl": [29, 32], "criteria": [20, 72, 131], "criterion": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 72, 131], "criterion_": [72, 131], "criterion__loss_funct": [2, 27, 31], "criterion__weight": [9, 10, 11], "crop": [1, 6, 8, 10, 11, 12, 16, 20, 24, 25, 29, 30, 31, 32, 33, 72, 73, 75, 78, 80, 83, 99, 109, 121, 124, 125, 128, 130, 131, 136, 137, 138, 140, 142, 144, 146, 152, 153], "crop_wake_min": [5, 9, 10, 11, 16, 80], "croppedloss": [2, 27, 31], "croppedtimeseriesepochscor": 2, "cross": [2, 8, 16, 27, 28, 74, 91, 92, 104, 108], "cross_entropi": 27, "cross_val_scor": 29, "crossentropyloss": [3, 4, 9, 10, 11, 14, 26, 28, 29, 30, 32, 72, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 131], "csr": [72, 131], "csv": 14, "csvlogger": 32, "cuda": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 72, 119, 122, 131, 144, 150], "cuda_dependent_attributes_": [72, 131], "cuda_path": 150, "cudnn": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 144, 153], "cudnn_benchmark": [2, 3, 4, 5, 8, 9, 11, 27, 28, 144], "cue": [74, 77], "cumbersom": [72, 131], "cupi": [119, 122], "current": [5, 11, 72, 123, 131, 147], "curv": [2, 8, 28], "custom": [3, 4, 15, 23, 24, 36, 75, 84, 90, 152], "custom_crop": 12, "cut": [3, 4, 19, 28, 29, 30, 37, 57, 84, 119], "cutoff": [2, 8, 16, 119], "cv": [4, 29, 30, 107], "cv_result": 29, "cv_results_": [4, 29, 30], "cycl": 14, "cz": [10, 12, 26, 123, 129], "cz_4": 129, "cz_8": 129, "c\u00e9dric": [3, 4], "d": [2, 3, 4, 5, 8, 12, 14, 22, 26, 27, 28, 29, 30, 31, 32, 38, 39, 42, 58, 60, 62, 79, 89, 93, 97, 102, 103, 106, 109, 110, 113, 115, 134, 146, 153], "d_ff": 112, "d_i": 12, "d_model": 112, "dafaram": 12, "dahl": 30, "dai": [12, 74], "dan": 20, "daniel": [20, 35, 153], "darkner": [11, 116, 132], "darva": 77, "data": [1, 2, 5, 6, 7, 8, 9, 10, 11, 13, 14, 16, 17, 18, 19, 21, 25, 30, 32, 33, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 56, 60, 63, 65, 66, 67, 68, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 86, 87, 91, 92, 93, 95, 97, 99, 104, 107, 108, 109, 117, 119, 120, 121, 122, 123, 124, 125, 127, 128, 130, 131, 136, 141, 144, 146, 147, 148, 152, 153], "data_class": [48, 67], "data_connector": 32, "data_loading_end": 14, "data_loading_start": 14, "data_prepar": 14, "datafram": [2, 4, 5, 8, 9, 10, 11, 14, 16, 20, 21, 22, 27, 28, 29, 30, 72, 75, 131, 132, 133, 134, 135], "dataload": [3, 4, 5, 14, 32, 36, 72, 131, 142], "datapoint": 75, "dataset": [1, 6, 13, 14, 15, 16, 23, 25, 26, 33, 36, 38, 41, 42, 43, 53, 54, 56, 72, 87, 89, 91, 98, 99, 109, 111, 112, 116, 121, 124, 125, 126, 128, 130, 131, 133, 135, 136, 137, 138, 140, 142, 144, 145, 146, 147, 148, 150, 151, 152, 153], "dataset__": [72, 131], "dataset_kwarg": 78, "dataset_load": 18, "dataset_load_kwarg": 78, "dataset_nam": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32, 78], "dataset_split": 2, "dataset_train": [72, 131, 137, 138, 139], "dataset_valid": [72, 131, 137, 138, 139], "datasets_io": [23, 152], "datautil": [0, 5, 18, 83, 153], "dauphin": [47, 66, 141], "david": [47, 66, 141], "db": [3, 16, 123], "dct": 90, "ddf2ff": 29, "de": 73, "deactiv": 11, "deal": [72, 131], "decai": 113, "decid": [8, 28, 38, 39, 40, 42, 48, 53, 55, 56], "decod": [1, 3, 4, 6, 7, 11, 13, 20, 22, 24, 25, 26, 29, 30, 31, 32, 33, 35, 72, 73, 75, 78, 84, 90, 93, 95, 99, 100, 103, 104, 106, 107, 109, 116, 121, 124, 125, 126, 128, 130, 131, 136, 137, 138, 140, 142, 144, 146, 148, 152, 153], "decompos": 119, "decomposit": [5, 92], "decreas": [2, 8, 11], "deep": [2, 3, 4, 5, 8, 9, 10, 11, 14, 26, 27, 28, 29, 30, 31, 32, 35, 44, 46, 63, 65, 90, 93, 97, 103, 104, 106, 109, 111, 112, 115, 146, 148, 150], "deep4": [27, 28, 153], "deep4net": [14, 26, 31, 153], "deepconvnet": 31, "deepcopi": 2, "deepsleepnet": [26, 153], "def": [2, 3, 5, 8, 9, 10, 11, 12, 14, 16, 29, 31, 32], "default": [2, 5, 8, 11, 12, 27, 28, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 72, 73, 79, 80, 81, 82, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 103, 104, 105, 107, 108, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 122, 123, 125, 131, 139, 144, 153], "defin": [2, 5, 9, 10, 11, 12, 14, 20, 21, 27, 28, 30, 40, 56, 59, 72, 83, 89, 90, 95, 98, 113, 115, 125, 131, 134], "definit": [27, 72, 131], "degre": [29, 32, 49, 50, 51, 52, 68], "deiss": [40, 59], "del": 14, "delai": [119, 153], "delboui": 153, "delet": [5, 22, 75, 130], "delta_freq": [43, 61], "deman": 127, "demand": 4, "demarc": [29, 30], "demean": 127, "demeanin": 127, "demonstr": [3, 4, 7, 22, 24, 26, 32, 97], "deni": [35, 153], "denot": 89, "dens": [27, 99, 108, 110, 111], "densefilt": 115, "densenet": [108, 115], "densiti": 3, "depend": [4, 5, 9, 10, 11, 14, 16, 26, 29, 30, 32, 35, 72, 77, 112, 131, 142, 149, 151, 153], "deprec": [2, 5, 10, 19, 31, 153], "depreci": [3, 4, 8, 27, 28, 29, 30, 31, 32], "depth": [3, 4, 11, 26, 27, 28, 29, 30, 32, 89, 90, 97, 99, 100, 104, 105, 116], "depth_multipli": [97, 100, 105], "depthwis": [89, 97, 100, 105], "deriv": 113, "desc_4": 73, "describ": [5, 11, 26, 27, 28, 29, 32, 77, 79, 93, 94, 97, 98, 99, 103, 109, 110, 111, 112, 116], "descript": [2, 5, 8, 12, 17, 18, 19, 20, 22, 27, 28, 29, 30, 32, 73, 74, 75, 76, 81, 82, 83, 86, 87, 89, 90, 95, 98, 100, 101, 102, 103, 104, 105, 106, 108, 110, 116, 124, 125], "design": [5, 16, 91, 92, 104, 107, 112, 119], "desir": [37, 49, 57, 68, 74, 117, 123], "despit": [9, 10, 11], "detail": [5, 26, 29, 32, 47, 48, 66, 67, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 122, 123, 129, 130, 144, 151], "detect": [16, 17, 19, 30, 77, 79], "determin": [12, 30, 72, 90, 97, 131], "develop": [26, 29, 32, 92, 108, 147, 151], "deviat": [44, 63], "devic": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 36, 72, 131, 153], "df": [2, 5, 8, 9, 10, 11, 12, 16, 27, 28], "df_of_ages_gend": 12, "dh": 89, "dict": [5, 9, 10, 11, 21, 26, 36, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 75, 76, 78, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 124, 125, 129, 131, 153], "dictionari": [21, 26, 72, 75, 78, 119, 131], "diederik": 31, "differ": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 18, 21, 26, 27, 28, 29, 30, 74, 97, 98, 116, 134, 149], "differenti": [38, 39, 58, 60], "digit": [11, 22, 116, 132], "dilat": [9, 10, 11, 27, 99, 100], "dilation_block_4": 100, "dilation_block_5": 100, "dim": [2, 8, 107], "dimens": [2, 5, 8, 46, 54, 65, 70, 89, 90, 95, 107, 112, 116, 122, 153], "dimension": [5, 72, 90, 91, 95, 104, 113, 131, 142], "dimshuffl": [3, 4, 26, 27, 28, 29, 32], "ding": [46, 65], "ding2024": [46, 65], "direct": [77, 119, 147], "directli": [2, 3, 5, 8, 12, 22, 26, 27, 28, 30, 31, 72, 83, 121, 123, 131, 151], "directori": [12, 16, 18, 27, 73, 75, 79, 81, 82, 87, 130, 151], "dirnam": 5, "disabl": [32, 72, 119, 131], "disappear": 74, "discard": [12, 80], "disconsid": 12, "discov": 5, "discret": [15, 23, 24, 75, 81, 124, 152, 153], "discrimin": 30, "disk": [12, 14, 16, 81, 82, 125], "dispatch": 14, "displai": [5, 9, 10, 11, 27, 28, 29, 32, 77, 144], "distanc": [37, 57, 74], "distinct": [29, 32], "distinguish": 29, "distribut": [9, 10, 29, 47, 107, 113, 149], "divers": [2, 4, 8], "divid": [77, 84, 85, 86, 124], "divis": [29, 32, 110, 112, 128], "divyesh": [10, 153], "dl": 22, "do": [4, 12, 14, 26, 27, 29, 32, 72, 84, 85, 86, 116, 124, 125, 131, 135, 144, 151, 153], "doc": [26, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 144, 151, 153], "docstr": [26, 153], "document": [4, 5, 10, 12, 35, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 117, 119, 120, 122, 123, 147, 151, 153], "doe": [2, 8, 14, 16, 18, 27, 29, 32, 45, 72, 89, 99, 125, 131, 147], "doesn": [32, 72, 73, 131], "dogrusoz": [37, 44, 54, 57, 63, 70], "doi": [2, 8, 10, 26, 27, 28, 29, 30, 35, 73, 89, 93, 96, 97, 103, 105, 106, 109, 110, 112, 115, 146], "domain": [2, 4, 8, 16, 28, 30, 43, 48, 61, 104, 116, 119, 122], "dominiqu": 35, "don": [5, 11, 17, 19, 72, 131], "done": [3, 11, 16, 18, 26, 27, 89, 124, 125], "dong": [94, 107], "doubl": 119, "double_time_conv": 14, "down": [74, 110, 116, 122, 144], "download": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 73, 81, 82, 150], "downsampl": [9, 10, 90, 104, 122], "downsid": 16, "downstream": 5, "downward": 77, "draw": [42, 62], "drawn": 47, "driver": 150, "drop": [3, 4, 10, 14, 19, 26, 27, 28, 29, 32, 38, 58, 86, 118, 125, 129], "drop_bad": [14, 86, 125], "drop_bad_window": [86, 125], "drop_channel": 118, "drop_index": [72, 131], "drop_last_window": [2, 12, 14, 17, 19, 22, 27, 31, 84, 85, 86, 124, 125], "drop_original_sign": 129, "drop_path_r": 107, "drop_prob": [14, 26, 30, 93, 95, 96, 97, 101, 102, 105, 109, 114, 115], "drop_rat": [100, 107, 108], "dropchannel": 153, "dropout": [3, 4, 5, 9, 10, 26, 27, 28, 29, 30, 32, 89, 90, 93, 95, 96, 97, 100, 107, 108, 109, 110, 111, 112, 114, 115], "dropout_inp": 90, "droppath": 107, "dtype": [22, 84, 124, 125, 127, 128, 153], "due": [18, 32, 153], "dummi": [2, 27], "dunder": [72, 131], "duong": 97, "duplic": [143, 153], "dur": [2, 3, 5, 8, 9, 10, 11, 26, 27, 28, 29, 30, 31], "durat": [12, 29, 30, 31, 117, 119, 125], "dure": [2, 4, 5, 8, 9, 10, 11, 12, 14, 27, 28, 29, 30, 32, 72, 73, 90, 107, 108, 119, 123, 131, 153], "dx": [26, 35, 93, 97, 103, 106, 109, 146], "dynam": [72, 113, 131], "dzirasa": 113, "e": [5, 9, 10, 11, 14, 16, 26, 27, 28, 29, 30, 32, 37, 40, 44, 46, 54, 56, 57, 59, 63, 65, 70, 72, 76, 79, 80, 81, 82, 83, 86, 89, 93, 94, 95, 96, 97, 98, 99, 101, 103, 106, 107, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 125, 129, 131, 135, 139, 146, 151, 153], "e1750": 108, "e1762": 108, "e215": [5, 9, 10, 11], "e220": [5, 9, 10, 11], "e231": 153, "e46769": 92, "each": [2, 4, 8, 9, 10, 11, 12, 14, 16, 17, 19, 21, 22, 26, 29, 30, 31, 36, 37, 38, 42, 46, 48, 49, 53, 55, 57, 58, 62, 65, 67, 68, 69, 71, 72, 73, 74, 75, 77, 80, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 122, 124, 125, 131, 133, 135, 137, 138, 139, 143], "eager": [15, 23, 24, 82, 93, 109, 124, 152], "earli": 29, "early_stop": 5, "earlystop": [5, 29, 32], "easiest": [26, 29], "easili": [2, 8, 20, 26, 28, 29, 30, 32, 133], "eca": 90, "ecg": 91, "ecog": [1, 6, 7, 13, 24, 73, 75, 99, 109, 121, 123, 124, 126, 128, 130, 137, 138, 140, 144, 148, 152, 153], "ecosystem": 32, "edf": [14, 16, 17, 19, 22], "edfx": 80, "edg": [16, 119], "edit": 151, "edu": [2, 4, 8, 73], "eee": 89, "eeg": [1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 13, 14, 15, 17, 20, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33, 35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 74, 75, 77, 78, 79, 80, 81, 82, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 120, 121, 123, 124, 125, 128, 130, 133, 134, 141, 144, 146, 148, 152, 153], "eegbci": [17, 19], "eegclassifi": [2, 5, 9, 10, 11, 26, 27, 28, 29, 30, 153], "eegconform": [26, 153], "eegincept": [97, 153], "eeginceptionerp": [26, 153], "eeginceptionmi": [26, 153], "eegitnet": [26, 153], "eegmmidb": [17, 19], "eegmodulemixin": [2, 31, 153], "eegnet": [101, 102, 105], "eegnet4": 102, "eegnetv1": 26, "eegnetv4": 26, "eegnex": [26, 153], "eegnexcod": 100, "eegregressor": [2, 8, 26, 31, 153], "eegresnet": [26, 153], "eegsimpleconv": [26, 153], "eegtcnet": [26, 153], "eegwindowsdataset": [5, 9, 16, 125, 153], "eeyhsong": 95, "effect": [3, 19], "effici": [2, 3, 16, 27, 90], "egg": 151, "eggensperg": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 146], "einop": 153, "either": [2, 8, 26, 28, 29, 30, 72, 74, 75, 77, 99, 119, 123, 131, 142], "el": [104, 153], "elabor": [29, 32], "eldel": [10, 112], "eldele2021": [7, 13, 24, 75, 80, 99, 112, 121, 125, 130, 133, 135, 144, 146, 152], "electrocorticograph": [2, 8, 73], "electrod": [4, 20, 74, 77, 123], "electroencephalogram": [37, 44, 54, 57, 63, 70, 92, 100], "electroencephalograph": [49, 50, 51, 52, 68], "electroencephalographi": 35, "electrophysiolog": 148, "element": [48, 49, 54, 68, 90], "elementwise_affin": 10, "elif": [14, 31], "elouaya": 104, "els": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 27, 28, 29, 30, 31, 32, 72, 107, 131], "elu": [11, 89, 90, 91, 92, 93, 94, 95, 96, 97, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 114, 115, 116], "emadeldeen24": 112, "emb": [5, 91], "emb_siz": [5, 91, 92, 107], "embc": [49, 50, 51, 52, 68], "embed": [5, 9, 10, 89, 91, 92, 95, 105, 107], "embedd": 5, "emg": 80, "emir": 11, "emit": 118, "emot": [44, 63, 113], "empir": [47, 66, 114, 141], "emploi": 90, "empti": [29, 72, 119, 123], "en": 27, "enabl": [14, 16, 27, 32, 72, 74, 115, 131, 153], "encapsul": 125, "encnet": 90, "encod": [11, 46, 65, 90, 91, 112, 116], "encount": [16, 18, 147], "encourag": [2, 8, 24, 27, 28], "end": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 35, 72, 98, 117, 122, 124, 125, 131, 137, 138, 139, 153], "end_dim": [9, 10], "enforc": 153, "eng": 115, "engemann": [4, 5, 35, 134, 153], "engin": [4, 5, 9, 10, 28, 29, 30, 46, 49, 50, 51, 52, 65, 68, 94, 95, 97, 98, 111, 112], "enough": [5, 77], "ensembl": [135, 153], "ensur": [2, 116, 144, 150, 153], "ensure4d": [3, 4, 26, 27, 28, 29, 32], "ensure_odd_conv_s": 116, "ensuredim": [3, 4, 26, 27, 28, 29, 32], "enter": [104, 151], "entir": [5, 14, 20, 29, 32, 153], "entri": [21, 118], "enumer": [5, 12, 29, 32], "env": 153, "environ": [4, 73, 144], "eog": [80, 116], "ep": [10, 128], "epo": [18, 75, 87], "epoch": [2, 3, 4, 5, 8, 9, 10, 11, 14, 19, 24, 25, 27, 28, 29, 30, 31, 32, 33, 72, 75, 83, 85, 86, 99, 109, 117, 118, 119, 120, 121, 123, 124, 125, 131, 134, 137, 138, 139, 152, 153], "epochsarrai": 26, "epochscor": [5, 8, 9, 10, 11, 72, 131], "epochscoring_1": [72, 131], "equal": [2, 8, 32, 84, 85, 86, 99, 107, 124], "equival": [3, 119], "eras": 38, "eric": 35, "erp": 97, "error": [12, 22, 27, 30, 31, 86, 118, 124, 125, 126, 131, 147, 153], "error_scor": [4, 29, 30], "eskandarian": 98, "especi": [9, 30, 32], "estim": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32], "et": [10, 26, 46, 65, 77, 89, 90, 91, 92, 93, 94, 95, 96, 98, 100, 101, 102, 103, 104, 105, 106, 108, 109, 110, 111, 112, 114, 115, 116, 139], "etc": [14, 28, 30, 91, 121], "ethic": 77, "eval": [4, 30, 32, 153], "eval_i": [4, 30], "eval_set": [4, 30], "eval_x": [4, 30], "evalu": [2, 3, 4, 5, 8, 9, 10, 11, 14, 21, 27, 28, 30, 92, 104, 114], "even": [11, 26, 29, 32, 72, 73, 116, 131], "event": [18, 19, 20, 21, 26, 27, 28, 29, 30, 32, 80, 86, 124, 125], "event_cod": [17, 19], "everi": [9, 10, 11, 12, 14, 18, 22, 29, 32, 77, 89, 90, 95, 98, 153], "evok": [118, 119, 120, 123], "exact": 26, "exactli": 125, "exampl": [1, 2, 6, 8, 9, 10, 11, 13, 14, 15, 16, 22, 23, 25, 31, 33, 34, 37, 39, 40, 44, 45, 46, 47, 48, 49, 55, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 123, 147, 152, 153], "exce": 117, "exceed": [86, 125], "except": [77, 80], "excess": 22, "excit": 90, "exclud": [117, 119, 120, 123], "exclus": [29, 32], "execut": [5, 6, 11, 12, 13, 14, 16, 17, 19, 23, 33, 34, 77, 130, 152, 153], "exemplifi": 153, "exist": [16, 18, 22, 29, 31, 73, 75, 76, 83, 123, 130], "exp": 113, "expand": [72, 90, 116, 131], "expand_dim": 31, "expans": [90, 107], "expect": [5, 14, 26, 32, 72, 92, 131], "expens": [14, 72, 131], "experi": [7, 14, 24, 29, 32, 73, 77], "experiment": [5, 124, 153], "expert": [9, 10, 11, 108], "explain": [1, 4, 24, 27, 96], "explan": [2, 27, 129, 130], "explicit": [27, 139], "explicitli": [5, 29, 32, 119, 120, 123], "explor": [5, 29], "exponent": [127, 128], "exponenti": [2, 3, 4, 8, 27, 28, 29, 30, 32, 116, 127, 128], "exponential_moving_standard": [2, 3, 4, 8, 27, 28, 29, 30, 32], "expos": 153, "express": [3, 4, 26, 27, 28, 29, 32], "extra": [32, 153], "extra_param": 90, "extract": [2, 8, 12, 14, 16, 17, 19, 22, 27, 32, 83, 97, 98, 107, 110, 112, 113, 124, 125, 132, 134], "extractor": [5, 9, 10, 94, 110, 111, 112, 116], "f": [4, 5, 10, 11, 12, 14, 16, 17, 22, 26, 27, 28, 29, 30, 31, 32, 44, 48, 63, 67, 79, 93, 97, 103, 106, 109, 115, 146], "f1": [5, 9, 10, 11, 89, 102, 139], "f2": 102, "f3": 12, "f4": 12, "f7": 12, "f8": 12, "f811": [12, 22], "f_c": 113, "f_criterion": 5, "f_histori": 5, "f_name": 5, "f_optim": 5, "facebookresearch": [47, 66, 141], "facilit": [26, 153], "factor": [3, 4, 5, 9, 10, 12, 27, 28, 29, 30, 32, 48, 90, 104, 107, 112, 115, 116, 122], "factor_new": [2, 3, 4, 8, 27, 28, 29, 30, 32, 127, 128], "factornew": [127, 128], "fail": [5, 12], "faisal": 97, "fake": [24, 25, 26, 33, 75, 76, 93, 99, 109, 124, 136, 144, 152, 153], "fake_data_split": 31, "fake_descript": 31, "fake_dur": 31, "fake_regression_dataset": 31, "fake_sfreq": 31, "fall": [86, 125], "fals": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 22, 26, 27, 28, 29, 30, 31, 32, 42, 47, 49, 50, 51, 52, 62, 68, 72, 73, 75, 76, 79, 80, 81, 82, 83, 86, 88, 89, 90, 91, 93, 94, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 109, 110, 111, 112, 114, 115, 116, 117, 121, 123, 124, 125, 126, 129, 130, 131, 134, 135, 137, 138, 144, 146, 153], "familiar": 149, "far": [5, 134], "farrugia": 104, "fast": [14, 16, 32, 144], "faster": [10, 16, 27, 72, 122, 131], "fattouh": [2, 8, 153], "favor": 153, "favour": 153, "fc": [10, 112], "fca": 90, "feat": 5, "feat_extractor": [9, 10], "featur": [5, 9, 10, 26, 29, 90, 94, 95, 97, 98, 99, 104, 107, 110, 111, 112, 113, 116, 147, 151], "feature_extractor": [9, 10], "feature_map": 104, "features1": 10, "features2": 10, "fed": [2, 27, 50, 51, 52, 104], "feed": [89, 112], "feed_forward": 10, "feedback": [5, 9, 10, 11, 74], "feedforwardblock": 95, "feel": [29, 32], "feet": [17, 18, 19, 21, 27, 28, 29, 30, 32, 74, 77], "femal": [12, 77], "female_df": 12, "fernand": 108, "fernandez": 110, "fetch": [17, 19, 20, 21, 74, 77, 78], "fetcher": 148, "few": [5, 9, 10, 11, 14, 16, 26, 153], "fewer": [116, 119], "fexion": 8, "fft": 122, "fieder": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 146], "field": [2, 27, 72, 123, 131, 142], "fif": [14, 16, 18, 75, 87, 153], "fiff_unit_v": 26, "fiff_unitm_non": 26, "fiffv_coil_eeg": 26, "fiffv_coord_head": 26, "fiffv_eeg_ch": 26, "fig": [2, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 31, 146], "figsiz": [2, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 31, 146], "figur": [12, 27, 28, 29, 74, 89, 146], "file": [5, 6, 12, 13, 14, 16, 17, 18, 19, 23, 26, 33, 34, 75, 80, 81, 82, 87, 117, 135, 147, 152, 153], "file_id": 135, "fileexistserror": 130, "fill": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "filter": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 20, 26, 27, 28, 29, 30, 32, 37, 57, 74, 89, 90, 93, 95, 97, 98, 100, 102, 105, 109, 111, 113, 114, 115, 116, 121, 122, 129, 153], "filter_1": [100, 105], "filter_2": 100, "filter_data": 119, "filter_length": 119, "filter_length_2": [14, 93], "filter_length_3": [14, 93], "filter_length_4": [14, 93], "filter_time_length": [14, 26, 93, 95, 109], "filter_width": 113, "filterbank": 153, "filtfilt": 119, "final": [2, 4, 5, 8, 9, 10, 11, 12, 14, 16, 26, 27, 29, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 128], "final_conv_length": [2, 3, 4, 8, 14, 26, 27, 28, 29, 30, 31, 32, 93, 101, 102, 109, 153], "final_fc_length": 95, "final_lay": [3, 4, 11, 26, 27, 28, 29, 32], "final_pool_length": [103, 153], "find": [2, 4, 8, 30], "fine": 30, "finer": [8, 153], "finger": [1, 6, 7, 13, 24, 73, 75, 77, 99, 109, 121, 124, 126, 128, 130, 137, 138, 140, 144, 152, 153], "fir": [16, 119, 122], "fir_design": 119, "fir_window": 119, "first": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 26, 27, 28, 30, 40, 46, 54, 65, 70, 72, 75, 79, 80, 81, 82, 89, 90, 93, 95, 100, 104, 105, 109, 112, 119, 122, 123, 125, 131, 147, 151], "first_filter_length": 103, "first_pool_mod": [14, 93], "first_pool_nonlin": 93, "first_samp": 117, "firstli": [12, 21], "firwin": [16, 119], "firwin2": 119, "fit": [2, 3, 5, 8, 9, 10, 11, 14, 24, 26, 27, 28, 29, 30, 31, 32, 72, 125, 131], "fit_loop": 32, "fit_param": [4, 30, 131], "fit_transform": 5, "five": [12, 73], "fix": [3, 40, 59, 91, 107, 119, 147, 153], "fix_init_weight_and_init_embed": 107, "fixat": 74, "flag": [90, 153], "flake8": 153, "flat": [10, 19, 38, 58, 124, 125, 126], "flatten": [5, 9, 10, 11], "flexion": [1, 6, 7, 13, 24, 73, 75, 99, 109, 121, 124, 126, 128, 130, 137, 138, 140, 144, 152, 153], "flip": [5, 53, 55, 69, 71], "float": [3, 5, 26, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 63, 68, 72, 80, 84, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 122, 124, 125, 127, 128, 129, 131, 141, 146], "float32": 22, "float64": [17, 19, 31], "fly": [2, 8, 28, 30, 76, 83, 153], "fmax": 3, "fmin": 3, "fmt": 30, "fn": [18, 121], "fname": 14, "fnin": 35, "focu": 4, "fold": [4, 30, 32], "folder": [14, 73], "follow": [3, 4, 5, 9, 10, 11, 14, 26, 29, 32, 91, 97, 104, 107, 119, 122, 125, 131, 149, 150, 151], "font": 146, "font_scal": 29, "fontsiz": [2, 8, 12, 27, 28], "fontweight": 146, "foot": 74, "footcit": 123, "forc": 73, "force_upd": 73, "form": [26, 47, 66, 74, 75, 76, 83], "format": [4, 14, 17, 19, 26, 75, 84, 85, 86], "former": [26, 72, 89, 90, 95, 98, 131], "fortun": 26, "forum": 144, "forward": [3, 4, 5, 11, 26, 27, 28, 29, 32, 41, 56, 72, 89, 90, 91, 92, 94, 95, 98, 99, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 119, 121, 123, 131, 136, 140, 142], "forward_featur": 107, "found": [2, 8, 10, 12, 16, 18, 19, 20, 21, 26, 27, 28, 29, 30, 32, 73, 123, 124, 125], "four": [5, 9, 49, 74, 77, 90], "fourier": [42, 62, 92], "fp1": 12, "fp2": 12, "fpz": 10, "fr": [3, 4, 11], "fraction": [29, 31], "framework": [4, 90], "frank": 35, "free": [29, 32], "freedom": [29, 32], "freez": [9, 10, 153], "freiburg": 77, "freq": [3, 74, 77], "freq_idx": 90, "freq_shift": 3, "freqs_to_notch": [37, 57], "frequenc": [2, 3, 4, 8, 11, 12, 16, 17, 26, 27, 28, 29, 30, 31, 32, 37, 43, 57, 61, 77, 84, 89, 90, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 122, 129, 132, 153], "frequency_band": 129, "frequencyshift": 3, "frequent": [9, 10, 11], "friendli": 153, "from": [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 38, 39, 42, 46, 47, 48, 49, 50, 51, 52, 58, 60, 62, 65, 67, 68, 72, 74, 76, 77, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 123, 124, 125, 131, 132, 133, 134, 135, 137, 138, 139, 141, 142, 149, 152, 153], "front": 74, "frontier": [27, 28, 29, 30, 35, 79], "frontiersin": 35, "ft": [42, 62, 89], "ft_surrog": 153, "ftsurrog": 4, "full": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 144], "fulli": [11, 29, 30, 89, 95, 97, 98, 105], "function": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 20, 22, 26, 27, 28, 30, 31, 32, 35, 42, 56, 72, 75, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 121, 123, 125, 131, 137, 138, 139, 144, 153], "functool": 30, "fundament": [24, 25], "further": [2, 4, 5, 8, 9, 10, 11, 27, 29, 32, 72, 90, 131], "furu": 107, "fusion": 90, "futur": [5, 10, 19, 26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "futurewarn": [2, 5, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "fz": 12, "g": [5, 9, 10, 11, 14, 16, 26, 27, 28, 29, 30, 32, 37, 40, 42, 44, 54, 56, 57, 59, 62, 63, 72, 76, 79, 80, 81, 82, 83, 86, 89, 93, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 109, 110, 111, 114, 115, 116, 117, 118, 119, 120, 121, 125, 129, 131, 135, 139, 146, 153], "galleri": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 152], "galtier": [5, 9, 10, 111], "gamma": 77, "gamma_1": 107, "gamma_2": 107, "gao": 95, "gate": 90, "gather": 90, "gaussian": [31, 44, 63], "gave": [4, 30], "gb": [9, 10, 11], "gca": 12, "gct": 90, "ge": [90, 108], "gelu": [10, 95, 107, 112], "gemein": [12, 17, 18, 19, 20, 21, 22, 31, 153], "gender": [12, 18, 22, 79, 81, 82], "gener": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 32, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 67, 72, 99, 107, 110, 113, 114, 119, 131, 139, 146, 153], "georg": 30, "get": [14, 16, 17, 22, 27, 28, 29, 32, 48, 72, 107, 131], "get_augmentation_param": [37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 56, 153], "get_center_label": [9, 10], "get_classifi": 107, "get_config": 27, "get_data": 17, "get_default_callback": [72, 131], "get_fc_siz": 95, "get_iter": [72, 131], "get_label": [2, 8, 27, 28], "get_legend_handles_label": 5, "get_loss": 72, "get_metadata": [5, 9, 10, 11, 27, 28, 29, 31, 75, 133], "get_num_lay": 107, "get_output_shap": [2, 27, 31, 99, 153], "get_param": 153, "get_posit": [49, 68], "get_torchinfo_statist": 99, "get_ylim": [27, 28], "geyer": 100, "gh": 153, "ghaith": 153, "gillmeist": 96, "gilmer": 30, "git": 151, "github": [4, 5, 30, 90, 91, 92, 104, 107, 108, 147, 149, 153], "give": [10, 12, 22, 26, 49, 68, 119, 147], "given": [3, 4, 5, 21, 32, 38, 39, 40, 42, 48, 53, 55, 56, 72, 73, 87, 119, 120, 123, 131, 142, 153], "gizzi": 90, "glass": [5, 9, 10, 11], "glasstett": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 146], "global": [72, 90, 104, 131, 139], "glossari": [2, 4, 8], "gmail": [2, 5, 8, 9, 10, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31], "gnassoun": [11, 153], "go": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 117], "goal": [32, 97, 98], "godbol": 30, "goe": 16, "goh": [37, 44, 54, 57, 63, 70], "goj": 35, "goldberg": [5, 9, 10, 11], "good": [2, 8, 26, 27, 28], "googl": 30, "gordon": [97, 101, 102], "got": 30, "gpu": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 72, 131, 150, 153], "gradient": [27, 153], "gradiomet": 3, "grai": 77, "gramfort": [4, 5, 9, 10, 35, 97, 111, 134, 153], "grand": 113, "grangier": [38, 39, 58, 60], "greater": [37, 57], "green": 12, "grid": [29, 30], "gridsearchcv": [4, 29, 30, 139, 153], "gridsearchcvifittedgridsearchcv": 4, "grifcc": 97, "gripon": 104, "gross": 97, "ground": [31, 74, 77], "group": 110, "groupbi": 16, "growth": [108, 115], "growth_rat": 108, "gsop": 90, "gt": 4, "guarante": [92, 96, 97, 98, 100, 101, 102, 108, 113], "guetschel": [26, 153], "guid": [22, 29, 150], "guidelin": 151, "guo": 94, "gustavo": 153, "h": [2, 4, 5, 8, 27, 28, 37, 40, 44, 54, 57, 59, 63, 70, 79, 89, 94, 96, 100, 134], "h_freq": [2, 3, 4, 5, 8, 9, 10, 16, 27, 28, 29, 30, 32, 119], "h_trans_bandwidth": 119, "ha": [2, 3, 4, 5, 8, 10, 12, 18, 19, 20, 21, 22, 27, 28, 29, 30, 31, 32, 50, 51, 52, 72, 75, 76, 80, 83, 86, 92, 96, 97, 98, 100, 101, 102, 108, 113, 116, 125, 130, 131, 141, 147, 153], "hac": [9, 10, 11], "had": [77, 97, 99], "half": [111, 119], "halv": 116, "ham": [16, 119], "hamlet": [40, 59], "hand": [17, 19, 24, 28, 30, 74, 77], "handl": [2, 3, 4, 8, 27, 28, 30, 123], "hangbo": 107, "hann": 119, "happen": [147, 153], "hard": 147, "hardwar": [14, 16], "hasattr": 30, "hausdorff": [5, 9, 10, 11], "have": [2, 4, 5, 8, 11, 12, 14, 16, 17, 19, 21, 26, 27, 28, 29, 30, 32, 46, 49, 54, 65, 68, 70, 72, 84, 85, 86, 98, 104, 107, 121, 123, 124, 131, 139, 147, 150, 151, 153], "hbm": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 146], "hbm23730": 35, "he": [9, 10, 11], "head": [89, 91, 95, 107, 112, 133], "head_dim": 107, "health": [37, 44, 54, 57, 63, 70, 91], "healthi": [77, 79, 80], "heart": 91, "heatmap": 30, "heavi": 146, "height": [12, 29, 100], "held": [9, 10], "help": [5, 9, 10, 21, 123], "helper": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31], "henrik": 153, "here": [2, 3, 4, 5, 8, 10, 11, 12, 21, 22, 24, 26, 27, 28, 29, 30, 32, 43, 61, 79, 86, 91, 98, 125], "hersch": 105, "heterogen": [38, 39, 58, 60, 97], "high": [2, 3, 4, 8, 11, 27, 28, 29, 30, 32, 37, 57, 77, 97, 116, 119, 132], "high_cut_hz": [2, 3, 4, 5, 8, 9, 10, 27, 28, 29, 30, 32], "higher": [2, 5, 8, 32, 112], "highli": 29, "hint": 153, "hist": 12, "histori": [2, 5, 8, 9, 10, 11, 27, 28, 31, 72, 131], "hold": [18, 75, 76, 83, 124, 125], "holdout": 29, "home": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 27, 28, 29, 30, 31, 32], "hong": 108, "hongyi": [47, 66, 141], "honor": [72, 131], "hook": [89, 90, 95, 98, 153], "hop": 91, "hop_length": [91, 92], "horizont": 12, "horizontalalign": 29, "hornero": 97, "hospit": [12, 81, 82, 153], "host": 27, "how": [2, 3, 4, 5, 8, 9, 10, 11, 12, 17, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 30, 31, 33, 72, 75, 78, 90, 99, 109, 117, 121, 123, 125, 128, 130, 131, 144, 152, 153], "howev": [2, 3, 4, 5, 8, 11, 14, 16, 21, 26, 27, 28, 29, 125], "hpu": 32, "hspace": 12, "html": [2, 4, 5, 8, 12, 26, 27, 72, 80, 81, 82, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 131, 144, 146, 153], "http": [2, 4, 5, 8, 12, 26, 27, 28, 29, 30, 35, 47, 66, 72, 73, 74, 77, 80, 89, 93, 95, 96, 97, 98, 99, 101, 103, 105, 106, 109, 110, 112, 114, 115, 116, 131, 141, 144, 146, 151], "hubert": [5, 9, 14, 16, 20, 153], "hue": 14, "hum": [27, 28, 29, 30], "human": [2, 8, 26, 31, 35, 40, 59, 73, 93, 103, 106, 109, 119, 146], "hung": [101, 102], "hutter": [26, 27, 28, 29, 30, 35, 93, 103, 106, 109, 146], "hybrid": 106, "hybridnet": 26, "hyeperparamet": 30, "hyperparamet": [2, 5, 8, 9, 10, 11, 14, 24, 25, 27, 28, 32, 33, 47, 72, 75, 78, 99, 104, 109, 121, 125, 128, 130, 131, 144, 152, 153], "hypnogram": [9, 10, 11], "hyv\u00e4rinen": [4, 5, 134], "hz": [2, 3, 4, 5, 8, 9, 11, 16, 27, 29, 30, 31, 37, 43, 57, 61, 74, 89, 95, 98, 116, 119], "h\u00e4m\u00e4l\u00e4inen": 35, "i": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 21, 22, 26, 27, 28, 30, 31, 35, 37, 41, 42, 43, 46, 47, 49, 54, 56, 57, 61, 62, 65, 66, 68, 70, 72, 73, 74, 75, 76, 77, 78, 79, 83, 84, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 121, 122, 123, 124, 125, 130, 131, 134, 139, 143, 144, 148, 149, 150, 153], "i_class": [27, 28], "i_start_in_tri": [83, 133], "i_stop_in_tri": [83, 133, 143], "i_window_in_tri": [83, 133, 143], "icassp": 113, "iclr": [47, 66, 107], "id": [12, 18, 20, 21, 27, 28, 29, 30, 32, 75, 79, 81, 82, 87, 124, 125, 130, 153], "ideal": 77, "ident": [9, 11, 32, 45, 72, 93, 131], "identifi": [9, 10, 11, 86, 125], "ids_to_load": [18, 87], "idx": [3, 4, 9, 10, 11, 26, 27, 28, 29, 30, 32], "idx_perm": [47, 66], "idx_shuffl": [48, 67], "idx_train": 8, "idx_valid": 8, "ie": 124, "ieee": [5, 9, 10, 11, 46, 48, 49, 50, 51, 52, 65, 67, 68, 89, 94, 95, 96, 97, 111, 112], "ieeexplor": 95, "igel": [11, 116, 132], "ignor": [2, 3, 4, 8, 54, 72, 89, 90, 95, 98, 118, 121, 124, 125, 131, 134], "ii": 29, "iia": 74, "iir": 119, "iir_param": 119, "ill": 10, "illustr": [3, 29], "illutr": 3, "imag": [74, 97, 107], "imageri": [4, 74, 89, 90, 96, 98, 104, 105, 153], "imagin": [17, 19], "imbal": [42, 62, 80], "imbalanc": [9, 10, 11], "immedi": 124, "impact": [14, 27, 30], "implement": [9, 10, 14, 16, 26, 29, 46, 47, 56, 65, 66, 72, 89, 92, 96, 97, 98, 100, 101, 102, 107, 108, 113, 131, 141, 142, 148, 153], "implicitli": [5, 27, 29, 32], "import": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 42, 62, 147, 151], "impos": [89, 105], "imposs": 14, "improv": [2, 3, 5, 8, 9, 10, 11, 32, 119, 147, 153], "in_chan": [11, 26, 31, 93, 101, 102, 103, 106, 109, 115, 116], "in_channel": [96, 97, 98, 107], "in_featur": [9, 10], "inat": 74, "incept": [96, 97, 98, 153], "inceptionnet": [97, 98], "includ": [9, 11, 12, 14, 28, 29, 30, 32, 39, 60, 78, 104, 117, 119, 120, 124, 125, 147, 148], "include_tmax": [12, 117], "incom": [72, 131], "incomplet": 12, "inconsist": 125, "incorrect": 153, "increas": [2, 3, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 32, 90, 98, 112, 153], "ind": 22, "ind1": 5, "ind2": 5, "inde": 4, "independ": [29, 32, 42, 62, 97, 119, 153], "indetermin": [2, 3, 4, 5, 8, 9, 11, 27, 28], "index": [2, 5, 8, 9, 10, 11, 17, 27, 28, 30, 31, 76, 90, 113, 117, 127, 128, 132, 133, 143, 149], "indic": [5, 9, 10, 21, 31, 47, 48, 66, 67, 75, 90, 119, 120, 123, 133, 134, 135, 153], "indices_": 29, "individu": [9, 10, 11, 12, 26, 27, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 153], "industri": 89, "inf": 12, "infer": [26, 29, 30, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 125, 131, 139], "infin": 123, "info": [2, 3, 4, 8, 12, 14, 16, 17, 19, 20, 21, 26, 27, 28, 29, 30, 32, 75, 83, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 120, 123, 133, 135, 147, 153], "inform": [3, 4, 12, 14, 17, 18, 20, 26, 29, 30, 42, 62, 72, 75, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 131, 133, 151], "informat": 89, "ingolfsson": 105, "ingolfsson2020": 105, "inherit": [8, 9, 10, 11, 26, 28, 30, 72, 131], "init_block_s": [2, 3, 4, 8, 27, 28, 29, 30, 32, 127, 128], "init_scal": 107, "init_valu": 107, "initi": [3, 4, 5, 9, 10, 11, 26, 29, 30, 32, 72, 90, 95, 97, 107, 113, 116, 131], "initialis": [30, 131], "initialized_": [72, 131], "initialz": [72, 131], "inplac": [9, 10, 16], "input": [2, 3, 4, 8, 10, 11, 14, 21, 26, 27, 28, 29, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 68, 69, 70, 71, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 153], "input_chan": 107, "input_s": 99, "input_size_": [89, 110, 111, 112, 116], "input_size_sampl": [5, 9, 10, 11], "input_window_": 98, "input_window_sampl": [2, 3, 4, 8, 14, 26, 27, 28, 29, 30, 31, 32, 93, 95, 96, 97, 101, 102, 103, 106, 109, 115], "input_window_second": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131], "inria": [3, 4, 11], "insecurerequestwarn": 27, "insert": [12, 22, 99], "insid": [4, 29, 30, 95, 97, 151], "insight": 5, "inspir": [107, 113, 132], "inst": [20, 118, 119, 120, 123], "instal": [32, 72, 119, 122, 131, 153], "instanc": [5, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 72, 89, 90, 95, 98, 117, 118, 119, 120, 123, 131, 133, 153], "instanti": [2, 3, 4, 8, 14, 26, 27, 28, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 72, 78, 131, 153], "instead": [3, 4, 5, 8, 22, 27, 28, 29, 30, 31, 32, 72, 89, 90, 95, 98, 99, 123, 131, 153], "instruct": 149, "int": [3, 4, 5, 9, 10, 14, 16, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 65, 67, 70, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 120, 122, 123, 124, 125, 127, 128, 130, 131, 132, 133, 134, 135, 142, 144, 146], "integ": [21, 22, 27, 28, 40, 46, 54, 59, 65, 70, 75, 119, 120, 130], "integr": [9, 10, 32, 153], "intend": 92, "intens": [4, 104], "inter": [74, 77], "interest": [5, 12, 22, 26], "interfac": [32, 35, 48, 67, 97, 101, 102, 105], "intermedi": 99, "intern": [11, 14, 16, 20, 21, 44, 47, 49, 50, 51, 52, 63, 66, 68, 107, 121], "interpol": [47, 49, 50, 51, 52, 66, 68], "interpret": [35, 40, 59, 108, 119, 120, 131], "interquartil": 11, "interrupt": [72, 131], "interv": [32, 77, 125, 153], "introduc": [5, 9, 10, 11, 14, 15, 24, 25, 27, 31], "invari": [115, 153], "invas": 77, "invert": 40, "invert_xaxi": 12, "invert_yaxi": 29, "investig": 26, "io": [5, 9, 16, 17, 19, 27, 76, 117, 119, 129], "ioven": 153, "ipynb": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32], "irregular": 147, "is_abbrev": [3, 4, 18, 20, 21, 29, 30], "is_avail": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32], "isinst": [9, 10], "isip": [12, 14, 81, 82], "isnan": 2, "isotrak": 16, "issn": 35, "issu": [5, 14, 16, 147, 153], "issubset": 12, "item": [5, 14, 19, 20, 26, 27, 28, 32], "iter": [3, 4, 5, 20, 22, 47, 72, 99, 118, 131, 142], "iterator_test": [72, 131], "iterator_test__batch_s": [72, 131], "iterator_train": [3, 4, 72, 131], "iterator_train__batch_s": [72, 131], "iterator_train__drop_last": [72, 131, 153], "iterator_train__num_work": 5, "iterator_train__sampl": [5, 9, 10, 11], "iterator_train__shuffl": [2, 5, 9, 10, 11, 27, 31, 72, 131], "iterator_train__transform": [3, 4], "iterator_valid": [72, 131], "iterator_valid__num_work": 5, "iterator_valid__sampl": [5, 9, 10, 11], "itertool": [14, 16], "itnet": [96, 153], "its": [3, 4, 5, 9, 10, 16, 18, 20, 21, 26, 29, 30, 31, 72, 75, 121, 130, 131], "itself": [14, 29, 30, 147], "iv": [1, 6, 7, 13, 20, 21, 24, 25, 26, 28, 29, 30, 32, 33, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 78, 89, 98, 99, 109, 121, 124, 125, 126, 128, 130, 136, 137, 138, 140, 144, 146, 152, 153], "ivanov": [5, 9, 10, 11], "izadi": [37, 44, 54, 57, 63, 70], "j": [2, 4, 5, 8, 26, 27, 28, 29, 30, 31, 37, 40, 42, 44, 54, 57, 59, 62, 63, 70, 73, 90, 91, 92, 93, 96, 97, 101, 102, 103, 106, 108, 109, 111, 114, 115, 146], "ja": 35, "jankauska": 153, "javad": 153, "jayaram": [28, 29, 30, 97], "jbanvil": [5, 9, 14, 16, 20], "je": [9, 10, 11], "jennum": [11, 116, 132], "jeunet": 97, "jiang": [44, 63, 107], "jiang2024": 107, "jimmi": 31, "jin": [40, 59], "jing": 108, "jing2023": 108, "jjl": [9, 10, 11], "jm": [9, 10, 11], "jmir": 92, "job": [12, 72, 81, 82, 87, 119, 122, 124, 125, 130, 131], "joblib": [16, 130], "john": 153, "joint": 123, "jointli": 29, "josef": 35, "jost": 35, "journal": [4, 28, 29, 30, 35, 98], "json": [18, 75, 87, 153], "jupyt": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "just": [2, 4, 8, 22, 26, 28, 29, 30, 72, 93, 109, 131], "justin": 30, "k": [3, 5, 9, 10, 11, 26, 27, 28, 30, 31, 32, 37, 44, 49, 50, 51, 52, 54, 57, 63, 68, 70, 93, 97, 98, 103, 106, 109, 113, 146], "kai": [2, 8, 73], "kaiser": 122, "kale": 31, "kamboh": 79, "kamphuisen": [5, 9, 10, 11], "katharina": 35, "kathrin": 153, "kc": 89, "keep": [3, 4, 10, 11, 16, 27, 28, 29, 30, 32, 77, 80, 153], "kei": [21, 26, 27, 28, 75, 76, 83, 107, 124, 125], "kemp": [5, 9, 10, 11], "kempfner": [11, 116, 132], "kept": [29, 32], "kern_length": 105, "kernel": [3, 4, 11, 26, 27, 28, 29, 30, 32, 49, 50, 51, 52, 68, 89, 90, 97, 98, 100, 104, 105, 110, 111, 114, 116], "kernel_block_4": 100, "kernel_block_5": 100, "kernel_length": 102, "kernel_s": [9, 10, 90, 99, 100, 104, 105, 114, 153], "kernel_unit_": 98, "keyboard": [72, 131], "keyword": [35, 36, 78, 117, 119, 120, 121, 122, 123, 129], "kfold": [4, 29, 30], "khan": 79, "khan2022": 79, "kiessner": 153, "kim": [49, 50, 51, 52, 68, 98], "kind": [14, 26], "kingma": 31, "know": [2, 3, 4, 26, 27], "known": [4, 72], "kobayashi": 105, "kolter": 114, "koltun": 114, "kosta": 115, "krell": [49, 50, 51, 52, 68], "kt": 89, "kumar": 31, "kv": [27, 28], "kwarg": [36, 72, 99, 121, 131, 137, 138, 139], "l": [5, 9, 10, 11, 12, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 89, 90, 93, 103, 105, 106, 109, 113, 116, 132, 146], "l2": [5, 89, 105], "l_freq": [2, 3, 4, 5, 8, 9, 10, 16, 27, 28, 29, 30, 32, 119], "l_trans_bandwidth": 119, "lab": 77, "label": [2, 3, 5, 8, 9, 10, 11, 12, 16, 22, 26, 27, 28, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 131, 134, 136, 140, 142, 146], "label_dict": [27, 28], "labelcolor": [2, 5, 8, 27, 28], "labelpad": 12, "labels": [2, 8, 12, 27, 28], "labels1": 5, "labels2": 5, "labram": [26, 153], "lack": 144, "lam": [47, 66], "lambda": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32, 72, 103, 131], "lampx": 27, "lan": [9, 10, 11], "lanc": [101, 102], "languag": 91, "larg": [2, 5, 14, 16, 26, 27, 75, 91, 107, 125, 130], "larger": [2, 5, 27, 97], "largest": 97, "larson": 35, "laskari": 97, "last": [5, 22, 27, 31, 32, 46, 48, 54, 65, 70, 77, 80, 84, 85, 86, 89, 95, 105, 119, 122, 124, 125, 153], "last_samp": 117, "last_target_onli": [2, 8, 83, 124, 126], "latenc": 104, "later": [5, 12, 22, 76, 77, 79, 81, 82, 93], "later_pool_mod": [14, 93], "later_pool_nonlin": 93, "latest": [147, 150, 151], "latter": [89, 90, 95, 98], "lauri": 35, "lawhern": [97, 101, 102], "layer": [3, 4, 5, 9, 10, 11, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 153], "layernorm": [10, 107], "lazi": [12, 15, 16, 23, 24, 82, 93, 109, 124, 152, 153], "lazy_metadata": [124, 153], "lazy_vs_eager_loading_result": 14, "lbfg": 5, "lead": [27, 29, 72, 123, 131], "leaderboard": [74, 77], "leakag": [29, 32], "leakyrelu": 115, "learn": [1, 2, 3, 4, 6, 8, 9, 10, 11, 24, 25, 27, 28, 29, 31, 32, 33, 35, 37, 38, 39, 40, 44, 46, 47, 54, 57, 58, 59, 60, 63, 65, 66, 70, 72, 75, 78, 80, 90, 91, 92, 93, 97, 99, 103, 104, 106, 107, 108, 109, 111, 112, 121, 125, 128, 130, 131, 133, 134, 144, 146, 148, 150, 152, 153], "learnabl": [29, 107, 113], "learning_r": 30, "least": [12, 119, 133, 134, 143], "leav": [5, 29, 153], "leeb": [27, 28, 29, 30], "left": [12, 27, 28, 29, 40, 72, 74, 77, 131], "left_hand": [18, 21, 27, 28, 29, 30, 32], "leftward": 77, "legaci": [20, 119], "legend": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 31], "len": [5, 8, 9, 10, 11, 12, 14, 17, 20, 22, 29, 32, 129], "len_last_lay": [9, 10], "length": [8, 9, 11, 12, 14, 16, 26, 27, 30, 46, 47, 65, 66, 74, 75, 77, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 119, 122, 124, 125, 153], "less": [5, 27, 29, 32], "let": [3, 4, 22, 26], "level": [5, 9, 10, 22, 73, 108, 117, 119, 120, 122, 123, 153], "leverag": [5, 112], "lfilter": 119, "lfp": 113, "li": [107, 113], "li2017": 113, "liang": 107, "lib": [2, 5, 10, 11, 27, 31, 32], "librari": [2, 3, 4, 8, 24, 26, 28, 29, 30, 35, 73, 151], "licens": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 31], "light": [11, 146], "lightning_log": 32, "lightningmodul": 32, "like": [2, 8, 16, 26, 28, 29, 30, 32, 37, 42, 48, 49, 57, 62, 67, 68, 72, 84, 85, 86, 90, 91, 92, 94, 96, 101, 103, 104, 107, 108, 110, 111, 112, 114, 115, 116, 119, 120, 131, 133, 151], "likelihood": [27, 72], "limit": [2, 5, 8, 11, 12, 16, 26, 117], "lin": 108, "line": [2, 8, 14, 27, 28, 31, 74, 147], "line2d": [2, 8, 27, 28], "linear": [5, 9, 10, 26, 30, 47, 66, 89, 91, 93, 94, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 109, 110, 111, 112, 114, 115, 116, 119, 122], "linear_model": 5, "linearattentiontransform": 91, "linearsegmentedcolormap": 146, "lines1": 5, "lines2": 5, "linestyl": [2, 8, 12, 27, 28], "linewidth": [2, 8, 27, 28], "link": 147, "linspac": [4, 12], "lioi": 104, "list": [3, 5, 11, 14, 16, 21, 22, 26, 27, 28, 29, 31, 32, 35, 36, 40, 41, 48, 50, 51, 52, 59, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 118, 119, 120, 123, 124, 125, 129, 130, 131, 141, 143, 146, 153], "list_of_d": [5, 75], "list_of_epoch": [19, 85], "lit_model": 32, "lite": 90, "litmodul": 32, "littl": 77, "liu": [44, 63, 95], "ll": 22, "load": [12, 16, 17, 19, 22, 23, 73, 75, 78, 80, 82, 87, 93, 109, 121, 124, 125, 130, 152, 153], "load_concat_dataset": [18, 153], "load_data": [17, 19, 78], "load_eeg_onli": 80, "load_example_data": 14, "load_param": 5, "load_state_dict": 99, "loader": [3, 4, 5, 14, 32], "loc": [2, 8, 12, 26, 27, 28, 29], "local": [2, 5, 10, 11, 14, 27, 31, 32, 73, 123, 147, 151], "locat": [27, 73], "locuslab": 114, "log": [22, 26, 27, 32, 72, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 117, 119, 120, 122, 123, 124, 125, 131, 153], "log10": 3, "log_dict": 32, "log_every_n_step": 32, "log_reg": 5, "logger": 32, "logger_connector": 32, "logic": [8, 9, 10, 11, 28, 30, 32], "logist": 5, "logisticregress": 5, "logit": 89, "logno": 26, "logsoftmax": [26, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 153], "long": [8, 14, 29, 30, 77, 94], "longer": [5, 29, 32, 72, 131], "look": [11, 12, 17, 22, 26, 29, 73, 133], "loop": [5, 9, 10, 11, 14, 72, 131], "lope": 153, "lopez": [47, 66, 141], "loss": [2, 5, 8, 9, 10, 11, 14, 26, 27, 28, 31, 32, 72, 89, 91, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 131, 136, 140, 141], "loss_fn": 32, "loss_funct": [136, 140], "loss_val": 14, "lot": [9, 10, 11, 72, 131], "lott": [48, 67], "lotte2015": 48, "low": [2, 3, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 32, 37, 57, 97, 104, 119], "low_cut_hz": [2, 3, 4, 8, 27, 28, 29, 30, 32], "lower": [5, 9, 12, 29, 32, 37, 57, 119, 139], "lower_is_bett": [2, 5, 8, 9, 10, 11, 137, 138, 139], "lowest": 5, "lowpass": [5, 9, 10, 16], "lr": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 72, 131], "lr_schedul": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "lrschedul": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "lt": 4, "lu": 107, "ludwig": 97, "luessi": 35, "luka": [12, 17, 18, 19, 20, 21, 22, 31, 35, 153], "m": [3, 4, 5, 9, 10, 11, 12, 16, 22, 26, 27, 28, 29, 30, 31, 32, 37, 40, 44, 49, 50, 51, 52, 54, 57, 59, 63, 68, 70, 79, 89, 90, 91, 92, 93, 97, 101, 102, 103, 105, 106, 108, 109, 111, 116, 119, 132, 146, 151], "m1": 123, "m2": 123, "m_": [127, 128], "m_t": [127, 128], "machin": [12, 14, 16, 29, 32, 35, 37, 40, 44, 54, 57, 59, 63, 70, 72, 97, 105, 131], "maciej": [2, 8, 153], "maciek": [2, 8], "macro": [5, 9, 10, 11], "made": [16, 27, 98, 153], "mae": [37, 44, 54, 57, 63, 70], "magnitud": [42, 54], "mai": [2, 3, 4, 5, 8, 9, 10, 11, 16, 18, 19, 27, 28, 29, 32, 35, 46, 65, 72, 107, 131, 139, 144, 147], "main": [5, 97, 98], "mainak": 35, "maintain": 77, "make": [2, 3, 4, 5, 8, 9, 11, 12, 27, 28, 29, 30, 32, 112, 119, 147, 153], "make_pipelin": 5, "make_standard_montag": [49, 68], "male": 12, "male_df": 12, "malici": 5, "manag": [8, 9, 10, 11, 28, 30, 31], "mandatori": 4, "mani": [2, 4, 5, 8, 16, 26, 27, 29, 32, 75], "manipul": 17, "manual": [26, 27, 29, 150], "map": [5, 9, 10, 11, 22, 26, 27, 28, 29, 30, 31, 35, 72, 86, 89, 93, 103, 104, 106, 109, 124, 125, 131, 146], "map_loc": 5, "marco": 153, "mark": [5, 9, 10, 11, 46, 65], "marker": [2, 5, 8, 16, 27, 28], "martin": [35, 153], "martin2023": 90, "martincod": 90, "martinez": 97, "martinwimpff": 90, "mask": [2, 5, 46, 54, 65, 70, 107, 112, 140], "mask_len_sampl": [4, 54, 70], "mask_start_per_sampl": [54, 70], "maskencod": 153, "mass": 9, "master": 151, "mastoid": [74, 123], "match": [16, 18, 19, 26, 75, 89], "mathemat": 27, "mathrm": [127, 128], "matplotlib": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31, 146, 153], "matric": [27, 28, 50, 51, 52, 72, 131], "matrix": [5, 9, 10, 11, 39, 40, 49, 59, 60, 68, 95, 104, 146, 153], "matter": [29, 32, 79, 81, 82], "matthieu": 153, "matti": 35, "max": [14, 16, 26, 29, 93, 101, 104, 109, 111, 115, 116, 119, 128], "max_degre": [49, 50, 51, 52], "max_delta_freq": [3, 43], "max_epoch": [5, 29, 32, 72, 131], "max_freq": 37, "max_it": 5, "max_mask_ratio": 46, "max_mem": 16, "max_norm_const": [89, 105], "max_pool_s": 110, "max_pool_size_": 111, "maxim": [9, 10, 30, 37], "maximum": [43, 49, 50, 51, 52, 89, 105, 124], "maxpool": [11, 116], "maxpool1d": [10, 11], "maxpool2d": 9, "mb": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 34, 152], "md": 5, "mean": [2, 3, 4, 8, 10, 12, 14, 16, 19, 26, 27, 29, 30, 31, 32, 77, 93, 102, 107, 109, 122, 123, 127, 128, 131, 147], "mean_test_scor": [4, 30], "mean_train_scor": [4, 30], "meaning": 29, "measur": 16, "mechan": [90, 112, 153], "med": [11, 116, 132], "median": 11, "medicin": [49, 50, 51, 52, 68], "meg": [3, 4, 20, 27, 28, 29, 30, 32, 35, 119, 120, 148], "meg0111": [119, 120], "meg2623": [119, 120], "mehr": [27, 28, 29, 30], "mem": [6, 13, 16, 23, 33, 34, 152], "memor": [29, 32], "memori": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 72, 125, 131], "memory_profil": 16, "memory_usag": 16, "mention": [26, 29], "merg": [5, 9, 10, 11, 153], "messag": [12, 14, 22, 147], "messi": 29, "metadata": [19, 26, 75, 83, 124, 131, 132, 133, 134, 135], "method": [2, 4, 5, 8, 12, 16, 21, 26, 29, 31, 32, 35, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 72, 73, 75, 76, 78, 83, 89, 90, 91, 92, 94, 95, 98, 99, 100, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 121, 122, 123, 131, 132, 133, 134, 136, 137, 138, 139, 140, 153], "methodolog": [90, 95, 104], "methodologi": 4, "metric": [2, 5, 9, 10, 11, 27, 28, 32, 146], "mi": [2, 8, 104], "mib": 16, "michael": 35, "micro": 12, "microcontinu": [5, 9, 10, 11], "microvolt": [5, 9, 10], "mietu": [9, 10, 11], "might": [5, 14, 16, 26, 29, 30, 32, 125, 133], "miller": [2, 8, 27, 28, 29, 30, 73], "min": [5, 12, 29, 80, 119], "ming": 107, "mini": [72, 131], "minibatch": 14, "minim": [31, 47, 48, 66, 67, 92, 141, 147], "minimum": 119, "minimum_phas": 119, "minut": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 80], "mirror": [119, 122], "misc": [2, 4, 8, 83], "misclass": [27, 28], "misclassif": [27, 28], "mismatch": 153, "miss": [26, 89, 90, 95, 98, 101, 102, 103, 104, 105, 106, 108, 110, 116, 153], "mistak": 147, "mix": [16, 18, 47, 48, 66, 141], "mixin": 99, "mixup": [141, 153], "mkdtemp": [12, 18], "ml": [29, 32], "mlp": [90, 107], "mlp_ratio": 107, "mlr": 97, "mne": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 15, 16, 17, 18, 20, 22, 23, 24, 25, 28, 30, 33, 49, 68, 73, 75, 76, 80, 83, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 129, 131, 147, 152, 153], "mne_data": [16, 17, 19, 27, 73], "mne_datasets_": 73, "mne_datasets_bnci_path": 27, "mne_filter_kwarg": 129, "mnepreproc": 153, "mo": [2, 8], "moabb": [3, 4, 15, 18, 21, 23, 24, 27, 28, 29, 30, 32, 74, 75, 77, 78, 121, 130, 150, 151, 152, 153], "moabbdataset": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32, 153], "mock": [12, 22], "mode": [2, 5, 24, 32, 72, 93, 107, 119, 122, 131, 139, 151, 153], "model": [12, 14, 21, 33, 35, 44, 63, 72, 75, 76, 78, 79, 121, 124, 125, 128, 130, 131, 136, 137, 138, 139, 140, 141, 142, 144, 145, 148, 152, 153], "model_build": [32, 33, 152], "model_evalu": [72, 131], "model_kind": 14, "model_nam": 31, "model_select": [4, 5, 8, 29, 30], "model_train": 14, "model_training_end": 14, "model_training_start": 14, "models_dict": [26, 72, 131, 153], "modelstatist": 99, "modif": [92, 107, 113], "modifi": [3, 5, 10, 12, 42, 62, 72, 90, 99, 117, 118, 120, 121, 129, 131, 144], "modul": [2, 4, 5, 8, 9, 10, 11, 14, 26, 28, 30, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 142, 144, 146, 150, 153], "module_": [3, 4, 9, 10, 11, 26, 72, 131], "module__": 26, "module__drop_prob": 30, "module__final_conv_length": 26, "modulelist": 10, "moham": [2, 8, 153], "mohammad": 153, "mohsenvand": [37, 44, 54, 57, 63, 70], "momentum": [10, 26, 93, 97, 109], "monopolarli": 74, "montag": [50, 51, 52, 74, 81, 82, 153], "month": [12, 35], "moodi": [9, 10, 11], "more": [1, 2, 3, 4, 5, 8, 9, 10, 11, 16, 18, 20, 21, 22, 24, 26, 27, 28, 29, 30, 46, 65, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 122, 123, 130, 131, 144, 151, 153], "moreau": [4, 153], "morlet": 113, "most": [3, 9, 10, 11, 14, 134, 147, 150], "mostli": 27, "motor": [2, 4, 8, 27, 28, 74, 77, 89, 90, 96, 98, 104, 105, 153], "moustapha": [47, 66, 141], "move": [2, 3, 4, 8, 14, 16, 27, 28, 29, 30, 32, 73, 99, 127, 128, 153], "movement": [74, 77], "mrcnn": 112, "mse": 31, "mse_loss": [2, 31], "mseloss": [8, 131], "msg": [2, 31], "much": [5, 27, 72, 90, 122, 131], "mueller": [27, 28, 29, 30], "muhammad": 89, "mult": [3, 4, 11, 26, 27, 28, 29, 32], "multi": [90, 112], "multi_class": 5, "multiclass": 32, "multiindex": 133, "multimedia": [44, 63], "multimod": [5, 9, 10, 111], "multinomi": 5, "multipl": [2, 3, 4, 8, 9, 10, 14, 15, 16, 21, 23, 24, 27, 29, 30, 72, 75, 81, 90, 98, 116, 119, 123, 124, 129, 131, 142, 152, 153], "multipli": [3, 4, 5, 9, 10, 12, 27, 28, 29, 30, 32, 89, 97, 100, 105], "multitap": 3, "multivari": [5, 9, 10, 111], "murad": 153, "muscular": 77, "music": 113, "must": [3, 4, 12, 14, 16, 18, 20, 21, 26, 29, 30, 83, 93, 109, 110, 117, 121, 123, 124, 132, 150, 153], "mypi": 153, "m\u00fcller": [27, 28, 29, 30], "n": [14, 16, 22, 26, 27, 28, 29, 30, 32, 34, 37, 38, 39, 44, 47, 54, 57, 58, 60, 63, 66, 70, 89, 91, 97, 101, 102, 104, 105, 111, 141], "n1": [5, 9, 10, 11], "n2": [5, 9, 10, 11], "n3": [5, 9, 10, 11], "n4": 10, "n_attn_head": 112, "n_batch": [32, 136, 140], "n_block": 114, "n_chan": [2, 8, 11, 26, 27, 28, 30, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131], "n_channel": [3, 4, 5, 9, 10, 14, 17, 19, 22, 29, 31, 32, 47, 49, 66, 68, 84, 89, 91, 92, 94, 95, 104, 106, 108, 110, 111, 112, 114, 115, 127, 128], "n_class": [2, 3, 4, 9, 10, 11, 14, 26, 27, 28, 29, 30, 31, 32, 72, 89, 93, 94, 95, 96, 97, 98, 101, 102, 103, 106, 109, 110, 111, 112, 115, 116, 131, 136, 140, 142], "n_codeword": 90, "n_compon": 5, "n_conv": [98, 104], "n_conv_ch": [5, 111], "n_conv_chan": 110, "n_epoch": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32], "n_exampl": [5, 134], "n_examples_test": 5, "n_examples_train": 5, "n_examples_valid": 5, "n_fake_ch": 31, "n_fake_chan": 31, "n_fake_rec": 31, "n_fake_target": 31, "n_filter": [97, 98, 114], "n_filters_2": [14, 31, 93], "n_filters_3": [14, 31, 93], "n_filters_4": [14, 31, 93], "n_filters_spat": [14, 26, 31, 93, 109], "n_filters_tim": [14, 26, 31, 93, 95, 109], "n_first_filt": 103, "n_freq": 92, "n_group": 110, "n_in_chan": 114, "n_iter_i": 5, "n_job": [2, 3, 4, 5, 12, 14, 16, 27, 28, 29, 30, 32, 79, 81, 82, 87, 119, 122, 124, 125, 126, 130, 153], "n_layer": [91, 107], "n_layers_per_block": 103, "n_out_chan": 8, "n_output": [5, 9, 10, 11, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131], "n_patch": 107, "n_predict": [72, 131, 136, 140, 142], "n_preds_per_input": [2, 27, 31], "n_rec": 16, "n_record": [14, 133], "n_repet": 16, "n_repetit": 14, "n_segment": [46, 48, 65, 67], "n_sequenc": [132, 135], "n_split": [4, 29, 30], "n_target": [72, 131, 142], "n_tce": 112, "n_temporal_filt": 90, "n_test": 29, "n_time": [3, 4, 5, 8, 9, 10, 11, 12, 14, 17, 19, 26, 27, 28, 29, 30, 31, 32, 47, 66, 84, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 127, 128, 131, 136, 140], "n_time_filt": 116, "n_timestep": [95, 104], "n_train": 29, "n_train2": 29, "n_trial": [72, 84, 131, 142], "n_val": 29, "n_window": [9, 10, 11, 22, 89, 132, 135], "n_windows_strid": [9, 10, 11, 135], "nado": 30, "name": [0, 2, 3, 4, 5, 8, 9, 10, 11, 16, 17, 18, 20, 21, 22, 26, 29, 30, 32, 40, 72, 74, 75, 76, 78, 84, 87, 118, 119, 120, 121, 123, 131, 137, 138, 139, 153], "nan": [26, 140], "narayanan": [10, 153], "nativ": 11, "natur": [2, 8, 14, 73], "nbsp": 4, "nbviewer": 4, "ncol": 29, "ndarrai": [22, 49, 68, 72, 84, 122, 127, 128, 131, 135, 142, 143], "ndataset": 29, "necessari": [4, 72, 123, 131], "need": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 26, 27, 28, 29, 32, 72, 89, 90, 95, 98, 131, 144, 149, 153], "neg": [5, 27, 31, 72, 134], "neg_root_mean_squared_error": 31, "neighbour": 27, "neighbourhood": 27, "nemati": [42, 62], "net": [5, 8, 26, 72, 112, 113, 116, 131, 137, 138, 139], "network": [2, 4, 5, 7, 8, 10, 13, 14, 25, 26, 27, 28, 29, 32, 33, 35, 44, 63, 72, 75, 76, 80, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 101, 102, 103, 104, 105, 106, 108, 109, 110, 111, 112, 113, 114, 115, 116, 121, 124, 125, 130, 131, 133, 135, 136, 142, 144, 146, 152, 153], "neural": [2, 4, 5, 8, 9, 10, 11, 14, 25, 26, 27, 28, 29, 33, 35, 44, 46, 63, 65, 75, 76, 90, 91, 92, 93, 94, 95, 97, 98, 99, 103, 104, 106, 107, 108, 109, 110, 111, 112, 113, 115, 124, 136, 144, 146, 152, 153], "neural_token": 107, "neuralnet": [72, 131], "neuralnetclassifi": [9, 10, 11, 28, 30], "neuralnetregressor": 8, "neurip": [91, 97], "neurologi": 108, "neuron": [5, 9, 10, 11], "neurophysiolog": 148, "neurosci": [27, 28, 29, 30, 35, 79], "neuroscientist": 148, "never": [29, 32], "new": [5, 9, 10, 11, 20, 40, 48, 59, 67, 72, 107, 117, 123, 131, 147, 151], "next": [3, 4, 5, 9, 10, 11, 12, 14, 16, 18, 22], "nice": 32, "night": [9, 10, 11], "nikol": [11, 116, 132], "nllloss": 72, "nmt": 153, "nn": [2, 3, 4, 5, 8, 9, 10, 11, 14, 26, 27, 28, 29, 30, 31, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 142], "nnloss": 32, "no_grad": [5, 32], "nois": [31, 44, 63, 74], "noisi": [42, 62], "nolt": [27, 28, 29, 30], "nomenclatur": 40, "non": [3, 4, 11, 16, 22, 26, 27, 28, 29, 30, 32, 72, 77, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 119, 131, 153], "none": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 18, 19, 20, 22, 26, 27, 28, 29, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 62, 63, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 120, 122, 123, 124, 125, 126, 127, 128, 130, 131, 132, 133, 134, 135, 137, 138, 139, 144, 146, 153], "nonlinear": [5, 29, 72, 89, 131], "noqa": [12, 22], "norm": [10, 89, 105], "norm_ax": 146, "norm_lay": 107, "normal": [2, 5, 8, 9, 10, 28, 30, 107, 108, 110, 111, 113, 133, 146, 153], "normalis": [26, 93, 104, 109], "notabl": [72, 131], "notat": [72, 131], "notch": 74, "notch_filt": 119, "note": [2, 3, 4, 5, 8, 9, 11, 17, 20, 26, 27, 28, 43, 61, 72, 73, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 120, 123, 131, 139, 144], "notebook": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "novel": [26, 46, 65, 97], "novemb": 91, "now": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 22, 26, 27, 28, 30, 123, 151, 153], "np": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 26, 29, 31, 32, 72, 127, 128, 131, 132, 133, 134, 135, 142], "npad": 122, "npj": [11, 116, 132], "nrepetit": 14, "nsplit": 29, "num_class": 32, "num_filt": 113, "num_head": 107, "num_param": 99, "num_work": [5, 14, 32, 142], "number": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 22, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 65, 67, 68, 70, 72, 75, 80, 81, 82, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 122, 124, 125, 129, 130, 131, 132, 133, 134, 135, 142, 143], "numer": 125, "numpi": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 17, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 68, 72, 119, 122, 131, 144, 146], "numpypreproc": 153, "nvidia": 150, "nyquist": 37, "o": [2, 4, 5, 8, 16, 27, 28, 37, 38, 39, 40, 44, 54, 57, 58, 59, 60, 63, 70, 90, 134], "o1": [12, 129], "o1_4": 129, "o1_8": 129, "o2": 12, "obery": 5, "obery\u00e9": [9, 10, 11], "object": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 18, 19, 21, 27, 28, 29, 30, 31, 32, 41, 76, 79, 80, 81, 82, 83, 86, 117, 121, 124, 125, 130, 146, 153], "obtain": [2, 3, 4, 5, 8, 9, 11, 27, 28, 49, 68, 72, 76, 77, 83, 104, 131, 133], "odd": [11, 98, 116], "off": [26, 29, 30, 119], "offici": [89, 150], "offset": [3, 4, 27, 28, 29, 30, 32, 75, 86, 124, 125, 130, 153], "often": [4, 9, 10, 11, 28, 30], "old": [75, 130, 153], "omar": [11, 153], "omega": 113, "omega_init_valu": 113, "omit": [9, 37], "on_batch_end": 138, "on_epoch_end": [137, 138, 139], "on_miss": [118, 124, 125], "on_train": [2, 5, 8, 9, 10, 11, 137, 138], "onc": [5, 16, 29, 119, 124, 134, 151], "one": [2, 4, 8, 9, 10, 11, 14, 16, 20, 26, 27, 29, 30, 32, 41, 46, 47, 54, 65, 70, 72, 74, 75, 89, 90, 95, 98, 99, 116, 123, 124, 125, 130, 131, 132, 133, 134, 147], "ones": [12, 26, 132, 153], "onli": [2, 4, 5, 8, 9, 10, 11, 12, 14, 18, 19, 21, 26, 27, 29, 30, 32, 41, 56, 72, 77, 80, 86, 91, 96, 97, 98, 100, 101, 102, 107, 117, 119, 120, 122, 123, 124, 125, 131, 140, 147, 151, 153], "onlin": [47, 66, 93, 97, 103, 106, 109, 141, 146], "onset": [86, 125], "open": [5, 16, 18, 79, 147, 148, 150], "openli": [4, 5, 9, 10, 11], "oper": [2, 3, 4, 8, 16, 37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 64, 90, 117, 122], "optim": [2, 3, 4, 5, 8, 9, 10, 11, 14, 27, 28, 29, 30, 31, 32, 72, 77, 131, 153], "optimizer__lr": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 72, 131], "optimizer__momentum": [72, 131], "optimizer__weight_decai": [2, 3, 4, 8, 27, 28, 29, 31], "optimizer_lr": 31, "optimizer_weight_decai": 31, "option": [5, 10, 18, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 72, 75, 78, 86, 89, 90, 91, 92, 97, 98, 99, 100, 104, 105, 107, 108, 113, 119, 122, 125, 131, 142, 146, 151, 153], "orang": [5, 12, 16], "order": [3, 4, 12, 21, 26, 40, 48, 50, 51, 52, 59, 72, 77, 79, 81, 82, 90, 119, 123, 129, 131, 135, 153], "order_by_frequency_band": 129, "ordered_ch_nam": [40, 50, 51, 52], "org": [2, 4, 5, 8, 26, 27, 28, 29, 30, 35, 47, 66, 72, 73, 80, 89, 93, 95, 96, 97, 98, 99, 101, 103, 104, 105, 106, 109, 110, 112, 114, 115, 116, 131, 141, 144, 146], "orient": 12, "origin": [3, 11, 17, 19, 26, 29, 47, 48, 49, 50, 51, 52, 54, 66, 68, 70, 75, 86, 90, 92, 95, 96, 97, 98, 100, 101, 102, 104, 107, 108, 113, 119, 125, 129, 130], "oscil": 113, "oscillatori": [48, 67], "oskar": 153, "other": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 18, 26, 29, 30, 32, 56, 72, 77, 80, 89, 90, 91, 93, 94, 99, 103, 105, 106, 107, 109, 110, 111, 112, 114, 116, 131], "otherwis": [2, 14, 27, 29, 31, 86, 125], "ou": 4, "ouahidi": [104, 153], "our": [2, 5, 8, 9, 10, 11, 12, 16, 20, 26, 27, 28, 30, 32, 77, 149], "out": [4, 8, 9, 10, 26, 37, 46, 54, 57, 65, 70, 72, 74, 90, 91, 113, 131, 132, 140, 147], "out_channel": 107, "out_featur": [9, 10], "out_path": 12, "outcom": [72, 131], "outlier": 12, "output": [2, 3, 4, 5, 11, 12, 14, 21, 26, 27, 28, 29, 30, 31, 32, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 120, 122, 123, 124, 125, 131], "output_s": [10, 99], "output_shap": 99, "outsid": [86, 125], "over": [4, 10, 16, 29, 31, 32, 42, 49, 50, 51, 52, 62, 68, 72, 131, 153], "overal": 14, "overfit": [2, 8, 9, 10, 11, 29, 90], "overhead": [14, 125], "overlaid": [9, 10, 11], "overlap": [9, 10, 11, 46, 65, 84, 85, 86, 119, 124, 125], "overnight": 80, "overrid": [72, 73, 131], "overridden": [89, 90, 95, 98], "overwrit": [16, 18, 72, 75, 76, 79, 81, 82, 83, 88, 130, 131], "own": [2, 8, 27, 28, 29, 30, 32, 77, 147], "oz": 10, "p": [5, 9, 10, 27, 28, 29, 30, 31, 37, 44, 54, 57, 63, 70, 79, 97, 100, 101, 102, 111], "p2": 89, "p3": 12, "p4": 12, "p_drop": [4, 38, 58], "p_shuffl": [39, 60], "pa": 89, "pace": 77, "packag": [2, 5, 10, 11, 27, 31, 32, 35, 149, 150], "pad": [2, 9, 10, 11, 27, 100, 111, 119, 122, 153], "pad_and_select_predict": 2, "pad_size_": 111, "padding_height": 100, "padding_width": 100, "page": [4, 29, 32, 35, 147], "paillard": 4, "pair": [5, 134], "pan": 100, "panagaki": 97, "panda": [2, 4, 5, 8, 9, 10, 11, 14, 16, 20, 21, 27, 28, 29, 30, 31, 72, 75, 76, 83, 86, 131], "paper": [4, 11, 35, 49, 50, 51, 52, 68, 89, 90, 95, 96, 97, 98, 100, 101, 102, 104, 112, 153], "paperswithcod": [74, 77], "paradigm": [4, 5, 72, 74, 104, 131, 142], "parallel": [12, 14, 15, 23, 24, 75, 80, 81, 82, 87, 97, 98, 119, 121, 122, 124, 125, 130, 152, 153], "param": [3, 4, 5, 11, 26, 27, 28, 29, 30, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54], "param_grid": [4, 29, 30], "param_iterator_train__transform": 4, "param_module__drop_prob": 30, "param_optimizer__lr": 30, "paramet": [2, 3, 4, 5, 8, 10, 14, 16, 17, 18, 19, 26, 28, 29, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 139, 140, 141, 142, 143, 144, 146, 153], "parameter": 113, "parent": [79, 81, 82], "parkkonen": 35, "pars": 12, "part": [2, 8, 16, 17, 19, 28, 29, 32, 38, 39, 46, 54, 58, 60, 65, 70, 95, 97], "partial": 30, "particip": 79, "particular": 26, "pasdeloup": 104, "pass": [3, 4, 9, 10, 11, 16, 22, 26, 27, 28, 29, 32, 36, 41, 56, 72, 78, 89, 90, 91, 92, 94, 95, 98, 100, 104, 105, 106, 108, 110, 111, 112, 113, 114, 115, 117, 119, 120, 122, 123, 131, 136, 139, 140, 153], "passband": 16, "past": 147, "patch": [29, 107], "patch_siz": 107, "patchemb": 107, "patchembed": 95, "patchfrequencyembed": 91, "path": [12, 14, 17, 18, 19, 22, 32, 73, 75, 79, 81, 82, 87, 88], "pathlib": 87, "patholog": [14, 18, 79, 82], "pathologi": 30, "patienc": 5, "patient": [12, 73], "pattern": 108, "paz": [47, 66, 141], "pazo": 110, "pc": 89, "pca": 5, "pch": [9, 10, 11], "pd": [2, 4, 5, 8, 9, 10, 11, 14, 16, 27, 28, 29, 30, 31, 75, 76, 83, 132, 133, 134, 135], "pdf": 73, "peak": [16, 124, 125], "pearson": 8, "pearson_r_scor": 8, "penalti": 5, "peng": [9, 10, 11, 44, 63, 107], "peopl": 115, "per": [2, 4, 5, 8, 9, 10, 11, 27, 46, 47, 54, 65, 70, 74, 77, 80, 98, 104, 108, 115, 123, 153], "percent": [27, 28], "percentag": 115, "percept": 32, "perceptron": 90, "perez": 96, "perform": [2, 4, 8, 9, 10, 11, 26, 27, 28, 29, 30, 32, 74, 75, 77, 89, 90, 95, 98, 104, 112, 127, 128, 153], "period": [31, 108], "permut": [39, 40, 47, 59, 60, 66], "persist": 147, "perslev": [11, 116, 132], "perslev2021": 132, "perturb": [42, 62], "phase": [16, 42, 62, 107, 113, 119, 122], "phase_freq": 4, "phase_init_valu": 113, "phase_noise_magnitud": [4, 42, 62], "phenomenon": 4, "phi_c": 113, "physic": 89, "physician": [81, 82], "physiobank": [5, 9, 10, 11], "physiolog": [5, 9, 10, 11], "physionet": [5, 7, 13, 16, 24, 75, 80, 99, 111, 112, 116, 121, 125, 130, 133, 135, 144, 146, 152, 153], "physionet_path": [17, 19], "physiotoolkit": [5, 9, 10, 11], "pi": [31, 42, 62], "pick": [2, 8, 10, 12, 19, 20, 119, 124, 125, 126, 153], "pick_channel": [12, 118, 121], "pick_typ": [2, 3, 4, 8, 20, 27, 28, 29, 30, 32, 118], "pickl": 5, "pickleabl": [72, 131], "piconepress": [12, 14, 81, 82], "pierr": [26, 153], "pietquin": [38, 39, 58, 60], "pin": 14, "pin_memori": 14, "pip": [32, 149, 150, 151, 153], "pipelin": [2, 5, 8, 29, 32], "pivot": 30, "pivot_t": 30, "pj": [11, 116, 132], "place": [20, 31, 99, 117, 129], "playbook": 30, "pleas": [2, 4, 5, 8, 11, 12, 22, 26, 27, 32, 73, 89, 93, 95, 96, 97, 98, 99, 101, 103, 104, 106, 109, 110, 114, 115, 116, 129, 151], "plot": [3, 5, 12, 14, 16, 29, 31, 153], "plot_basic_training_epoch": [26, 33, 152], "plot_bcic_iv_2a_moabb_crop": [27, 33, 152], "plot_bcic_iv_2a_moabb_tri": [28, 33, 152], "plot_bcic_iv_4_ecog_crop": [2, 6, 152], "plot_bcic_iv_4_ecog_tri": [8, 13, 152], "plot_benchmark_preprocess": [16, 23, 152], "plot_confusion_matrix": [9, 10, 11, 27, 28, 153], "plot_custom_dataset_exampl": [17, 23, 152], "plot_data_augment": [3, 6, 152], "plot_data_augmentation_search": [4, 6, 152], "plot_how_train_test_and_tun": [29, 33, 152], "plot_hyperparameter_tuning_with_scikit": [30, 33, 152], "plot_k_fold": 29, "plot_load_save_dataset": [18, 23, 152], "plot_mne_dataset_exampl": [19, 23, 152], "plot_moabb_dataset_exampl": [20, 23, 152], "plot_psd": 3, "plot_regress": [31, 33, 152], "plot_relative_posit": [5, 6, 152], "plot_simple_train_test": 29, "plot_sleep_staging_chambon2018": [9, 13, 152], "plot_sleep_staging_eldele2021": [10, 13, 152], "plot_sleep_staging_usleep": [11, 13, 152], "plot_split_dataset": [21, 23, 152], "plot_train_in_pure_pytorch_and_pytorch_lightn": [32, 33, 152], "plot_train_valid_test": 29, "plot_tuh_discrete_multitarget": [22, 23, 152], "plot_tuh_eeg_corpu": [12, 13, 152], "plt": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31], "plt_histogram": 12, "pmlr": [37, 44, 54, 57, 63, 70], "point": [19, 20, 26, 74, 123, 127, 128], "polici": [38, 39, 58, 60], "poly1d": 31, "polyfit": 31, "polyphas": 122, "pool": [3, 4, 26, 27, 28, 29, 32, 89, 90, 93, 95, 97, 99, 100, 104, 107, 109, 111, 113, 115, 116], "pool_length": 90, "pool_length_inp": 90, "pool_mod": [26, 101, 102, 109], "pool_nonlin_exp": [3, 4, 26, 27, 28, 29, 32], "pool_siz": 113, "pool_strid": 90, "pool_stride_inp": 90, "pool_time_length": [14, 26, 93, 95, 109], "pool_time_strid": [14, 26, 93, 95, 109], "pooling_s": 97, "popul": [72, 131, 153], "popular": 26, "portion": 147, "posit": [1, 6, 24, 27, 37, 46, 49, 50, 51, 52, 54, 57, 65, 68, 70, 75, 80, 99, 107, 111, 121, 125, 130, 133, 134, 143, 144, 152], "positionwisefeedforward": 112, "possibl": [3, 4, 5, 11, 12, 16, 18, 26, 72, 74, 124, 131, 144, 147, 153], "potenti": [14, 16, 32, 150], "power": [3, 5, 30, 119, 122], "pp": [10, 37, 44, 49, 50, 51, 52, 54, 57, 63, 68, 70, 95, 112], "pre": [26, 84, 91, 107, 123, 153], "preced": 8, "precis": [5, 9, 10, 11, 146], "pred": [2, 8, 32, 136, 140, 141, 143], "predefin": [2, 8, 28, 30], "predefined_split": [2, 3, 5, 8, 9, 10, 11, 27, 28, 29, 31], "predict": [2, 4, 5, 8, 9, 10, 11, 27, 28, 31, 72, 76, 79, 99, 104, 131, 136, 137, 138, 139, 140, 141, 142, 143, 153], "predict_nonlinear": [72, 131], "predict_proba": [72, 131, 153], "predict_tri": [2, 72, 131, 153], "preds_per_tri": 143, "preds_test": [2, 8], "preds_train": [2, 8], "preds_valid": [2, 8], "prefer": [72, 131], "prefix": [26, 72, 131], "prefixes_": [72, 131], "preload": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 22, 27, 28, 29, 30, 31, 32, 79, 80, 81, 82, 86, 87, 123, 124, 125, 126, 130, 153], "prepar": [14, 16, 20, 32], "prepare_data": 16, "prepocess": [2, 8, 28, 30], "preprint": [5, 31, 37, 38, 39, 40, 42, 44, 54, 57, 58, 59, 60, 62, 63, 70, 90, 101, 102, 104, 114, 134], "preprocess": [14, 15, 18, 19, 20, 21, 22, 23, 24, 26, 31, 75, 80, 148, 152, 153], "preprocessor": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 18, 20, 27, 28, 29, 30, 32, 130, 153], "presampl": [5, 134], "present": [4, 29, 32, 74, 77, 91, 118], "preserv": [48, 79, 81, 82], "press": 97, "pretext": 4, "pretti": [14, 147], "prevent": 90, "previou": [32, 153], "previous": [29, 32], "print": [2, 4, 5, 8, 9, 10, 11, 14, 17, 20, 21, 22, 26, 27, 28, 29, 30, 32, 72, 131, 147], "print_batch_stat": 32, "print_log": [72, 131], "prior": [5, 99], "prob": 4, "proba_drop": 38, "probabl": [3, 4, 26, 30, 32, 37, 38, 39, 40, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 72, 89, 90, 91, 93, 96, 109, 114, 115, 131], "problem": [5, 26, 42, 62, 147, 150], "proc": 16, "proceed": [48, 67, 97], "process": [2, 4, 5, 7, 8, 13, 14, 15, 16, 22, 24, 29, 30, 48, 67, 75, 81, 90, 91, 100, 113, 121, 124, 130, 152, 153], "process_pipelin": 78, "processor": [29, 30], "produc": [27, 29, 32, 112], "product": [14, 16], "progress_bar": 32, "project": [5, 12, 14, 19, 26, 81, 82, 123], "projector": 123, "prompt": [74, 147], "propag": 153, "proper": [2, 8], "properli": [29, 119, 122, 123], "properti": [5, 75, 153], "proport": [86, 97, 125], "propos": [4, 38, 39, 42, 48, 54, 58, 60, 62, 70, 91, 98, 153], "protonmail": [3, 20], "provid": [2, 8, 9, 10, 11, 26, 28, 30, 32, 35, 72, 74, 75, 76, 79, 81, 82, 91, 119, 120, 121, 130, 131, 147], "provind": 4, "proxim": 77, "psd": 3, "psd_array_multitap": 3, "psds_mean": 3, "pseudo": 77, "psg": 16, "pt": [5, 89], "publish": 26, "pure": [2, 5, 8, 28, 30, 153], "purpos": [3, 14, 16, 32], "push": [27, 72, 131], "putz": [27, 28, 29, 30], "py": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 152, 153], "pypi": 149, "pyplot": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31], "pyproject": 153, "python": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 35, 117, 144, 148, 149, 151, 153], "python3": [2, 5, 10, 11, 27, 31, 32], "pythonhashse": 144, "pytorch": [2, 5, 8, 14, 22, 24, 25, 26, 27, 28, 30, 33, 72, 75, 78, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 101, 103, 104, 106, 107, 108, 109, 110, 111, 112, 114, 115, 116, 121, 125, 128, 130, 131, 142, 144, 150, 152, 153], "pz": [10, 12], "q": 95, "qixiang": 107, "qk_norm": 107, "qk_scale": 107, "qkv_bia": 107, "quadrat": [49, 50, 51, 52, 68], "quantiti": 5, "quantiz": [90, 107], "queri": 107, "quick": [5, 133], "quickli": 29, "quit": [26, 29], "r": [3, 5, 9, 10, 11, 26, 27, 28, 29, 30, 31, 37, 44, 54, 57, 63, 70, 79, 93, 97, 101, 102, 103, 106, 109, 112, 146], "r2": [2, 8], "r2_score": 2, "r2_train": 2, "r2_valid": 2, "r382d436f3223": 74, "r5e478952091a": 77, "rais": [4, 14, 26, 29, 30, 31, 72, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 118, 125, 130, 153], "rand_indic": [48, 67], "randint": [26, 31], "randn": 26, "random": [2, 3, 4, 5, 8, 9, 10, 11, 26, 27, 28, 30, 31, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 77, 132, 133, 134, 135, 139, 144, 153], "random_st": [4, 5, 8, 30, 37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 63, 132, 133, 134, 135], "randomli": [3, 5, 27, 37, 38, 39, 44, 46, 48, 54, 58, 60, 63, 135], "randomst": [132, 133, 134, 135], "rang": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 26, 27, 28, 29, 31, 32, 42, 62, 73, 104, 113, 129, 146], "rank_test_scor": [4, 29, 30], "rate": [2, 5, 14, 27, 28, 29, 30, 31, 32, 72, 90, 95, 97, 100, 107, 108, 110, 111, 112, 116, 131, 153], "rather": [9, 10], "ratio": [29, 46, 107], "ravel": 31, "raw": [2, 3, 4, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 27, 28, 29, 30, 31, 75, 76, 79, 80, 81, 82, 86, 94, 117, 118, 119, 120, 121, 123, 124, 125, 129, 148, 153], "raw_or_epoch": 121, "raw_preproc_kwarg": 75, "rawarrai": [17, 19, 31, 86], "rbf": [49, 50, 51, 52, 68], "re": [12, 21, 72, 123, 131, 147], "reach": [5, 9, 10, 32], "read": [12, 14, 16, 17, 18, 19, 79, 81, 82, 87, 125], "read_raw_edf": [17, 19], "readabl": [29, 32, 119], "readi": [12, 16, 17, 18, 19, 31], "readthedoc": 27, "real": 32, "realiz": 153, "realli": 29, "rearrang": [3, 4, 26, 27, 28, 29, 32, 153], "reason": [5, 10, 29, 32, 72, 131, 139], "rec_ind": [132, 133], "recal": [5, 9, 10, 11], "recalibr": [90, 112], "receiv": [5, 95], "recent": [4, 26, 147], "recept": [2, 27, 72, 131, 142], "recip": [89, 90, 95, 98], "reciproc": 119, "recod": 12, "recoding_id": 153, "recogn": [29, 32], "recognit": [44, 63, 113], "recombin": 95, "recommend": [5, 9, 11, 16, 29, 30, 35, 95, 104, 150, 151], "recomput": 139, "reconstruct": [48, 67, 119], "record": [2, 4, 8, 9, 10, 11, 14, 16, 21, 22, 26, 31, 73, 74, 77, 79, 80, 81, 82, 86, 90, 92, 93, 94, 95, 96, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 123, 124, 125, 132, 133, 134, 153], "recording_id": [5, 9, 10, 11, 12, 14, 16, 22, 79, 80, 81, 82], "recordingsampl": [132, 134, 135], "recurr": 114, "red": [2, 8, 27, 28], "reddi": 31, "reduc": [5, 10, 14, 16, 80, 90, 125], "reduct": 90, "reduction_r": 90, "redund": 27, "ref_channel": [12, 123], "refactor": 153, "refer": [12, 35, 37, 38, 39, 40, 42, 44, 46, 47, 48, 49, 50, 51, 52, 54, 57, 58, 59, 60, 62, 63, 65, 66, 67, 68, 70, 73, 74, 79, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 123, 129, 132, 134, 141, 146], "referenc": 123, "refit": [4, 29, 30], "reflect": [119, 122], "reflect_limit": [119, 122], "regard": [12, 104], "regardless": [72, 131], "regim": 5, "region": [12, 119], "regist": [89, 90, 95, 98], "regress": [2, 5, 8, 24, 25, 30, 33, 75, 76, 93, 99, 109, 124, 131, 136, 144, 152, 153], "regressor": [2, 8, 26, 31, 153], "regular": [5, 90, 127, 128], "rehabilit": [5, 9, 10, 46, 65, 94, 95, 97, 111, 112], "reimplement": [96, 97, 98, 100, 101, 102], "reiniti": [29, 32], "reject": [10, 19, 124, 125, 126], "rel": [1, 6, 24, 29, 30, 75, 80, 99, 111, 121, 125, 130, 133, 134, 144, 152], "relat": [4, 5, 26, 27, 35, 77, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 153], "relativepositioningdataset": 5, "relativepositioningsampl": 5, "relax": 77, "releas": [5, 147, 151], "relev": [5, 29, 35, 72, 131], "reliabl": [29, 32, 100], "reload": [12, 16, 130], "relu": [9, 10, 90, 91, 92, 94, 96, 98, 101, 103, 104, 107, 108, 110, 111, 112, 113, 114, 115, 116], "rem": [9, 10, 11], "remain": [16, 29, 32], "rememb": [4, 29, 32], "remi": 153, "remov": [2, 3, 4, 5, 8, 9, 11, 18, 19, 20, 21, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 118, 123, 143, 153], "renam": [3, 4, 18, 20, 21, 29, 30, 81, 82, 153], "rename_channel": [12, 81, 82], "render": 4, "reorder": [38, 39, 58, 60], "reorder_channel": 118, "repeat": [14, 147], "repetit": [14, 16, 77], "replac": [29, 46, 54, 65, 70, 153], "replic": 147, "repo": 151, "report": [5, 9, 10, 11, 14, 29, 32, 81, 82, 89, 147], "report_messag": 4, "repositori": [104, 149], "repres": [21, 50, 51, 52, 95, 104], "represent": [4, 37, 44, 47, 54, 57, 63, 66, 70, 91, 92, 107, 153], "reproduc": [2, 3, 4, 5, 8, 9, 10, 11, 24, 27, 28, 30, 144, 153], "request": [27, 119, 123, 147], "requir": [5, 11, 12, 14, 16, 17, 22, 56, 72, 77, 83, 131, 153], "rerun": 4, "res_channel": 92, "resampl": [5, 12, 14, 18, 20, 80, 119, 153], "resample_poli": 122, "resampling_freq": 104, "rescal": [29, 30], "research": [5, 9, 10, 11, 30, 35, 97, 148], "reset": 107, "reset_classifi": 107, "residu": [89, 92, 105, 107], "resili": [11, 116, 132], "resolut": 112, "resolv": [72, 131], "resourc": [5, 7, 9, 10, 11, 13, 16, 24, 75, 81, 121, 124, 130, 152, 153], "resp": 56, "respect": [4, 5, 30, 122], "respir": 80, "respons": [8, 9, 10, 11, 28, 30], "rest": [77, 123], "restor": [32, 72], "result": [3, 12, 14, 16, 29, 32, 72, 86, 122, 125, 131, 139, 144, 147], "results_column": [2, 8, 27, 28], "results_df": 14, "retain": 119, "return": [2, 5, 8, 9, 10, 11, 12, 14, 17, 19, 21, 29, 30, 31, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 69, 70, 71, 72, 75, 76, 79, 81, 82, 83, 84, 85, 86, 87, 91, 92, 94, 95, 99, 100, 104, 105, 107, 108, 110, 111, 112, 113, 116, 117, 118, 119, 120, 122, 123, 124, 125, 127, 128, 129, 130, 131, 132, 133, 139, 141, 142, 143, 146, 153], "return_all_token": 107, "return_feat": [9, 10, 94, 110, 111, 112], "return_featur": [91, 95, 104], "return_pair": 5, "return_patch_token": 107, "return_target": [2, 72, 131, 142], "return_train_scor": [4, 29, 30], "reus": [5, 9, 11], "review": [27, 28, 29, 30], "rg": [9, 10, 11], "rhythmic": 108, "right": [2, 4, 8, 12, 27, 28, 29, 32, 40, 74, 77, 151], "right_hand": [18, 21, 27, 28, 29, 30, 32], "rightward": 77, "rippl": 16, "risk": [29, 47, 66, 141], "rivero": 110, "rmse": 31, "robin": [35, 153], "robust": 98, "robust_scal": 11, "rodrigu": 153, "roman": 35, "rommel": [3, 4, 153], "room": [27, 28], "root": [31, 48, 151], "rot": 4, "rotat": [29, 49, 50, 51, 52, 68, 146], "rotate_col_label": 146, "rotate_precis": 146, "rotate_row_label": 146, "rouann": 97, "rough": 29, "roughli": [2, 3, 4, 5, 8, 9, 11, 27, 28, 77], "round": [2, 8], "row": [14, 22, 40, 75, 99, 146], "row_set": 99, "rp": 5, "rudzicz": 115, "rule": [27, 72, 131], "run": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 72, 74, 77, 86, 89, 90, 95, 98, 110, 119, 121, 122, 125, 131, 133, 144, 147, 151, 153], "run_0": 133, "run_train": 14, "runner": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 27, 28, 29, 30, 31, 32], "runtim": 27, "runtimewarn": 27, "s0": 22, "s001": 22, "s004": 22, "s00500": 110, "s022": [17, 19], "s022r05": [17, 19], "s022r06": [17, 19], "s022r09": [17, 19], "s022r10": [17, 19], "s022r13": [17, 19], "s022r14": [17, 19], "s41562": [2, 8, 73], "s_growth": 115, "saeed": [38, 39, 58, 60], "safelog": [3, 4, 26, 27, 28, 29, 32, 109], "sake": 14, "salami": 96, "salami2022": 96, "salvocalcagno": 113, "same": [2, 3, 4, 5, 8, 9, 10, 11, 14, 18, 21, 27, 28, 29, 30, 32, 43, 54, 61, 70, 72, 77, 80, 100, 112, 119, 122, 131, 134], "same_rec_neg": [5, 134], "sampl": [2, 3, 4, 5, 8, 9, 10, 14, 16, 17, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 42, 43, 47, 48, 49, 50, 51, 52, 54, 57, 60, 61, 62, 70, 72, 74, 76, 84, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 124, 125, 132, 133, 134, 135, 141, 147, 153], "sample_class": 132, "sample_record": 133, "sample_window": 133, "sampler": 153, "sanjiv": 31, "santamaria": 97, "santamaria2020": 97, "sara": [31, 153], "sashank": 31, "satyen": 31, "save": [2, 3, 4, 5, 8, 9, 10, 12, 14, 15, 16, 23, 24, 27, 28, 29, 30, 32, 72, 75, 78, 87, 121, 125, 130, 131, 152, 153], "save_dir": [12, 16, 130], "savgol_filt": 119, "sc4001e0": 16, "sc4011e0": 16, "scalar": 139, "scale": [5, 9, 10, 11, 12, 16, 95, 97, 98, 107, 153], "scales_samples_": 97, "scalp": 79, "scanno": 26, "scatter": [5, 16, 31], "scenario": [16, 125], "schalk": 77, "schedul": [31, 32], "scheme": [29, 32, 123, 153], "schirrmeist": [26, 27, 28, 29, 30, 31, 35, 77, 93, 103, 106, 109, 146, 153], "schirrmeister2017": [26, 77, 93, 103, 106, 109], "schwabed": [42, 62], "scientif": 35, "scikit": [5, 24, 25, 33, 72, 75, 78, 99, 109, 121, 125, 128, 130, 131, 144, 146, 152, 153], "scipi": [49, 50, 51, 52, 68, 72, 119, 122, 131], "score": [2, 4, 5, 9, 10, 11, 29, 30, 72, 94, 110, 131, 137, 138, 139, 153], "scorer": 139, "screen": 74, "script": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 144], "se": [10, 90], "seaborn": [14, 29, 30], "seamlessli": 32, "search": [1, 6, 24, 29, 30, 36, 38, 42, 54, 56, 72, 75, 78, 99, 109, 121, 125, 128, 130, 131, 144, 147, 152, 153], "search_result": [4, 29, 30], "searchwork": [2, 8, 73], "sec": [16, 17, 18, 19, 31], "second": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 30, 31, 32, 40, 74, 77, 79, 81, 82, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117], "second_kernel_s": 101, "section": [12, 22, 77, 150], "secur": 5, "sedlar": [31, 153], "see": [2, 3, 4, 5, 8, 9, 10, 11, 16, 18, 20, 21, 24, 26, 27, 28, 29, 30, 32, 47, 48, 66, 67, 72, 73, 74, 77, 80, 82, 83, 96, 99, 101, 102, 106, 114, 115, 117, 118, 119, 120, 122, 123, 124, 125, 130, 131, 132, 134, 135, 141, 144, 147, 150, 151], "seed": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 63, 144], "seeg": 123, "segment": [12, 16, 29, 32, 46, 48, 65, 67, 95, 107, 119], "segment_length": [46, 65], "segmentationreconstruct": 153, "segmentpatch": 107, "seizur": 108, "select": [2, 4, 8, 9, 16, 20, 27, 28, 29, 30, 32, 37, 77, 107, 123, 132], "select_by_channel": 12, "select_by_dur": 12, "self": [1, 4, 6, 11, 24, 32, 72, 75, 80, 89, 92, 95, 99, 111, 121, 125, 130, 131, 133, 134, 135, 144, 147, 152, 153], "self_attn": 10, "send": [2, 3, 4, 8, 9, 10, 11, 16, 27, 28, 29, 30, 32], "sensit": [30, 74, 146], "sensor": [3, 4, 27, 28, 29, 30, 32, 40, 49, 50, 51, 52, 68, 77], "sensors_positions_matrix": [49, 68], "sent": [72, 131], "separ": [5, 29, 32, 74, 104, 119, 125, 134], "seq2seq": 11, "sequenc": [36, 41, 72, 107, 114, 131, 132, 135, 142, 150, 153], "sequencesampl": [9, 10, 11, 153], "sequenti": [3, 4, 5, 9, 10, 11, 16, 26, 27, 28, 29, 30, 32, 77, 99], "seri": [2, 4, 5, 8, 9, 10, 29, 30, 31, 72, 76, 83, 86, 92, 104, 110, 111, 131, 133, 137, 153], "serial": [5, 12, 15, 18, 23, 24, 75, 80, 121, 124, 130, 152, 153], "serv": [14, 74, 76, 83], "session": [2, 4, 8, 12, 18, 20, 21, 27, 28, 29, 30, 31, 32, 74, 77, 133], "session_t": 133, "set": [2, 4, 8, 9, 10, 11, 12, 14, 16, 17, 19, 22, 26, 27, 29, 30, 31, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 62, 66, 72, 74, 75, 77, 81, 82, 93, 97, 98, 109, 110, 111, 115, 116, 117, 120, 123, 124, 125, 130, 131, 144, 150, 153], "set_bipolar_refer": 123, "set_config": 27, "set_descript": [22, 32, 75, 76, 83], "set_eeg_refer": [12, 123], "set_log_level": [2, 8, 12, 14, 22], "set_montag": [12, 81, 82], "set_num_thread": 14, "set_param": [11, 72, 131], "set_random_se": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 153], "set_titl": [2, 8, 16, 31], "set_xlabel": [2, 4, 5, 8, 9, 10, 11, 16, 27, 28, 31], "set_xlim": 29, "set_ylabel": [2, 5, 8, 9, 10, 11, 16, 27, 28, 31], "set_ylim": [4, 27, 28], "seta": 12, "setb": 12, "seteegrefer": 153, "setter": 5, "setup": [2, 4, 8, 27, 149], "seven": 110, "seventh": 91, "sever": [4, 12, 18, 24, 90, 124, 125, 148], "sex": 5, "sfreq": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 26, 27, 28, 29, 30, 31, 32, 37, 43, 57, 61, 84, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 131, 153], "sgd": [72, 131], "shafait": 79, "shallow": [2, 8, 14, 26, 27, 28, 31, 109], "shallowconvnet": [26, 31], "shallowfbcsp": 153, "shallowfbcspnet": [2, 3, 4, 8, 14, 26, 27, 28, 29, 30, 31, 32], "shallu": 30, "shape": [2, 3, 4, 5, 8, 9, 10, 11, 17, 20, 22, 26, 27, 28, 29, 30, 32, 49, 68, 72, 92, 94, 95, 99, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 135, 136, 140], "share": [2, 8, 14, 27, 28, 113], "sharex": [9, 10, 11], "shell": 147, "shh": 112, "shift": [3, 29, 43, 61, 113], "short": [11, 29, 32, 74, 92, 94], "short_ch_nam": 12, "shorter": [11, 153], "shortest": 119, "should": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 20, 26, 27, 28, 30, 37, 40, 46, 49, 54, 57, 65, 68, 70, 72, 73, 75, 76, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 120, 122, 123, 131, 139, 147, 151], "show": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 17, 18, 19, 20, 21, 26, 28, 29, 30, 31, 32, 77, 99, 153], "show_titl": 12, "showcas": [12, 29, 32], "shown": [4, 5, 9, 11, 16, 29, 32, 74, 77], "shrink": 116, "shtml": [12, 81, 82], "shuffl": [4, 8, 14, 29, 30, 32, 39, 47, 48, 60, 67, 72, 131, 153], "siames": 5, "side": [40, 119], "sigmoid": [10, 72, 131], "sign": [53, 69], "sign_flip": 3, "signal": [2, 3, 4, 5, 8, 9, 10, 11, 12, 18, 20, 26, 28, 29, 30, 31, 36, 37, 38, 39, 42, 43, 46, 48, 49, 50, 51, 52, 54, 57, 58, 60, 61, 62, 65, 67, 68, 70, 74, 76, 80, 84, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 122, 123, 124, 125, 129, 131, 134, 153], "signatur": 139, "signflip": 3, "signific": 30, "significantli": 16, "silenc": 32, "silent": [89, 90, 95, 98], "similar": [5, 27, 117], "similarli": [21, 32], "simon": [3, 20, 153], "simonbrandt": [3, 20], "simpl": [5, 12, 16, 24, 25, 32, 33, 91, 99, 104, 109, 152], "simpleconv": 104, "simpler": 11, "simplest": 16, "simpli": [22, 26], "simplifi": [9, 10, 133, 153], "simul": 26, "simultan": [27, 97], "sin": 31, "sinc": [5, 9, 10, 11, 12, 22, 26, 30, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 147], "singl": [5, 9, 10, 27, 30, 41, 42, 43, 61, 62, 72, 91, 94, 104, 112, 123, 131, 142, 153], "sinusoid": 31, "sit": 74, "site": [2, 5, 10, 11, 27, 31, 32], "situat": [72, 131], "size": [2, 3, 4, 5, 11, 14, 16, 26, 27, 28, 29, 30, 31, 32, 37, 46, 54, 57, 65, 70, 72, 84, 85, 86, 89, 90, 91, 92, 95, 97, 98, 99, 100, 104, 105, 107, 110, 111, 113, 114, 115, 116, 119, 122, 124, 125, 131, 134, 136, 140, 142, 146], "skip": [18, 22, 29, 32, 98, 116], "skip_by_annot": 119, "sklearn": [2, 4, 5, 8, 9, 10, 11, 16, 27, 28, 29, 30, 31, 72, 131, 139, 146, 153], "skorch": [2, 3, 4, 5, 8, 9, 10, 11, 17, 26, 27, 28, 29, 30, 31, 72, 84, 85, 86, 131, 153], "sleep": [7, 13, 16, 24, 30, 42, 62, 75, 80, 91, 92, 94, 99, 110, 111, 112, 116, 121, 125, 130, 132, 133, 135, 144, 146, 152, 153], "sleep_physionet": [5, 9, 10, 11], "sleepdata": 112, "sleepphysionet": [5, 9, 10, 11, 16, 153], "sleepstagerblanco2020": [26, 153], "sleepstagerchambon2018": [5, 9, 26], "sleepstagereldele2021": [10, 26, 153], "slice": [30, 119, 120, 124, 125], "slicedata": 4, "slicedataset": [4, 29, 30], "slid": 89, "slide": [14, 31, 89, 124], "slightli": 139, "sliwowski": [2, 8], "slow": [5, 9, 10, 11, 16, 144, 153], "slower": [10, 14, 19, 125], "small": [11, 12, 27, 29, 147], "smaller": [5, 27, 32, 86, 97, 125], "smallest": 147, "smoothli": [54, 70], "smoothtimemask": 4, "sn": [14, 29, 30], "snippet": 147, "snyder": [42, 62], "so": [2, 5, 8, 9, 10, 11, 14, 16, 18, 26, 27, 28, 29, 30, 32, 37, 40, 72, 116, 124, 129, 131], "societi": [49, 50, 51, 52, 68], "soft": 110, "softmax": [26, 27, 31, 72, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 131], "softwar": [35, 147], "solon": [101, 102], "solut": [16, 123], "solv": [144, 153], "solver": 5, "some": [2, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 22, 26, 27, 28, 30, 35, 72, 75, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 123, 131, 144], "song": [95, 153], "song2022": 95, "sort": [12, 27, 28, 153], "sound": [29, 32], "sourc": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 148, 149], "sourceestim": 119, "space": [5, 16, 91], "span": 79, "sparcnet": [26, 153], "spars": [72, 131], "spat_lay": 115, "spatial": [4, 26, 42, 62, 90, 93, 109, 116, 153], "spatial_conv": 9, "spatial_expans": 90, "speak": [9, 11, 14], "special": [72, 131], "specif": [5, 9, 10, 11, 16, 18, 30, 72, 87, 110, 113, 117, 131, 133, 149], "specifi": [2, 3, 5, 8, 9, 10, 11, 12, 18, 21, 22, 26, 27, 28, 29, 72, 73, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 123, 130, 131], "spectral": [3, 92], "speed": [10, 11, 16, 153], "speedup": 14, "spent": [9, 10, 11], "spheric": [49, 50, 51, 52, 68], "spherical_splin": [49, 50, 51, 52, 68], "sphinx": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "spline": [49, 50, 51, 52, 68], "split": [12, 15, 20, 23, 24, 26, 31, 48, 72, 75, 78, 93, 109, 125, 131, 152, 153], "split_first_lay": [14, 26, 93, 103, 109], "split_id": [5, 9, 10, 11, 12, 75, 153], "splitter": 29, "spoclab": 115, "springenberg": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 146], "sqrt": 128, "squar": [31, 48, 109, 131], "squeez": [2, 3, 4, 26, 27, 28, 29, 30, 32, 90], "src": 11, "srm": 90, "ss3": 9, "ssl": [5, 27], "ssvep": [46, 65], "stabil": 128, "stabl": [2, 4, 5, 8, 16, 26, 72, 80, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 131, 144, 146], "stack": [3, 8], "stage": [7, 13, 24, 29, 30, 32, 75, 80, 92, 94, 99, 110, 111, 112, 116, 121, 125, 130, 132, 133, 135, 144, 146, 152, 153], "stai": [16, 27, 74], "standard": [2, 3, 4, 5, 8, 9, 10, 11, 27, 28, 29, 30, 32, 36, 44, 49, 50, 51, 52, 63, 68, 81, 82, 123, 128, 153], "standard_1020": [49, 68], "standard_scal": [5, 9, 10], "standardscal": 5, "stanford": [2, 8, 73], "stanlei": [5, 9, 10, 11], "start": [3, 4, 5, 12, 14, 16, 22, 27, 28, 29, 30, 32, 46, 54, 65, 70, 72, 86, 104, 117, 122, 124, 125, 131, 149], "start_dim": [9, 10], "start_ind": 17, "start_offset_sampl": [2, 14, 22, 31, 124], "state": [32, 132, 133, 134, 135], "state_dict": 99, "static": [37, 38, 39, 40, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 73, 100, 107], "statist": 12, "statu": 5, "std": [12, 29, 44, 63, 77], "std_train_scor": 4, "step": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 18, 22, 28, 29, 30, 32, 86, 92, 107, 125, 147, 153], "stft": [91, 92], "still": [2, 3, 4, 5, 8, 9, 11, 27, 28, 29, 77, 104], "stim": [3, 4, 18, 20, 21, 27, 28, 29, 30, 32], "stim_channel": [17, 19], "stimuli": 77, "stimulu": [29, 30], "stochast": 31, "stop": [5, 32, 37, 57, 86, 124, 125, 143, 153], "stop_ind": 17, "stop_offset_sampl": [2, 14, 22, 31, 124, 153], "stopband": 16, "storag": 14, "store": [2, 4, 8, 9, 10, 11, 12, 14, 18, 22, 28, 29, 30, 32, 73, 75, 87, 153], "stori": [29, 32], "str": [14, 22, 26, 27, 28, 29, 36, 72, 73, 75, 76, 78, 79, 81, 82, 83, 84, 86, 87, 90, 93, 95, 99, 109, 117, 118, 119, 120, 121, 122, 123, 124, 125, 130, 131, 139, 146], "straightforward": 104, "strategi": [4, 25, 29, 30, 90], "strength": 4, "stricker": 79, "strictli": 5, "stride": [2, 9, 10, 11, 26, 27, 84, 85, 86, 90, 93, 95, 99, 109, 115, 124, 125], "stride_before_pool": [14, 31, 93], "string": [21, 22, 26, 35, 40, 50, 51, 52, 72, 75, 119, 120, 121, 130, 131, 139], "strip": 14, "strohmeier": 35, "strong": [104, 107], "strongli": [2, 8, 27, 28, 97, 98], "structur": [4, 5, 16, 17, 19, 133, 134, 153], "studi": [4, 5, 7, 24, 91, 92, 100, 104], "stumbl": 26, "style": [2, 5, 8, 27, 28, 50, 51, 52, 90, 115], "st\u00f8rmer": 153, "sub": [27, 153], "sub_df": 16, "subclass": [89, 90, 95, 98], "subdirectori": [16, 18, 75, 130], "subj": [74, 77], "subj_test": 5, "subj_train": 5, "subj_valid": 5, "subject": [4, 5, 9, 10, 11, 12, 14, 18, 19, 20, 21, 22, 29, 37, 44, 54, 57, 63, 70, 73, 74, 76, 77, 78, 80, 97, 104, 133], "subject_id": [2, 3, 4, 5, 8, 9, 10, 11, 16, 17, 18, 19, 20, 21, 27, 28, 29, 30, 32, 73, 74, 77, 78, 80, 153], "sublayer_output": 10, "subplot": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 31], "subplots_adjust": 12, "subsequ": [90, 117], "subset": [5, 8, 20, 29, 31, 75, 119, 120, 153], "subset_nam": 20, "substanti": [2, 3, 4, 5, 8, 9, 10, 11, 14, 19, 27, 28, 125], "suffici": 29, "suffix": [72, 131], "suggest": [37, 40, 44, 49, 50, 51, 52, 54, 57, 59, 63, 68, 86, 125], "sum": [32, 153], "summar": 14, "summari": [72, 99, 115, 131], "sun": [40, 59, 91, 92, 108], "super": [5, 32, 137, 138], "supervis": [1, 4, 6, 24, 29, 32, 75, 80, 92, 99, 111, 121, 125, 130, 133, 134, 144, 152, 153], "suppli": [2, 3, 5, 8, 9, 10, 11, 27, 28, 29], "support": [5, 9, 10, 11, 18, 27, 32, 72, 119, 122, 123, 129, 131, 153], "suppos": 26, "suppress": [48, 67, 74, 119], "supratak": 94, "supratak2017": 94, "suptitl": 12, "sure": 147, "surrog": [42, 62], "switch": [5, 32, 153], "sylvain": 153, "symmetr": 119, "synchron": 113, "synchroni": 113, "syncnet": [26, 153], "synthet": 48, "system": [5, 9, 10, 46, 49, 65, 68, 81, 82, 91, 94, 95, 97, 111, 112, 113, 119, 150], "systemat": 4, "t": [2, 4, 5, 11, 17, 19, 26, 27, 28, 29, 30, 31, 32, 42, 62, 72, 73, 74, 79, 93, 103, 105, 106, 109, 116, 117, 127, 128, 131, 144, 146], "t0": 19, "t1": 19, "t2": 19, "t3": 12, "t4": 12, "t5": 12, "t6": 12, "t_filter": 115, "t_max": [2, 3, 4, 8, 27, 28, 29, 30, 31, 32], "tab": [2, 5, 8, 16, 27, 28], "tabl": [27, 28, 29, 30, 32, 89, 99, 153], "take": [9, 10, 11, 16, 17, 29, 31, 56, 87, 89, 90, 91, 92, 95, 98, 112], "taken": [2, 5, 8, 14], "tangermann": [26, 27, 28, 29, 30, 31, 35, 93, 103, 106, 109, 146], "tanh": 11, "tap": 77, "target": [2, 4, 5, 8, 9, 10, 15, 17, 18, 20, 23, 24, 27, 28, 29, 31, 47, 56, 66, 72, 73, 75, 76, 81, 83, 84, 86, 87, 113, 124, 125, 131, 132, 133, 136, 137, 140, 141, 142, 146, 152, 153], "target_extractor": [137, 138, 139], "target_from": 26, "target_nam": [12, 14, 18, 22, 31, 75, 76, 79, 81, 82, 87, 153], "target_sfreq": [2, 8], "target_subset": 31, "target_transform": [2, 8, 9, 10, 75, 153], "targets_from": [2, 83, 124, 131], "task": [4, 9, 10, 11, 26, 30, 42, 62, 74, 76, 79, 134], "tau": 113, "tau_max": 134, "tau_neg": [5, 134], "tau_po": [5, 134], "tb": 14, "tce": 112, "tcn": [26, 89, 105, 153], "tcn_activ": 89, "tcn_depth": 89, "tcn_dropout": 89, "tcn_kernel_s": 89, "tcn_n_filter": 89, "tcnet": 105, "techniqu": [40, 59, 119, 123], "tell": [3, 4, 147], "temp": [2, 8], "temp_filter_length": 90, "temp_filter_length_inp": 90, "temp_lay": 115, "temp_len": 115, "temp_span": 115, "tempczyk": 97, "temperatur": 80, "tempfil": [12, 16, 18], "templ": [12, 81, 82, 153], "tempor": [5, 9, 10, 14, 26, 89, 90, 93, 95, 96, 97, 105, 107, 108, 109, 110, 111, 112, 114, 115, 116, 153], "temporalconv": 107, "temporari": [18, 153], "temporarydirectori": 16, "ten_twenty_montag": [49, 68], "teng": 100, "tensor": [9, 10, 11, 22, 26, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 91, 92, 94, 95, 98, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 131, 136, 140, 141], "tensorboard": 32, "tensorboardx": 32, "tensorflow": [89, 100], "teon": 35, "term": [2, 4, 8, 94, 99], "terri": 153, "test": [9, 10, 11, 16, 21, 24, 25, 27, 28, 30, 33, 72, 75, 77, 78, 99, 109, 121, 125, 128, 130, 131, 144, 152, 153], "test_acc": [29, 32], "test_accuraci": 32, "test_bal_acc": 5, "test_dataload": 32, "test_load": 32, "test_loss": 32, "test_model": 32, "test_sampl": 5, "test_set": [2, 8, 29, 31, 32], "test_siz": [5, 8, 29], "test_step": 32, "test_y_pr": 5, "text": [9, 10, 11, 29, 146], "textcolor": 146, "tf": [42, 62], "than": [2, 5, 8, 9, 10, 11, 12, 14, 16, 27, 32, 37, 46, 57, 65, 72, 79, 86, 119, 125, 131, 153], "thei": [2, 3, 4, 5, 8, 14, 16, 26, 27, 28, 29, 30, 32, 123, 153], "them": [3, 4, 5, 12, 14, 16, 17, 19, 26, 27, 29, 32, 72, 75, 89, 90, 91, 93, 94, 95, 98, 99, 103, 105, 106, 107, 109, 110, 111, 112, 114, 116, 131, 151], "theo": 11, "therefor": [2, 8, 12, 16, 27, 28, 29, 30, 32, 139], "thi": [0, 2, 8, 9, 10, 11, 14, 16, 17, 18, 19, 20, 22, 31, 50, 51, 52, 72, 73, 74, 75, 77, 79, 80, 81, 82, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 122, 123, 125, 127, 128, 130, 131, 133, 139, 144, 147, 151, 153], "thing": 151, "thinker": [115, 153], "thinkerinvari": 115, "third": 32, "third_kernel_s": [101, 102], "thirti": 91, "thoma": 153, "those": [2, 4, 5, 8, 12, 72, 119, 120, 131], "though": [14, 16, 29, 32], "thread": 14, "three": [4, 16, 29, 32, 72, 73, 79, 95, 97, 104, 131, 147], "through": [3, 4, 11, 12, 14, 16, 20, 22, 27, 49, 68, 76, 83, 91, 94, 107, 110, 111, 112, 153], "throughout": [2, 8, 9, 10, 11, 28, 29, 32], "thu": [2, 4, 8, 117], "thumb": [2, 8, 27], "th\u00e9o": 153, "tibor": [35, 153], "tick_param": [2, 5, 8, 12, 27, 28], "tidnet": [26, 153], "tight": [72, 131], "tight_layout": [2, 4, 5, 8, 9, 10, 11, 27, 28, 30], "tii": 89, "time": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 46, 48, 55, 65, 67, 71, 72, 73, 75, 80, 83, 89, 90, 91, 92, 93, 94, 95, 96, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 119, 122, 127, 128, 130, 131, 132, 136, 137, 140, 143, 153], "time_as_index": 117, "time_conv_size_": [111, 116], "time_frequ": 3, "time_start": [46, 65], "time_taken": 16, "timecrop": 153, "timedistribut": [9, 10, 153], "timeseri": 140, "timeseriesloss": 2, "timestep": 27, "titl": [3, 12, 29, 30, 35], "tmax": [2, 8, 12, 117], "tmin": [2, 8, 12, 16, 19, 117], "tmp": [16, 18], "tmp3mmu2kqx": 16, "tmp8rqaf5x8": 18, "tmp_dir": 16, "tmpdir": 18, "tmphz8hdcoi": 16, "tmpuoeu3_w1": 16, "tmpvjq3k0_t": 16, "tnsre": [10, 97, 112], "to_csv": 14, "to_dense_prediction_model": [2, 27, 31, 99, 153], "to_list": [5, 9, 10, 11], "to_numpi": [31, 137, 138, 139], "tobia": 35, "todo": 2, "toe": 77, "togeth": [16, 27, 153], "token": 107, "tokenizor": 107, "toml": 153, "tone": 74, "tongu": [18, 21, 27, 28, 29, 30, 32, 74], "tonio": 35, "too": [11, 91], "tool": [2, 4, 8, 80, 148, 151], "toolbox": 148, "top": [5, 9, 10, 11, 35], "topic": [1, 24, 35], "torch": [2, 3, 4, 5, 8, 9, 10, 11, 14, 22, 26, 27, 28, 29, 30, 31, 32, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 131, 136, 140, 141, 142, 144, 153], "torch_stft": 92, "torchinfo": [27, 28, 29, 32, 99, 153], "torchmetr": 32, "torchvis": [2, 8, 28, 30], "total": [2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 20, 21, 22, 23, 26, 27, 28, 29, 30, 31, 32, 33, 34, 74, 152], "total_tri": [74, 77], "toward": 100, "tpu": 32, "tqdm": 32, "tr_idx": 29, "track": 97, "track_running_stat": 10, "tracker": 147, "tradeoff": 16, "tradit": 95, "train": [12, 14, 20, 21, 33, 72, 75, 77, 78, 83, 90, 91, 99, 107, 109, 121, 125, 128, 130, 131, 144, 152, 153], "train_acc": 5, "train_accuraci": [3, 27, 28, 29, 30, 32], "train_bal_acc": [5, 9, 10, 11], "train_dataload": 32, "train_i": [4, 30], "train_indic": 29, "train_load": 32, "train_loss": [2, 3, 5, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32, 72, 131], "train_misclass": [27, 28], "train_neg_root_mean_squared_error": 31, "train_one_epoch": 32, "train_pearson_r": 8, "train_r2": 8, "train_sampl": [5, 9, 10, 11], "train_set": [2, 3, 4, 8, 9, 10, 11, 27, 28, 29, 30, 31, 32], "train_split": [2, 3, 4, 5, 8, 9, 10, 11, 26, 27, 28, 29, 30, 31, 72, 131], "train_subset": 29, "train_test_split": [5, 8, 29], "train_val_split": 29, "train_x": [4, 30], "train_y_pr": 5, "trainabl": [3, 4, 11, 26, 27, 28, 29, 32], "trained_model": 14, "trainer": 32, "training_scor": 4, "training_setup": 14, "training_setup_end": 14, "training_setup_start": 14, "training_step": 32, "tran": [5, 9, 10], "transact": [5, 10, 46, 65, 89, 94, 95, 97, 111, 112], "transax": 29, "transfer": 97, "transform": [2, 5, 8, 9, 10, 11, 20, 27, 28, 29, 30, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 57, 58, 59, 60, 61, 62, 63, 64, 65, 67, 69, 70, 71, 72, 76, 83, 84, 85, 86, 90, 91, 92, 95, 99, 107, 108, 131, 153], "transformerencod": 95, "transforms_freq": 4, "transforms_spati": 4, "transforms_tim": 4, "transit": [16, 37, 57, 119], "translat": 3, "transposit": 153, "tremend": 107, "trend": 31, "tri": 139, "trial": [2, 3, 4, 8, 19, 21, 27, 28, 29, 30, 31, 32, 48, 67, 72, 74, 77, 84, 86, 125, 131, 137, 138, 142, 143, 153], "trial_label": [72, 131, 142], "trial_predict": [72, 131, 142], "trial_start_offset_sampl": [3, 4, 5, 9, 10, 11, 18, 19, 21, 27, 28, 29, 30, 32, 86, 125], "trial_start_offset_second": [3, 4, 27, 28, 29, 30, 32], "trial_stop_offset_sampl": [3, 4, 5, 9, 10, 11, 18, 19, 21, 27, 28, 29, 30, 31, 32, 86, 125, 153], "trial_stop_offset_second": [29, 30], "trialwis": [2, 4, 8, 20, 27, 28, 30, 72, 131, 142, 153], "trigger": 11, "troubleshoot": 150, "true": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 26, 27, 28, 29, 30, 31, 32, 47, 49, 50, 51, 52, 72, 75, 76, 79, 80, 81, 82, 83, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 121, 123, 124, 125, 126, 129, 131, 134, 135, 137, 138, 139, 142, 144, 153], "truncat": 107, "trust": 4, "trustworthi": [28, 29, 30], "truth": 31, "try": [3, 4, 12, 18, 22, 24, 30, 147, 151], "tsne": 5, "tugraz": 27, "tuh": [7, 13, 14, 15, 23, 24, 75, 82, 91, 121, 124, 130, 152, 153], "tuh_eeg": [12, 14, 22, 81, 82], "tuh_eeg_abnorm": 14, "tuh_path": [12, 14, 22], "tuh_preproc": 12, "tuh_window": [12, 22], "tuhabnorm": [14, 18, 153], "tuk": [5, 9, 10, 11], "tune": [24, 25, 32, 33, 75, 78, 95, 99, 109, 121, 125, 128, 130, 144, 152, 153], "tuning_playbook": 30, "tupl": [29, 30, 47, 56, 66, 72, 76, 80, 81, 82, 91, 99, 100, 113, 122, 129, 131, 134, 146], "tutori": [2, 3, 4, 5, 8, 9, 10, 11, 22, 24, 26, 27, 28, 29, 30, 32, 151, 153], "tuzel": [37, 44, 54, 57, 63, 70], "tweak": 29, "twelfth": 107, "twenti": 74, "twice": 119, "twinx": [2, 5, 8, 27, 28], "two": [4, 5, 9, 10, 11, 12, 14, 16, 18, 27, 29, 32, 47, 54, 66, 74, 77, 80, 98, 104, 107, 110, 119, 122, 123, 134, 135, 141, 153], "type": [2, 3, 4, 8, 11, 26, 27, 28, 29, 32, 37, 38, 39, 40, 42, 43, 44, 46, 47, 48, 49, 54, 66, 72, 75, 77, 84, 85, 86, 87, 90, 92, 98, 99, 100, 104, 105, 107, 108, 113, 119, 120, 122, 123, 124, 125, 127, 128, 130, 131, 133, 135, 141, 143, 146, 153], "typic": [27, 72, 117, 131], "u": [3, 5, 7, 13, 24, 30, 75, 80, 99, 116, 121, 125, 130, 132, 133, 135, 144, 146, 151, 152, 153], "ufabc": 4, "ul": 79, "ultim": 14, "ultrabold": 146, "ultralight": 146, "umap": 5, "unabl": 4, "unaffect": [72, 131], "uncov": [4, 5, 134], "undefinedmetricwarn": 10, "under": [5, 14, 73, 130, 151, 153], "underli": [2, 5, 8, 28, 30, 121], "underscore_cas": 0, "understand": [5, 24, 29, 104], "unexpect": 147, "unfilt": 129, "unifi": 153, "uniform": [56, 113], "uniformli": [42, 47, 49, 50, 51, 52, 62, 132], "uniniti": [4, 72, 131], "uninstanti": [72, 131], "unintend": 112, "uniqu": [5, 9, 10, 11, 21, 72, 76, 79, 131], "unit": [11, 26, 119, 151], "unit_mul": 26, "univers": [12, 77, 81, 82, 153], "unknown": [31, 139], "unlabel": 5, "unless": [5, 32, 131], "unmodifi": [72, 131], "unoffici": 108, "unpickl": [5, 72, 131], "unreli": 29, "unseen": 29, "until": [29, 74], "untrac": 153, "untrust": 5, "unverifi": 27, "up": [16, 17, 74, 116, 122, 153], "updat": [32, 72, 73, 75, 76, 83, 86, 125, 129, 131, 150, 153], "update_path": [17, 19], "upfirdn": 122, "upon": [18, 26], "upper": [12, 16, 119], "upsampl": [11, 116, 122], "upward": 77, "url": 35, "urllib3": 27, "us": [2, 3, 4, 7, 8, 13, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 35, 37, 39, 40, 44, 46, 47, 48, 49, 50, 51, 52, 55, 58, 60, 62, 63, 65, 67, 68, 72, 74, 77, 79, 83, 89, 90, 92, 95, 96, 97, 98, 100, 101, 103, 104, 105, 106, 107, 108, 110, 113, 114, 115, 117, 119, 120, 122, 123, 131, 139, 142, 147, 150, 151, 152, 153], "usag": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 26, 27, 28, 29, 30, 31, 32, 147, 153], "use_abs_pos_emb": 107, "use_cach": [72, 131, 137, 138], "use_deterministic_algorithm": 144, "use_log_softmax": 153, "use_mean_pool": 107, "use_mlp": 90, "use_mne_epoch": [125, 153], "user": [5, 27, 72, 131, 147, 149, 150, 153], "userwarn": [2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 18, 19, 27, 28, 29, 30, 31, 32], "usleep": [11, 26, 153], "usual": [2, 3, 4, 8, 16, 29, 32, 72, 131], "util": [2, 3, 4, 5, 8, 9, 10, 11, 14, 18, 22, 26, 27, 28, 30, 31, 32, 72, 131, 153], "uv": [2, 3, 4, 5, 8, 9, 10, 12, 27, 28, 29, 30, 32], "v": [2, 3, 4, 5, 8, 9, 10, 12, 16, 27, 28, 29, 30, 32, 97, 101, 102, 104, 114], "v1": [22, 32], "v176": 97, "v2": [14, 107], "v4": 102, "v_": 128, "v_num": 32, "v_t": 128, "val_idx": 29, "val_indic": 29, "val_subset": 29, "valentin": 153, "valid": [2, 21, 26, 27, 31, 32, 72, 112, 123, 124, 125, 131, 139, 140, 153], "valid_acc": [3, 5, 9, 10, 11, 26, 28, 29, 30], "valid_accuraci": [3, 27, 28, 29, 30], "valid_bal_acc": [5, 9, 10, 11], "valid_loss": [2, 3, 5, 8, 9, 10, 11, 26, 27, 28, 29, 30, 31], "valid_misclass": [27, 28], "valid_neg_root_mean_squared_error": 31, "valid_pearson_r": 8, "valid_r2": 8, "valid_sampl": [5, 9, 10, 11], "valid_set": [2, 3, 8, 9, 10, 11, 27, 28, 31], "valid_y_pr": 5, "validation_scor": 4, "validsplit": [26, 30, 72, 131], "valu": [2, 4, 5, 8, 9, 10, 11, 12, 26, 27, 28, 30, 31, 32, 43, 47, 66, 72, 75, 76, 83, 86, 90, 98, 104, 107, 115, 119, 120, 122, 123, 124, 125, 131, 140, 141, 142, 153], "valueerror": [14, 26, 31, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "vaquerizo": 97, "var_nam": [3, 4, 11, 26, 27, 28, 29, 32, 99], "variabl": [2, 4, 8, 29, 30, 73, 144], "varianc": [29, 30, 128], "varun": 30, "vazquez": 97, "ve": 147, "vector": [9, 10, 107, 119, 122], "verbos": [2, 3, 4, 8, 29, 30, 72, 73, 117, 119, 120, 122, 123, 124, 125, 126, 131, 153], "veri": [11, 29, 32, 75, 104, 125, 130], "verif": 27, "verifi": 151, "version": [2, 3, 4, 5, 9, 10, 18, 20, 21, 22, 29, 30, 31, 72, 79, 90, 91, 95, 99, 104, 107, 108, 117, 118, 119, 120, 122, 123, 131, 147, 149, 150, 151], "version_0": 32, "versionad": 92, "versu": 31, "vertic": 119, "verticalalign": 29, "via": [5, 26, 28, 29, 30, 116, 119, 149, 150, 153], "view": [2, 4, 8, 22, 73], "villar": 97, "vinai": [28, 29, 30], "viridi": 5, "virtual": 123, "vision": 98, "visit": [26, 29], "visual": [2, 8, 9, 10, 11, 12, 26, 27, 28, 30, 31, 35, 77, 93, 95, 103, 106, 107, 109, 148, 153], "vmax": 146, "vmin": 146, "vol": [10, 112], "volt": 12, "volta": [72, 131], "volum": 35, "volv": 77, "vqsnp": 107, "vytauta": 153, "w": [5, 9, 10, 11, 12, 27, 28, 29, 30, 79, 90, 97, 108], "w_1": 10, "w_2": 10, "wa": [4, 5, 9, 10, 11, 27, 28, 29, 32, 72, 74, 77, 91, 95, 112, 119, 131, 132, 153], "wai": [2, 5, 8, 16, 21, 24, 26, 29, 112, 149, 151], "wainrib": [5, 9, 10, 111], "wake": [9, 10, 11, 80], "wang": [44, 63, 105], "want": [12, 14, 18, 21, 22, 24, 28, 29, 30, 32, 72, 131, 148, 151], "warm": [72, 131], "warm_start": [72, 131], "warn": [2, 3, 4, 5, 8, 9, 10, 12, 14, 16, 18, 19, 27, 28, 29, 30, 31, 32, 74, 112, 118, 124, 125, 144, 153], "wave": [5, 9, 10, 11], "wavelet": 113, "waytowich": [101, 102], "we": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 20, 21, 22, 24, 26, 27, 28, 29, 30, 32, 35, 77, 91, 95, 131, 144, 147, 150, 151], "websit": 4, "wei": [97, 107], "wei22a": 97, "weight": [5, 9, 10, 11, 29, 30, 32, 89, 91, 105, 107, 146], "weight_decai": [2, 3, 4, 8, 27, 28, 29, 32], "weights_onli": 5, "welcom": 22, "well": [2, 5, 8, 12, 26, 27, 28, 29, 32, 86, 125, 148, 153], "wenlong": [46, 65], "wentrup": 97, "were": [2, 8, 9, 11, 14, 19, 26, 30, 74, 75, 77, 95, 110, 119, 153], "westov": [40, 59, 91, 92, 108], "what": [26, 29, 72, 89, 124, 125, 131], "whatev": [72, 131], "when": [5, 9, 10, 11, 14, 16, 22, 27, 29, 32, 35, 41, 42, 49, 50, 51, 52, 56, 62, 68, 72, 73, 78, 84, 85, 86, 89, 91, 95, 116, 118, 119, 120, 122, 123, 124, 125, 130, 131, 144, 147, 153], "whenev": 16, "where": [2, 4, 5, 8, 9, 10, 22, 27, 28, 29, 37, 46, 47, 49, 54, 57, 65, 66, 68, 70, 72, 73, 75, 84, 104, 107, 113, 130, 131, 142, 144, 153], "whether": [5, 14, 26, 38, 39, 40, 42, 48, 49, 50, 51, 52, 53, 55, 56, 62, 68, 72, 75, 83, 84, 85, 86, 87, 89, 90, 93, 95, 96, 97, 98, 99, 101, 103, 106, 107, 108, 109, 110, 114, 115, 116, 124, 129, 130, 131, 134, 139, 144, 147], "which": [2, 3, 4, 5, 8, 9, 10, 11, 14, 16, 19, 20, 21, 24, 26, 27, 29, 30, 32, 35, 36, 39, 42, 48, 49, 60, 62, 67, 68, 72, 75, 76, 77, 83, 99, 104, 112, 119, 122, 123, 125, 131, 133, 134, 135, 147], "while": [4, 5, 14, 29, 32, 77, 89, 90, 95, 98, 104, 110, 143], "white": [44, 63], "whitespac": 153, "who": 148, "whole": [2, 8, 9, 10], "whose": [72, 86, 125, 131], "wide": 98, "width": [12, 30, 100, 104, 113, 115, 119], "wil": 20, "wild": [91, 92, 108], "wilson": [20, 153], "wimpff": [90, 153], "win_len_": 14, "winddow_size_sampl": 124, "window": [14, 16, 18, 19, 21, 26, 72, 75, 83, 84, 85, 86, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 119, 122, 124, 125, 131, 132, 133, 134, 135, 142, 143, 153], "window_ind": 17, "window_kwarg": [27, 28, 75], "window_len": 140, "window_len_": 14, "window_len_sampl": 14, "window_preproc_kwarg": 75, "window_s": 153, "window_size_": [5, 9, 10, 11], "window_size_sampl": [2, 5, 8, 9, 10, 11, 12, 14, 17, 19, 22, 27, 31, 84, 85, 86, 124, 125, 126], "window_stride_sampl": [2, 5, 9, 10, 11, 12, 14, 17, 19, 22, 27, 31, 84, 85, 86, 124, 125], "windows_d": [14, 16], "windows_dataset": [3, 4, 5, 8, 9, 10, 11, 17, 18, 19, 27, 28, 29, 30, 31, 32, 84, 85, 86, 124, 125], "windows_dataset_load": 18, "windowsattentionblock": 107, "windowsdataset": [3, 18, 26, 75, 84, 85, 86, 87, 124, 125, 130, 131, 153], "winner": 97, "wise": [3, 4, 5, 9, 10, 11], "with_f1_scor": 146, "with_skip_connect": [11, 116], "within": [3, 4, 77, 89, 90, 95, 98, 104, 115, 134, 153], "withinconsist": 86, "without": [16, 26, 27, 29, 30, 32, 72, 131, 141, 153], "wolfram": 35, "work": [2, 3, 4, 5, 8, 9, 10, 12, 16, 18, 19, 20, 22, 24, 27, 28, 29, 30, 31, 32, 72, 92, 99, 116, 117, 131, 139, 148, 150, 153], "worker": [14, 32, 142, 153], "worker_init_fn": 14, "world": [32, 92], "wors": 139, "would": [3, 26, 27, 29, 32, 72, 93, 109, 131], "wrap": [5, 26, 32, 75, 122], "wrapper": [26, 28, 29, 91], "write": [16, 18], "written": [11, 130, 149], "wrong": 153, "wspace": 12, "wu": 94, "www": [12, 14, 35, 73, 81, 82], "x": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 20, 22, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 84, 85, 86, 89, 90, 91, 92, 94, 95, 97, 98, 100, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114, 115, 116, 122, 127, 128, 131, 136, 139, 140, 142], "x1": [5, 134], "x2": [5, 134], "x27": 4, "x_i": 17, "x_t": [127, 128], "x_tr": 3, "x_train": 29, "xiao": 92, "xlabel": [3, 12, 29, 30], "xlim": 12, "xxx": 14, "y": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 20, 22, 26, 27, 28, 29, 30, 31, 32, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 51, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 84, 85, 86, 94, 95, 97, 98, 100, 113, 122, 131, 139], "y1": 5, "y2": 5, "y_estim": 31, "y_gt": 31, "y_hat": 32, "y_i": 17, "y_pred": [5, 9, 10, 11, 27, 28, 72, 116, 138], "y_proba": [72, 131], "y_test": [2, 8, 29], "y_train": [2, 8, 9, 10, 11, 29], "y_true": [5, 9, 10, 11, 27, 28, 72], "y_valid": [2, 8], "yang": [90, 91, 92, 108], "yang2021": 92, "yang2023": 91, "yann": [47, 66, 141], "yao2001": 123, "yassin": [104, 153], "yassine2023": 104, "yassine2023cod": 104, "ycq091044": [91, 92, 108], "ye": [104, 107], "year": [12, 35], "yerr": 4, "yet": [17, 19, 99, 151], "yield": [5, 14, 20, 74, 115, 147], "ylabel": [3, 12, 30], "ylgnbu": 30, "ylim": 12, "yml": 153, "yonghao": 153, "you": [2, 3, 4, 5, 8, 9, 11, 12, 16, 17, 18, 19, 21, 22, 24, 27, 28, 29, 32, 35, 72, 131, 139, 147, 149, 150, 151], "your": [2, 8, 14, 16, 21, 24, 25, 27, 28, 30, 33, 35, 72, 75, 78, 89, 93, 95, 96, 97, 98, 99, 101, 103, 106, 109, 110, 114, 115, 116, 121, 125, 128, 130, 131, 144, 147, 149, 152], "ys1": 5, "ys2": 5, "ytick": 12, "z": [5, 9, 10, 31, 49, 52, 68, 108, 114], "z1": 5, "z2": 5, "zachari": 30, "zafeiri": 97, "zamboni": 153, "zeghidour": [38, 39, 58, 60], "zenodo": 35, "zerfowski": 90, "zero": [11, 16, 46, 54, 65, 70, 90, 119, 122, 125, 128, 153], "zero_divis": 10, "zero_grad": [14, 32], "zhang": [47, 66, 98, 141], "zhao": 107, "zheng": 95, "zhiliang": 107, "zhong": [44, 63], "zip": [2, 3, 4, 5, 8, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32], "zipbal": 151, "zk881ps0522": [2, 8, 73], "zscore": 153, "zwinderman": [5, 9, 10, 11], "\u015bliwowski": [97, 153], "\u03bcv": 74, "\u03c6max": 4}, "titles": ["API Reference", "Advanced neural network training strategies", "Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset", "Data Augmentation on BCIC IV 2a Dataset", "Searching the best data augmentation on BCIC IV 2a Dataset", "Self-supervised learning on EEG with relative positioning", "Computation times", "Applied examples on real-world datasets", "Fingers flexion decoding on BCIC IV 4 ECoG Dataset", "Sleep staging on the Sleep Physionet dataset using Chambon2018 network", "Sleep staging on the Sleep Physionet dataset using Eldele2021", "Sleep staging on the Sleep Physionet dataset using U-Sleep network", "Process a big data EEG resource (TUH EEG Corpus)", "Computation times", "Benchmarking eager and lazy loading", "Loading and organizing data", "Benchmarking preprocessing with parallelization and serialization", "Custom Dataset Example", "Load and save dataset example", "MNE Dataset Example", "MOABB Dataset Example", "Split Dataset Example", "Multiple discrete targets with the TUH EEG Corpus", "Computation times", "Examples", "Basic model building and training", "Simple training on MNE epochs", "Cropped Decoding on BCIC IV 2a Dataset", "Basic Brain Decoding on EEG Data", "How to train, test and tune your model?", "Hyperparameter tuning with scikit-learn", "Convolutional neural network regression model on fake data.", "Training a Braindecode model in PyTorch", "Computation times", "Computation times", "How to cite Braindecode", "braindecode.augmentation.AugmentedDataLoader", "braindecode.augmentation.BandstopFilter", "braindecode.augmentation.ChannelsDropout", "braindecode.augmentation.ChannelsShuffle", "braindecode.augmentation.ChannelsSymmetry", "braindecode.augmentation.Compose", "braindecode.augmentation.FTSurrogate", "braindecode.augmentation.FrequencyShift", "braindecode.augmentation.GaussianNoise", "braindecode.augmentation.IdentityTransform", "braindecode.augmentation.MaskEncoding", "braindecode.augmentation.Mixup", "braindecode.augmentation.SegmentationReconstruction", "braindecode.augmentation.SensorsRotation", "braindecode.augmentation.SensorsXRotation", "braindecode.augmentation.SensorsYRotation", "braindecode.augmentation.SensorsZRotation", "braindecode.augmentation.SignFlip", "braindecode.augmentation.SmoothTimeMask", "braindecode.augmentation.TimeReverse", "braindecode.augmentation.Transform", "braindecode.augmentation.functional.bandstop_filter", "braindecode.augmentation.functional.channels_dropout", "braindecode.augmentation.functional.channels_permute", "braindecode.augmentation.functional.channels_shuffle", "braindecode.augmentation.functional.frequency_shift", "braindecode.augmentation.functional.ft_surrogate", "braindecode.augmentation.functional.gaussian_noise", "braindecode.augmentation.functional.identity", "braindecode.augmentation.functional.mask_encoding", "braindecode.augmentation.functional.mixup", "braindecode.augmentation.functional.segmentation_reconstruction", "braindecode.augmentation.functional.sensors_rotation", "braindecode.augmentation.functional.sign_flip", "braindecode.augmentation.functional.smooth_time_mask", "braindecode.augmentation.functional.time_reverse", "braindecode.classifier.EEGClassifier", "braindecode.datasets.BCICompetitionIVDataset4", "braindecode.datasets.BNCI2014001", "braindecode.datasets.BaseConcatDataset", "braindecode.datasets.BaseDataset", "braindecode.datasets.HGD", "braindecode.datasets.MOABBDataset", "braindecode.datasets.NMT", "braindecode.datasets.SleepPhysionet", "braindecode.datasets.TUH", "braindecode.datasets.TUHAbnormal", "braindecode.datasets.WindowsDataset", "braindecode.datasets.create_from_X_y", "braindecode.datasets.create_from_mne_epochs", "braindecode.datasets.create_from_mne_raw", "braindecode.datautil.load_concat_dataset", "braindecode.datautil.save_concat_dataset", "braindecode.models.ATCNet", "braindecode.models.AttentionBaseNet", "braindecode.models.BIOT", "braindecode.models.ContraWR", "braindecode.models.Deep4Net", "braindecode.models.DeepSleepNet", "braindecode.models.EEGConformer", "braindecode.models.EEGITNet", "braindecode.models.EEGInceptionERP", "braindecode.models.EEGInceptionMI", "braindecode.models.EEGModuleMixin", "braindecode.models.EEGNeX", "braindecode.models.EEGNetv1", "braindecode.models.EEGNetv4", "braindecode.models.EEGResNet", "braindecode.models.EEGSimpleConv", "braindecode.models.EEGTCNet", "braindecode.models.HybridNet", "braindecode.models.Labram", "braindecode.models.SPARCNet", "braindecode.models.ShallowFBCSPNet", "braindecode.models.SleepStagerBlanco2020", "braindecode.models.SleepStagerChambon2018", "braindecode.models.SleepStagerEldele2021", "braindecode.models.SyncNet", "braindecode.models.TCN", "braindecode.models.TIDNet", "braindecode.models.USleep", "braindecode.preprocessing.Crop", "braindecode.preprocessing.DropChannels", "braindecode.preprocessing.Filter", "braindecode.preprocessing.Pick", "braindecode.preprocessing.Preprocessor", "braindecode.preprocessing.Resample", "braindecode.preprocessing.SetEEGReference", "braindecode.preprocessing.create_fixed_length_windows", "braindecode.preprocessing.create_windows_from_events", "braindecode.preprocessing.create_windows_from_target_channels", "braindecode.preprocessing.exponential_moving_demean", "braindecode.preprocessing.exponential_moving_standardize", "braindecode.preprocessing.filterbank", "braindecode.preprocessing.preprocess", "braindecode.regressor.EEGRegressor", "braindecode.samplers.BalancedSequenceSampler", "braindecode.samplers.RecordingSampler", "braindecode.samplers.RelativePositioningSampler", "braindecode.samplers.SequenceSampler", "braindecode.training.CroppedLoss", "braindecode.training.CroppedTimeSeriesEpochScoring", "braindecode.training.CroppedTrialEpochScoring", "braindecode.training.PostEpochTrainScoring", "braindecode.training.TimeSeriesLoss", "braindecode.training.mixup_criterion", "braindecode.training.predict_trials", "braindecode.training.trial_preds_from_window_preds", "braindecode.util.set_random_seeds", "braindecode.visualization.compute_amplitude_gradients", "braindecode.visualization.plot_confusion_matrix", "Frequently Asked Questions (FAQ)", "Braindecode", "Installation", "Installing from PyPI", "Installing from sources", "Computation times", "What\u2019s new"], "titleterms": {"": [29, 153], "0": 153, "06": 153, "07": 153, "1": [29, 32, 153], "10": 153, "11": 153, "12": 153, "14": 153, "2": [29, 32], "2021": 153, "2022": 153, "2a": [3, 4, 27], "3": 29, "4": [2, 8], "5": 153, "6": 153, "7": 153, "8": 153, "9": 153, "By": 21, "about": [29, 32], "advanc": [1, 24], "algorithm": 35, "an": [3, 4], "analys": 4, "api": [0, 153], "appli": [7, 24], "ask": 147, "atcnet": 89, "attentionbasenet": 90, "augment": [0, 3, 4, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71], "augmenteddataload": 36, "author": 153, "balancedsequencesampl": 132, "bandstop_filt": 57, "bandstopfilt": 37, "baseconcatdataset": 75, "basedataset": 76, "basic": [24, 25, 28], "bcic": [2, 3, 4, 8, 27], "bcicompetitionivdataset4": 73, "benchmark": [14, 16], "best": [4, 30], "between": 31, "big": 12, "biot": 91, "bnci2014001": 74, "brain": 28, "braindecod": [26, 32, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 151], "bug": [147, 153], "build": [24, 25], "can": 147, "care": [29, 32], "chambon2018": 9, "chang": 153, "channels_dropout": 58, "channels_permut": 59, "channels_shuffl": 60, "channelsdropout": 38, "channelsshuffl": 39, "channelssymmetri": 40, "choos": 31, "cite": [35, 147], "classifi": [0, 72], "clone": 151, "cnn": 31, "combin": 12, "compat": 26, "compos": [3, 41], "comput": [2, 6, 8, 12, 13, 23, 27, 28, 30, 32, 33, 34, 152], "compute_amplitude_gradi": 145, "conclus": 5, "confus": [27, 28], "contrawr": 92, "convolut": 31, "corpu": [12, 22], "cover": [3, 4, 5, 12, 21, 26, 27, 28, 29, 30, 32], "cpu": 31, "creat": [2, 3, 4, 5, 8, 9, 10, 11, 12, 22, 27, 28, 29, 30, 32], "create_fixed_length_window": 124, "create_from_mne_epoch": 85, "create_from_mne_raw": 86, "create_from_x_i": 84, "create_windows_from_ev": 125, "create_windows_from_target_channel": 126, "crop": [2, 27, 117], "croppedloss": 136, "croppedtimeseriesepochscor": 137, "croppedtrialepochscor": 138, "cross": 29, "current": 153, "custom": 17, "cut": [2, 8, 12, 27, 32], "data": [0, 3, 4, 12, 15, 22, 24, 26, 27, 28, 29, 31], "dataload": 22, "dataset": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 17, 18, 19, 20, 21, 22, 24, 27, 28, 29, 30, 31, 32, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86], "datautil": [87, 88], "decod": [2, 8, 27, 28], "deep4net": 93, "deepsleepnet": 94, "defin": [3, 4, 29, 31, 32], "descript": 21, "desir": [3, 4], "dev0": 153, "discret": 22, "do": [30, 147], "document": 26, "dropchannel": 118, "eager": 14, "ecog": [2, 8], "eeg": [5, 12, 22, 28], "eegclassifi": [3, 4, 72], "eegconform": 95, "eeginceptionerp": 97, "eeginceptionmi": 98, "eegitnet": 96, "eegmodulemixin": 99, "eegnetv1": 101, "eegnetv4": 102, "eegnex": 100, "eegregressor": 131, "eegresnet": 103, "eegsimpleconv": 104, "eegtcnet": 105, "eldele2021": 10, "enhanc": 153, "epoch": 26, "etc": [29, 32], "evalu": [29, 31, 32], "examin": 26, "exampl": [3, 4, 5, 7, 12, 17, 18, 19, 20, 21, 24, 26, 27, 28, 29, 30, 32, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 76, 78, 80, 81, 82, 84, 85, 86, 87, 93, 99, 109, 111, 112, 116, 121, 124, 125, 126, 128, 130, 133, 134, 135, 136, 137, 138, 140, 144, 146], "explor": [22, 26], "exponential_moving_demean": 127, "exponential_moving_standard": 128, "extract": [3, 4, 5, 9, 10, 11, 28, 29, 30], "fake": 31, "faq": 147, "filter": 119, "filterbank": 129, "find": 26, "finger": [2, 8], "first": 29, "fit": 4, "flexion": [2, 8], "fold": 29, "found": 147, "frequency_shift": 61, "frequencyshift": 43, "frequent": 147, "from": [150, 151], "ft_surrog": 62, "ftsurrog": 42, "function": [29, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71], "gaussian_nois": 63, "gaussiannois": 44, "gener": 31, "get": [30, 147], "github": 151, "gpu": 31, "help": 147, "hgd": 77, "homepag": 148, "hospit": 22, "how": [29, 32, 35, 147], "hybridnet": 106, "hyperparamet": [29, 30], "i": [29, 32, 147, 151], "ident": 64, "identitytransform": 45, "index": 21, "inform": 21, "inspect": 5, "instal": [149, 150, 151], "iv": [2, 3, 4, 8, 27], "k": 29, "labram": 107, "lazi": 14, "learn": [5, 26, 30], "let": 29, "level": 3, "lightn": 32, "list": 4, "load": [2, 3, 4, 5, 8, 9, 10, 11, 14, 15, 18, 21, 24, 26, 27, 28, 29, 30, 32], "load_concat_dataset": 87, "loop": 32, "manipul": 3, "manual": 3, "mask_encod": 65, "maskencod": 46, "matrix": [27, 28], "mixup": [47, 66], "mixup_criterion": 141, "mne": [19, 26, 35], "moabb": 20, "moabbdataset": 78, "model": [0, 2, 3, 4, 5, 8, 9, 10, 11, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116], "multipl": 22, "need": 30, "network": [1, 9, 11, 24, 30, 31], "neural": [1, 24, 30, 31], "new": 153, "nmt": 79, "observ": 21, "offlin": 32, "one": 3, "onlin": 26, "option": [29, 32], "organ": [15, 24], "other": 35, "own": 26, "parallel": 16, "paramet": 27, "perform": 5, "physionet": [9, 10, 11], "pick": 120, "plot": [2, 4, 8, 9, 10, 11, 27, 28, 30], "plot_confusion_matrix": 146, "posit": 5, "postepochtrainscor": 139, "predict_tri": 142, "prepar": [2, 8, 28], "preprocess": [0, 2, 3, 4, 5, 8, 9, 10, 11, 12, 16, 27, 28, 29, 30, 32, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130], "preprocessor": 121, "pretext": 5, "process": 12, "processor": 31, "pure": 32, "pypi": 150, "python": 147, "pytorch": 32, "question": 147, "raw": [5, 32], "real": [7, 24], "record": [5, 12], "recordingsampl": 133, "refer": [0, 4, 5, 9, 10, 11, 26, 27, 28, 29, 30, 31, 147], "regress": 31, "regressor": [0, 131], "rel": 5, "relativepositioningsampl": 134, "repositori": 151, "represent": 5, "resampl": 122, "resourc": 12, "result": [2, 4, 5, 8, 9, 10, 11, 27, 28, 30], "row": 21, "sampler": [0, 5, 9, 10, 11, 132, 133, 134, 135], "save": 18, "save_concat_dataset": 88, "scikit": [26, 30], "search": 4, "second": 29, "segmentation_reconstruct": 67, "segmentationreconstruct": 48, "select": 12, "self": 5, "sensors_rot": 68, "sensorsrot": 49, "sensorsxrot": 50, "sensorsyrot": 51, "sensorszrot": 52, "sequenc": [9, 10, 11], "sequencesampl": 135, "serial": 16, "session": 3, "set": [3, 5, 28], "set_random_se": 144, "seteegrefer": 123, "shallowfbcspnet": 109, "should": [29, 32], "sign_flip": 69, "signflip": 53, "simpl": [26, 29], "sleep": [5, 9, 10, 11], "sleepphysionet": 80, "sleepstagerblanco2020": 110, "sleepstagerchambon2018": 111, "sleepstagereldele2021": 112, "smooth_time_mask": 70, "smoothtimemask": 54, "sourc": 151, "sparcnet": 108, "split": [2, 3, 4, 5, 8, 9, 10, 11, 21, 27, 28, 29, 30, 32], "stage": [5, 9, 10, 11], "step": 12, "still": 147, "strategi": [1, 24], "structur": 32, "summari": [74, 77], "supervis": 5, "syncnet": 113, "t": 147, "target": 22, "task": 5, "tcn": 114, "templ": 22, "test": [2, 5, 8, 29, 31, 32, 151], "thi": [3, 4, 5, 12, 21, 26, 27, 28, 29, 30, 32], "think": 147, "third": 29, "tidnet": 115, "time": [6, 13, 23, 33, 34, 152], "time_revers": 71, "timerevers": 55, "timeseriesloss": 140, "train": [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 22, 24, 25, 26, 27, 28, 29, 30, 31, 32, 136, 137, 138, 139, 140, 141, 142, 143], "transform": [3, 4, 32, 56], "trial_preds_from_window_pr": 143, "tuh": [12, 22, 81], "tuhabnorm": 82, "tuhmock": 12, "tune": [29, 30], "u": 11, "univers": 22, "us": [5, 9, 10, 11, 12, 36, 38, 41, 42, 43, 53, 54, 56, 73, 75, 76, 78, 80, 81, 82, 84, 85, 86, 87, 93, 99, 109, 111, 112, 116, 121, 124, 125, 126, 128, 130, 133, 134, 135, 136, 137, 138, 140, 144, 146], "usleep": 116, "util": [0, 29, 144], "val": 29, "valid": [3, 4, 5, 8, 9, 10, 11, 28, 29, 30], "version": 153, "visual": [0, 3, 5, 29, 145, 146], "want": 26, "what": [147, 153], "why": [29, 30, 32], "window": [2, 3, 4, 5, 8, 9, 10, 11, 12, 22, 27, 28, 29, 30, 31, 32], "windowsdataset": 83, "work": [147, 151], "world": [7, 24], "you": [26, 30], "your": [26, 29, 32, 151]}})
\ No newline at end of file
diff --git a/dev/sg_execution_times.html b/dev/sg_execution_times.html
index 3a9a8a78..42a94832 100644
--- a/dev/sg_execution_times.html
+++ b/dev/sg_execution_times.html
@@ -449,7 +449,7 @@
   
   <section id="computation-times">
 <span id="sphx-glr-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Link to this heading">#</a></h1>
-<p><strong>13:49.768</strong> total execution time for 24 files <strong>from all galleries</strong>:</p>
+<p><strong>12:49.182</strong> total execution time for 24 files <strong>from all galleries</strong>:</p>
 <div class="docutils container">
 <style scoped>
 <link href="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/5.3.0/css/bootstrap.min.css" rel="stylesheet" />
@@ -471,96 +471,96 @@
 </thead>
 <tbody>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/applied_examples/plot_sleep_staging_chambon2018.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-chambon2018-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Chambon2018 network</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/applied_examples/plot_sleep_staging_chambon2018.py</span></code>)</p></td>
-<td><p>03:42.544</p></td>
-<td><p>633.0</p></td>
+<td><p>03:06.130</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_benchmark_preprocessing.html#sphx-glr-auto-examples-datasets-io-plot-benchmark-preprocessing-py"><span class="std std-ref">Benchmarking preprocessing with parallelization and serialization</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_benchmark_preprocessing.py</span></code>)</p></td>
-<td><p>02:21.167</p></td>
-<td><p>857.3</p></td>
+<td><p>02:04.980</p></td>
+<td><p>940.2</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/advanced_training/plot_relative_positioning.html#sphx-glr-auto-examples-advanced-training-plot-relative-positioning-py"><span class="std std-ref">Self-supervised learning on EEG with relative positioning</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/advanced_training/plot_relative_positioning.py</span></code>)</p></td>
-<td><p>02:12.090</p></td>
-<td><p>730.1</p></td>
+<td><p>01:55.988</p></td>
+<td><p>707.7</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/advanced_training/plot_bcic_iv_4_ecog_cropped.html#sphx-glr-auto-examples-advanced-training-plot-bcic-iv-4-ecog-cropped-py"><span class="std std-ref">Fingers flexion cropped decoding on BCIC IV 4 ECoG Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/advanced_training/plot_bcic_iv_4_ecog_cropped.py</span></code>)</p></td>
-<td><p>01:02.861</p></td>
-<td><p>1343.8</p></td>
+<td><p>01:05.215</p></td>
+<td><p>1687.3</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/model_building/plot_bcic_iv_2a_moabb_cropped.html#sphx-glr-auto-examples-model-building-plot-bcic-iv-2a-moabb-cropped-py"><span class="std std-ref">Cropped Decoding on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_bcic_iv_2a_moabb_cropped.py</span></code>)</p></td>
-<td><p>00:45.109</p></td>
-<td><p>1477.9</p></td>
+<td><p>00:44.249</p></td>
+<td><p>1466.3</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/model_building/plot_how_train_test_and_tune.html#sphx-glr-auto-examples-model-building-plot-how-train-test-and-tune-py"><span class="std std-ref">How to train, test and tune your model?</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_how_train_test_and_tune.py</span></code>)</p></td>
-<td><p>00:33.996</p></td>
-<td><p>1074.6</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/advanced_training/plot_data_augmentation_search.html#sphx-glr-auto-examples-advanced-training-plot-data-augmentation-search-py"><span class="std std-ref">Searching the best data augmentation on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/advanced_training/plot_data_augmentation_search.py</span></code>)</p></td>
+<td><p>00:34.659</p></td>
+<td><p>829.9</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="auto_examples/advanced_training/plot_data_augmentation_search.html#sphx-glr-auto-examples-advanced-training-plot-data-augmentation-search-py"><span class="std std-ref">Searching the best data augmentation on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/advanced_training/plot_data_augmentation_search.py</span></code>)</p></td>
-<td><p>00:33.063</p></td>
-<td><p>885.9</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="auto_examples/model_building/plot_how_train_test_and_tune.html#sphx-glr-auto-examples-model-building-plot-how-train-test-and-tune-py"><span class="std std-ref">How to train, test and tune your model?</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_how_train_test_and_tune.py</span></code>)</p></td>
+<td><p>00:34.426</p></td>
+<td><p>863.6</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.html#sphx-glr-auto-examples-model-building-plot-hyperparameter-tuning-with-scikit-learn-py"><span class="std std-ref">Hyperparameter tuning with scikit-learn</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_hyperparameter_tuning_with_scikit-learn.py</span></code>)</p></td>
-<td><p>00:30.151</p></td>
-<td><p>673.8</p></td>
+<td><p>00:30.716</p></td>
+<td><p>863.4</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/applied_examples/plot_bcic_iv_4_ecog_trial.html#sphx-glr-auto-examples-applied-examples-plot-bcic-iv-4-ecog-trial-py"><span class="std std-ref">Fingers flexion decoding on BCIC IV 4 ECoG Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/applied_examples/plot_bcic_iv_4_ecog_trial.py</span></code>)</p></td>
-<td><p>00:26.059</p></td>
-<td><p>735.0</p></td>
+<td><p>00:26.037</p></td>
+<td><p>837.3</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/advanced_training/plot_data_augmentation.html#sphx-glr-auto-examples-advanced-training-plot-data-augmentation-py"><span class="std std-ref">Data Augmentation on BCIC IV 2a Dataset</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/advanced_training/plot_data_augmentation.py</span></code>)</p></td>
-<td><p>00:17.639</p></td>
-<td><p>1022.4</p></td>
+<td><p>00:18.447</p></td>
+<td><p>1131.3</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="auto_examples/applied_examples/plot_sleep_staging_eldele2021.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-eldele2021-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Eldele2021</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/applied_examples/plot_sleep_staging_eldele2021.py</span></code>)</p></td>
-<td><p>00:13.159</p></td>
-<td><p>635.1</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.html#sphx-glr-auto-examples-model-building-plot-bcic-iv-2a-moabb-trial-py"><span class="std std-ref">Basic Brain Decoding on EEG Data</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_bcic_iv_2a_moabb_trial.py</span></code>)</p></td>
+<td><p>00:13.339</p></td>
+<td><p>865.2</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/model_building/plot_bcic_iv_2a_moabb_trial.html#sphx-glr-auto-examples-model-building-plot-bcic-iv-2a-moabb-trial-py"><span class="std std-ref">Basic Brain Decoding on EEG Data</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_bcic_iv_2a_moabb_trial.py</span></code>)</p></td>
-<td><p>00:12.885</p></td>
-<td><p>1125.9</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/applied_examples/plot_sleep_staging_eldele2021.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-eldele2021-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using Eldele2021</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/applied_examples/plot_sleep_staging_eldele2021.py</span></code>)</p></td>
+<td><p>00:13.021</p></td>
+<td><p>635.2</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.html#sphx-glr-auto-examples-model-building-plot-train-in-pure-pytorch-and-pytorch-lightning-py"><span class="std std-ref">Training a Braindecode model in PyTorch</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_train_in_pure_pytorch_and_pytorch_lightning.py</span></code>)</p></td>
-<td><p>00:11.548</p></td>
-<td><p>1020.1</p></td>
+<td><p>00:11.972</p></td>
+<td><p>770.4</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/applied_examples/plot_sleep_staging_usleep.html#sphx-glr-auto-examples-applied-examples-plot-sleep-staging-usleep-py"><span class="std std-ref">Sleep staging on the Sleep Physionet dataset using U-Sleep network</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/applied_examples/plot_sleep_staging_usleep.py</span></code>)</p></td>
-<td><p>00:11.337</p></td>
-<td><p>667.0</p></td>
+<td><p>00:11.396</p></td>
+<td><p>638.0</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/applied_examples/plot_tuh_eeg_corpus.html#sphx-glr-auto-examples-applied-examples-plot-tuh-eeg-corpus-py"><span class="std std-ref">Process a big data EEG resource (TUH EEG Corpus)</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/applied_examples/plot_tuh_eeg_corpus.py</span></code>)</p></td>
-<td><p>00:07.651</p></td>
+<td><p>00:07.693</p></td>
 <td><p>633.0</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/model_building/plot_regression.html#sphx-glr-auto-examples-model-building-plot-regression-py"><span class="std std-ref">Convolutional neural network regression model on fake data.</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_regression.py</span></code>)</p></td>
-<td><p>00:07.172</p></td>
-<td><p>634.0</p></td>
+<td><p>00:07.292</p></td>
+<td><p>633.8</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_load_save_datasets.html#sphx-glr-auto-examples-datasets-io-plot-load-save-datasets-py"><span class="std std-ref">Load and save dataset example</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_load_save_datasets.py</span></code>)</p></td>
-<td><p>00:04.661</p></td>
-<td><p>633.0</p></td>
+<td><p>00:05.148</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_moabb_dataset_example.html#sphx-glr-auto-examples-datasets-io-plot-moabb-dataset-example-py"><span class="std std-ref">MOABB Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_moabb_dataset_example.py</span></code>)</p></td>
-<td><p>00:04.582</p></td>
-<td><p>632.9</p></td>
+<td><p>00:04.855</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_split_dataset.html#sphx-glr-auto-examples-datasets-io-plot-split-dataset-py"><span class="std std-ref">Split Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_split_dataset.py</span></code>)</p></td>
-<td><p>00:04.314</p></td>
-<td><p>632.9</p></td>
+<td><p>00:04.811</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_tuh_discrete_multitarget.html#sphx-glr-auto-examples-datasets-io-plot-tuh-discrete-multitarget-py"><span class="std std-ref">Multiple discrete targets with the TUH EEG Corpus</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_tuh_discrete_multitarget.py</span></code>)</p></td>
-<td><p>00:02.794</p></td>
+<td><p>00:03.223</p></td>
 <td><p>633.6</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_custom_dataset_example.html#sphx-glr-auto-examples-datasets-io-plot-custom-dataset-example-py"><span class="std std-ref">Custom Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_custom_dataset_example.py</span></code>)</p></td>
-<td><p>00:01.887</p></td>
-<td><p>632.9</p></td>
+<td><p>00:02.243</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/model_building/plot_basic_training_epochs.html#sphx-glr-auto-examples-model-building-plot-basic-training-epochs-py"><span class="std std-ref">Simple training on MNE epochs</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/model_building/plot_basic_training_epochs.py</span></code>)</p></td>
-<td><p>00:01.788</p></td>
-<td><p>666.5</p></td>
+<td><p>00:01.827</p></td>
+<td><p>668.7</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="auto_examples/datasets_io/plot_mne_dataset_example.html#sphx-glr-auto-examples-datasets-io-plot-mne-dataset-example-py"><span class="std std-ref">MNE Dataset Example</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/plot_mne_dataset_example.py</span></code>)</p></td>
-<td><p>00:01.313</p></td>
-<td><p>632.9</p></td>
+<td><p>00:01.515</p></td>
+<td><p>632.8</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="auto_examples/datasets_io/benchmark_lazy_eager_loading.html#sphx-glr-auto-examples-datasets-io-benchmark-lazy-eager-loading-py"><span class="std std-ref">Benchmarking eager and lazy loading</span></a> (<code class="docutils literal notranslate"><span class="pre">../examples/datasets_io/benchmark_lazy_eager_loading.py</span></code>)</p></td>
 <td><p>00:00.000</p></td>
diff --git a/dev/whats_new.html b/dev/whats_new.html
index cf2835ef..363b9aa6 100644
--- a/dev/whats_new.html
+++ b/dev/whats_new.html
@@ -461,13 +461,6 @@
   
   <section id="what-s-new">
 <span id="whats-new"></span><h1>What’s new<a class="headerlink" href="#what-s-new" title="Link to this heading">#</a></h1>
-<p>Please follow the examples below like <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.EEGClassifier</span></code>, so the
-whats_new page will have a link to the function/class documentation.</p>
-<ul class="simple">
-<li><p>“Enhancements” for new features</p></li>
-<li><p>“Bugs” for bug fixes</p></li>
-<li><p>“API changes” for backward-incompatible changes</p></li>
-</ul>
 <section id="current-0-9-dev0">
 <span id="current"></span><h2>Current 0.9 (dev0)<a class="headerlink" href="#current-0-9-dev0" title="Link to this heading">#</a></h2>
 <section id="enhancements">
@@ -484,7 +477,7 @@ <h3>Enhancements<a class="headerlink" href="#enhancements" title="Link to this h
 <li><p>Adding cache and pre-processing option to <a class="reference internal" href="generated/braindecode.datasets.MOABBDataset.html#braindecode.datasets.MOABBDataset" title="braindecode.datasets.MOABBDataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.MOABBDataset</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/582">#582</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Add type hints to datasets (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/590">#590</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Add channel names and montage to  <a class="reference internal" href="generated/braindecode.datasets.TUH.html#braindecode.datasets.TUH" title="braindecode.datasets.TUH"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.TUH</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/593">#593</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
-<li><p>Add <code class="docutils literal notranslate"><span class="pre">offset</span></code> arg to <a href="#id1"><span class="problematic" id="id2">:function:`braindecode.preprocessing.preprocess`</span></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/599">#599</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
+<li><p>Add <code class="docutils literal notranslate"><span class="pre">offset</span></code> arg to <a class="reference internal" href="generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.preprocess()</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/599">#599</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Add type hints to preprocessing (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/600">#600</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Add <code class="docutils literal notranslate"><span class="pre">mypy</span></code> type checks to pre-commit and CI (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/606">#606</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Code clarity changes in <cite>windowers.py</cite> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/615">#615</a> by <a class="reference external" href="https://github.com/OverLordGoldDragon/">John Muradeli</a>)</p></li>
@@ -492,7 +485,7 @@ <h3>Enhancements<a class="headerlink" href="#enhancements" title="Link to this h
 <li><p>Add two models <a class="reference internal" href="generated/braindecode.models.ContraWR.html#braindecode.models.ContraWR" title="braindecode.models.ContraWR"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.ContraWR</span></code></a> and <a class="reference internal" href="generated/braindecode.models.SPARCNet.html#braindecode.models.SPARCNet" title="braindecode.models.SPARCNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.SPARCNet</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/611">#611</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Add Sleep Physionet 18 dataset (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/621">#621</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a> and <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Optimize the CI by executing only the last commit (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/612">#612</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
-<li><p>Add experimental <cite>lazy_metadata</cite> parameter to <a href="#id3"><span class="problematic" id="id4">:function:`braindecode.preprocessing.create_fixed_length_windows`</span></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/597">#597</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
+<li><p>Add experimental <cite>lazy_metadata</cite> parameter to <a class="reference internal" href="generated/braindecode.preprocessing.create_fixed_length_windows.html#braindecode.preprocessing.create_fixed_length_windows" title="braindecode.preprocessing.create_fixed_length_windows"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_fixed_length_windows()</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/597">#597</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Increasing moabb version to 1.1.0 (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/632">#632</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Add MaskEncoding augmentation <a class="reference internal" href="generated/braindecode.augmentation.MaskEncoding.html#braindecode.augmentation.MaskEncoding" title="braindecode.augmentation.MaskEncoding"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.augmentation.MaskEncoding</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/631">#631</a> by <a class="reference external" href="https://github.com/gustavohenriquesr">Gustavo Rodrigues</a>)</p></li>
 <li><p>Adding <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGNex</span></code>  (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/635">#635</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a> )</p></li>
@@ -519,20 +512,20 @@ <h3>Bugs<a class="headerlink" href="#bugs" title="Link to this heading">#</a></h
 <section id="api-changes">
 <h3>API changes<a class="headerlink" href="#api-changes" title="Link to this heading">#</a></h3>
 <ul class="simple">
-<li><p>Expose the <code class="docutils literal notranslate"><span class="pre">use_mne_epochs</span> <span class="pre">parameter</span></code> of <a href="#id5"><span class="problematic" id="id6">:function:`braindecode.preprocessing.create_windows_from_events`</span></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/607">#607</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
+<li><p>Expose the <code class="docutils literal notranslate"><span class="pre">use_mne_epochs</span> <span class="pre">parameter</span></code> of <a class="reference internal" href="generated/braindecode.preprocessing.create_windows_from_events.html#braindecode.preprocessing.create_windows_from_events" title="braindecode.preprocessing.create_windows_from_events"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_windows_from_events()</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/607">#607</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Parameter <code class="docutils literal notranslate"><span class="pre">use_log_softmax</span></code> is default as <cite>False</cite> for all the models in (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/624">#624</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 </ul>
 </section>
 </section>
 <section id="current-0-8-11-2022">
 <span id="changes-0-8-0"></span><h2>Current 0.8 (11-2022)<a class="headerlink" href="#current-0-8-11-2022" title="Link to this heading">#</a></h2>
-<section id="id7">
-<h3>Enhancements<a class="headerlink" href="#id7" title="Link to this heading">#</a></h3>
+<section id="id1">
+<h3>Enhancements<a class="headerlink" href="#id1" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Adding <a class="reference internal" href="generated/braindecode.models.EEGInceptionMI.html#braindecode.models.EEGInceptionMI" title="braindecode.models.EEGInceptionMI"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGInceptionMI</span></code></a> network for motor imagery (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/428">#428</a> by <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
 <li><p>Adding <a class="reference internal" href="generated/braindecode.models.ATCNet.html#braindecode.models.ATCNet" title="braindecode.models.ATCNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.ATCNet</span></code></a> network for motor imagery (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/429">#429</a> by <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
 <li><p>Adding to <a class="reference internal" href="generated/braindecode.datasets.TUH.html#braindecode.datasets.TUH" title="braindecode.datasets.tuh.TUH"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.tuh.TUH</span></code></a> compatibility with version 3.0 of TUH dataset (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/431">#431</a> by <a class="reference external" href="https://github.com/MohammadJavadD">Mohammad Javad D</a>, <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>, <a class="reference external" href="https://github.com/robintibor">Robin Tibor Schirrmeister</a>, <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>, <a class="reference external" href="https://github.com/dengemann">Denis A. Engemann</a> and <a class="reference external" href="https://github.com/ostormer">Oskar Størmer</a>)</p></li>
-<li><p>Adding <a class="reference internal" href="generated/braindecode.models.DeepSleepNet.html#braindecode.models.DeepSleepNet" title="braindecode.models.DeepSleepNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.DeepSleepNet</span></code></a> network for sleep staging (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/417">#417</a> by <a class="reference external" href="https://github.com/Tgnassou">Theo Gnassounou</a>)</p></li>
+<li><p>Adding <a class="reference internal" href="generated/braindecode.models.DeepSleepNet.html#braindecode.models.DeepSleepNet" title="braindecode.models.DeepSleepNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.DeepSleepNet</span></code></a> network for sleep staging (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/417">#417</a> by <a class="reference external" href="https://github.com/Tgnassou">Théo Gnassounou</a>)</p></li>
 <li><p>Adding <a class="reference internal" href="generated/braindecode.models.EEGConformer.html#braindecode.models.EEGConformer" title="braindecode.models.EEGConformer"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGConformer</span></code></a> network (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/454">#454</a> by <a class="reference external" href="https://github.com/eeyhsong">Yonghao Song</a> and <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Adding einops in the requirements (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/466">#466</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Have moabb as an extra dependency (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/467">#467</a> by <a class="reference external" href="https://github.com/ZamboniMarco99">Marco Zamboni</a>)</p></li>
@@ -555,9 +548,9 @@ <h3>Enhancements<a class="headerlink" href="#id7" title="Link to this heading">#
 <li><p>Add models user-friendly representation with torchinfo tables to <a class="reference internal" href="generated/braindecode.models.EEGModuleMixin.html#braindecode.models.EEGModuleMixin" title="braindecode.models.base.EEGModuleMixin"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.base.EEGModuleMixin</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/488">#488</a> by <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a>)</p></li>
 <li><p>Merged temporal and spatial convolutions for Deep4 and ShallowFBCSP (by <a class="reference external" href="https://github.com/dcwil">Daniel Wilson</a> and <a class="reference external" href="https://github.com/Sara04">Sara Sedlar</a>)</p></li>
 <li><p>Enabling data augmentation of single inputs (with no batch dimension). (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/503">#503</a> by <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
-<li><p>Adding <cite>randomize</cite> parameter to <a class="reference internal" href="generated/braindecode.samplers.SequenceSampler.html#braindecode.samplers.SequenceSampler" title="braindecode.samplers.SequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.SequenceSampler</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/504">#504</a> by <a href="#id23"><span class="problematic" id="id24">`Théo Gnassounou`_</span></a>.)</p></li>
+<li><p>Adding <cite>randomize</cite> parameter to <a class="reference internal" href="generated/braindecode.samplers.SequenceSampler.html#braindecode.samplers.SequenceSampler" title="braindecode.samplers.SequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.SequenceSampler</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/504">#504</a> by <a class="reference external" href="https://github.com/Tgnassou">Théo Gnassounou</a>.)</p></li>
 <li><p>Creating new preprocessor objects based on mne’s raw/Epochs methods <a class="reference internal" href="generated/braindecode.preprocessing.Resample.html#braindecode.preprocessing.Resample" title="braindecode.preprocessing.Resample"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.preprocessing.Resample</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.DropChannels.html#braindecode.preprocessing.DropChannels" title="braindecode.preprocessing.DropChannels"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.preprocessing.DropChannels</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.SetEEGReference.html#braindecode.preprocessing.SetEEGReference" title="braindecode.preprocessing.SetEEGReference"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.preprocessing.SetEEGReference</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.Filter.html#braindecode.preprocessing.Filter" title="braindecode.preprocessing.Filter"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.preprocessing.Filter</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.Pick.html#braindecode.preprocessing.Pick" title="braindecode.preprocessing.Pick"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.preprocessing.Pick</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.Crop.html#braindecode.preprocessing.Crop" title="braindecode.preprocessing.Crop"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.preprocessing.Crop</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/500">#500</a> by <a class="reference external" href="https://github.com/brunaafl">Bruna Lopes</a> and <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
-<li><p>Moving <a href="#id8"><span class="problematic" id="id9">:function:`braindecode.models.util.get_output_shape`</span></a> and <a href="#id10"><span class="problematic" id="id11">:function:`braindecode.models.util.to_dense_prediction_model`</span></a> to <a class="reference internal" href="generated/braindecode.models.EEGModuleMixin.html#braindecode.models.EEGModuleMixin" title="braindecode.models.base.EEGModuleMixin"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.base.EEGModuleMixin</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/514">#514</a> by <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a>)</p></li>
+<li><p>Moving <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.util.get_output_shape</span></code> and <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.models.util.to_dense_prediction_model()</span></code> to <a class="reference internal" href="generated/braindecode.models.EEGModuleMixin.html#braindecode.models.EEGModuleMixin" title="braindecode.models.base.EEGModuleMixin"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.base.EEGModuleMixin</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/514">#514</a> by <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a>)</p></li>
 <li><p>Automatically populate signal-related parameters in <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.EEGClassifier</span></code> and <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.EEGRegressor</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/517">#517</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
 <li><p>Adding a pure PyTorch tutorial (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/523">#523</a> by <a class="reference external" href="https://github.com/remidbs">Remi Delbouys</a>  and <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Add <code class="docutils literal notranslate"><span class="pre">models_dict</span></code> to <code class="xref py py-mod docutils literal notranslate"><span class="pre">braindecode.models.util</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/524">#524</a> by <a class="reference external" href="https://github.com/PierreGtch">Pierre Guetschel</a>)</p></li>
@@ -573,8 +566,8 @@ <h3>Enhancements<a class="headerlink" href="#id7" title="Link to this heading">#
 <li><p>Adding pre-commit hooks (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/556">#556</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 </ul>
 </section>
-<section id="id12">
-<h3>Bugs<a class="headerlink" href="#id12" title="Link to this heading">#</a></h3>
+<section id="id2">
+<h3>Bugs<a class="headerlink" href="#id2" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Fixing conda env in the CI (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/461">#461</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
 <li><p>Fixing E231 missing whitespace after ‘,’ untraceable error in old flake8 (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/460">#460</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
@@ -585,8 +578,8 @@ <h3>Bugs<a class="headerlink" href="#id12" title="Link to this heading">#</a></h
 <li><p>Fix bug when using GPU and channel shuffle transform (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/546">#546</a> by <a class="reference external" href="https://github.com/robintibor">Robin Tibor Schirrmeister</a>)</p></li>
 </ul>
 </section>
-<section id="id13">
-<h3>API changes<a class="headerlink" href="#id13" title="Link to this heading">#</a></h3>
+<section id="id3">
+<h3>API changes<a class="headerlink" href="#id3" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Renaming the <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGInception</span></code> network as <a class="reference internal" href="generated/braindecode.models.EEGInceptionERP.html#braindecode.models.EEGInceptionERP" title="braindecode.models.EEGInceptionERP"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGInceptionERP</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/428">#428</a> by <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
 <li><p>Removing support for Python 3.7 (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/397">#397</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
@@ -596,8 +589,8 @@ <h3>API changes<a class="headerlink" href="#id13" title="Link to this heading">#
 </section>
 <section id="current-0-7-10-2022">
 <span id="changes-0-7-0"></span><h2>Current 0.7 (10-2022)<a class="headerlink" href="#current-0-7-10-2022" title="Link to this heading">#</a></h2>
-<section id="id14">
-<h3>Enhancements<a class="headerlink" href="#id14" title="Link to this heading">#</a></h3>
+<section id="id4">
+<h3>Enhancements<a class="headerlink" href="#id4" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Adding EEG-Inception Network <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGInception</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/390">#390</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a> and <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
 <li><p>Adding EEG-ITNet Network <a class="reference internal" href="generated/braindecode.models.EEGITNet.html#braindecode.models.EEGITNet" title="braindecode.models.EEGITNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.EEGITNet</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/400">#400</a> by <a class="reference external" href="https://github.com/GhBlg">Ghaith Bouallegue</a>)</p></li>
@@ -607,18 +600,18 @@ <h3>Enhancements<a class="headerlink" href="#id14" title="Link to this heading">
 <li><p>Adding tutorial with a Unified Validation scheme (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/378">#378</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a> and <a class="reference external" href="https://github.com/martinwimpff">Martin Wimpff</a>)</p></li>
 <li><p>Adding <cite>verbose</cite> parameter to <a class="reference internal" href="generated/braindecode.preprocessing.create_windows_from_events.html#braindecode.preprocessing.create_windows_from_events" title="braindecode.preprocessing.create_windows_from_events"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_windows_from_events()</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.create_windows_from_target_channels.html#braindecode.preprocessing.create_windows_from_target_channels" title="braindecode.preprocessing.create_windows_from_target_channels"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_windows_from_target_channels()</span></code></a>, and <a class="reference internal" href="generated/braindecode.preprocessing.create_fixed_length_windows.html#braindecode.preprocessing.create_fixed_length_windows" title="braindecode.preprocessing.create_fixed_length_windows"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_fixed_length_windows()</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/391">#391</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
 <li><p>Enable augmentation on GPU within <code class="xref py py-class docutils literal notranslate"><span class="pre">AugmentedDataloader</span></code> via a new <cite>device</cite> parameter (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/406">#406</a> by <a class="reference external" href="https://github.com/martinwimpff">Martin Wimpff</a>, <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a> and <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
-<li><p>Adding <cite>randomize</cite> parameter to <a class="reference internal" href="generated/braindecode.samplers.SequenceSampler.html#braindecode.samplers.SequenceSampler" title="braindecode.samplers.SequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.SequenceSampler</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/504">#504</a> by <a href="#id25"><span class="problematic" id="id26">`Théo Gnassounou`_</span></a>.)</p></li>
+<li><p>Adding <cite>randomize</cite> parameter to <a class="reference internal" href="generated/braindecode.samplers.SequenceSampler.html#braindecode.samplers.SequenceSampler" title="braindecode.samplers.SequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.SequenceSampler</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/504">#504</a> by <a class="reference external" href="https://github.com/Tgnassou">Théo Gnassounou</a>.)</p></li>
 </ul>
 </section>
-<section id="id15">
-<h3>Bugs<a class="headerlink" href="#id15" title="Link to this heading">#</a></h3>
+<section id="id5">
+<h3>Bugs<a class="headerlink" href="#id5" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Fixing parameter <cite>subject_ids</cite> to <cite>recoding_ids</cite> in TUHAbnormal example (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/402">#402</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a> and <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
 <li><p>Bug fix <a class="reference internal" href="generated/braindecode.augmentation.functional.ft_surrogate.html#braindecode.augmentation.functional.ft_surrogate" title="braindecode.augmentation.functional.ft_surrogate"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.augmentation.functional.ft_surrogate()</span></code></a> and add option to sample independently per-channel (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/409">#409</a> by <a class="reference external" href="https://github.com/martinwimpff">Martin Wimpff</a> and <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
 </ul>
 </section>
-<section id="id16">
-<h3>API changes<a class="headerlink" href="#id16" title="Link to this heading">#</a></h3>
+<section id="id6">
+<h3>API changes<a class="headerlink" href="#id6" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Renaming the method <cite>get_params</cite> to <cite>get_augmentation_params</cite> in augmentation classes. This makes the Transform module compatible with scikit-learn cloning mechanism (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/388">#388</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a> and <a class="reference external" href="http://alexandre.gramfort.net">Alex Gramfort</a>)</p></li>
 <li><p>Delaying the deprecation of the preprocessing scale function <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.scale()</span></code> and updates tutorials where the function were used. (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/413">#413</a> by <a class="reference external" href="https://github.com/bruAristimunha">Bruno Aristimunha</a>)</p></li>
@@ -629,12 +622,12 @@ <h3>API changes<a class="headerlink" href="#id16" title="Link to this heading">#
 </section>
 <section id="version-0-6-2021-12-06">
 <span id="changes-0-6-0"></span><h2>Version 0.6 (2021-12-06)<a class="headerlink" href="#version-0-6-2021-12-06" title="Link to this heading">#</a></h2>
-<section id="id17">
-<h3>Enhancements<a class="headerlink" href="#id17" title="Link to this heading">#</a></h3>
+<section id="id7">
+<h3>Enhancements<a class="headerlink" href="#id7" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Adding <a class="reference internal" href="generated/braindecode.samplers.SequenceSampler.html#braindecode.samplers.SequenceSampler" title="braindecode.samplers.SequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.SequenceSampler</span></code></a> along with support for returning sequences of windows in <a class="reference internal" href="generated/braindecode.datasets.BaseConcatDataset.html#braindecode.datasets.BaseConcatDataset" title="braindecode.datasets.BaseConcatDataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.BaseConcatDataset</span></code></a> and an updated sleep staging example to show how to train on sequences of windows (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/263">#263</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p>Adding Thinker Invariance Network <a class="reference internal" href="generated/braindecode.models.TIDNet.html#braindecode.models.TIDNet" title="braindecode.models.TIDNet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.TIDNet</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/170">#170</a> by <a class="reference external" href="https://github.com/Ann-KathrinKiessner">Ann-Kathrin Kiessner</a>, <a class="reference external" href="https://github.com/dcwil">Daniel Wilson</a>, <a class="reference external" href="https://github.com/HenrikBons">Henrik Bonsmann</a>, <a class="reference external" href="https://github.com/vytjan">Vytautas Jankauskas</a>)</p></li>
-<li><p>Adding a confusion matrix plot generator <a class="reference internal" href="generated/braindecode.visualization.plot_confusion_matrix.html#braindecode.visualization.plot_confusion_matrix" title="braindecode.visualization.plot_confusion_matrix"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.visualization.plot_confusion_matrix()</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/274">#274</a> by <a class="reference external" href="https://github.com/Ann-KathrinKiessner">Ann-Kathrin Kiessner</a>, <a href="#id27"><span class="problematic" id="id28">`Dan Wilson`_</span></a>, <a class="reference external" href="https://github.com/HenrikBons">Henrik Bonsmann</a>, <a class="reference external" href="https://github.com/vytjan">Vytautas Jankauskas</a>)</p></li>
+<li><p>Adding a confusion matrix plot generator <a class="reference internal" href="generated/braindecode.visualization.plot_confusion_matrix.html#braindecode.visualization.plot_confusion_matrix" title="braindecode.visualization.plot_confusion_matrix"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.visualization.plot_confusion_matrix()</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/274">#274</a> by <a class="reference external" href="https://github.com/Ann-KathrinKiessner">Ann-Kathrin Kiessner</a>, <a class="reference external" href="https://github.com/dcwil">Daniel Wilson</a>, <a class="reference external" href="https://github.com/HenrikBons">Henrik Bonsmann</a>, <a class="reference external" href="https://github.com/vytjan">Vytautas Jankauskas</a>)</p></li>
 <li><p>Adding data <a class="reference internal" href="api.html#augmentation-api"><span class="std std-ref">Augmentation</span></a> module (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/254">#254</a> by <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>, <a class="reference external" href="http://alexandre.gramfort.net">Alex Gramfort</a> and <a class="reference external" href="https://tommoral.github.io">Thomas Moreau</a>)</p></li>
 <li><p>Adding Mixup augmentation <a class="reference internal" href="generated/braindecode.augmentation.Mixup.html#braindecode.augmentation.Mixup" title="braindecode.augmentation.Mixup"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.augmentation.Mixup</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/254">#254</a> by <a class="reference external" href="https://github.com/sbbrandt">Simon Brandt</a>)</p></li>
 <li><p>Adding saving of preprocessing and windowing choices in <a class="reference internal" href="generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.preprocess()</span></code></a>, <a class="reference internal" href="generated/braindecode.preprocessing.create_windows_from_events.html#braindecode.preprocessing.create_windows_from_events" title="braindecode.preprocessing.create_windows_from_events"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_windows_from_events()</span></code></a> and <a class="reference internal" href="generated/braindecode.preprocessing.create_fixed_length_windows.html#braindecode.preprocessing.create_fixed_length_windows" title="braindecode.preprocessing.create_fixed_length_windows"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.create_fixed_length_windows()</span></code></a> to datasets to facilitate reproducibility (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/287">#287</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
@@ -643,9 +636,9 @@ <h3>Enhancements<a class="headerlink" href="#id17" title="Link to this heading">
 <li><p>Preprocessing and windowing choices are now saved on the level of individual datasets (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/288">#288</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
 <li><p>Serialization now happens entirely on dataset level creating subsets for individual datasets that contain ‘fif’ and ‘json’ files (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/288">#288</a> <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
 <li><p>Instantiation of TUH <a class="reference internal" href="generated/braindecode.datasets.TUH.html#braindecode.datasets.TUH" title="braindecode.datasets.tuh.TUH"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.tuh.TUH</span></code></a> and TUHAbnormal <a class="reference internal" href="generated/braindecode.datasets.TUHAbnormal.html#braindecode.datasets.TUHAbnormal" title="braindecode.datasets.tuh.TUHAbnormal"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.tuh.TUHAbnormal</span></code></a>, as well as loading <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.datautil.serialization.load_concat_dataset()</span></code> of stored datasets now support multiple workers (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/288">#288</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
-<li><p>Adding balanced sampling of sequences of windows with <a class="reference internal" href="generated/braindecode.samplers.BalancedSequenceSampler.html#braindecode.samplers.BalancedSequenceSampler" title="braindecode.samplers.BalancedSequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.BalancedSequenceSampler</span></code></a>  as proposed in U-Sleep paper (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/295">#295</a> by <a class="reference external" href="https://github.com/Tgnassou">Theo Gnassounou</a> and <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
+<li><p>Adding balanced sampling of sequences of windows with <a class="reference internal" href="generated/braindecode.samplers.BalancedSequenceSampler.html#braindecode.samplers.BalancedSequenceSampler" title="braindecode.samplers.BalancedSequenceSampler"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.samplers.BalancedSequenceSampler</span></code></a>  as proposed in U-Sleep paper (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/295">#295</a> by <a class="reference external" href="https://github.com/Tgnassou">Théo Gnassounou</a> and <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p><a class="reference internal" href="generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.preprocess()</span></code></a> can now work in parallel and serialize datasets to enable lazy-loading (i.e. <cite>preload=False</cite>) (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/277">#277</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
-<li><p>Adding <a class="reference internal" href="generated/braindecode.models.TimeDistributed.html#braindecode.models.TimeDistributed" title="braindecode.models.TimeDistributed"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.TimeDistributed</span></code></a> to apply a module on a sequence (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/318">#318</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
+<li><p>Adding <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.TimeDistributed</span></code> to apply a module on a sequence (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/318">#318</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p>Adding time series targets decoding together with <a class="reference internal" href="generated/braindecode.datasets.BCICompetitionIVDataset4.html#braindecode.datasets.BCICompetitionIVDataset4" title="braindecode.datasets.BCICompetitionIVDataset4"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.BCICompetitionIVDataset4</span></code></a> and fingers flexion decoding from ECoG examples (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/261">#261</a> by <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a> and <a class="reference external" href="https://github.com/MFattouh">Mohammed Fattouh</a>)</p></li>
 <li><p>Make EEGClassifier and EEGRegressor cloneable for scikit-learn (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/347">#347</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>, <a class="reference external" href="https://github.com/robintibor">Robin Tibor Schirrmeister</a>, <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a> and <a class="reference external" href="http://alexandre.gramfort.net">Alex Gramfort</a>)</p></li>
 <li><p>Allow to raise a warning when a few trials are shorter than the windows length, instead of raising an error and stopping all computation. (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/353">#353</a> by <a class="reference external" href="https://cedricrommel.github.io">Cedric Rommel</a>)</p></li>
@@ -655,19 +648,19 @@ <h3>Enhancements<a class="headerlink" href="#id17" title="Link to this heading">
 <li><p>Adding <code class="docutils literal notranslate"><span class="pre">crop</span></code> parameter to <a class="reference internal" href="generated/braindecode.datasets.SleepPhysionet.html#braindecode.datasets.SleepPhysionet" title="braindecode.datasets.SleepPhysionet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.SleepPhysionet</span></code></a> dataset to speed up examples (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/367">#367</a> by <a class="reference external" href="http://alexandre.gramfort.net">Alex Gramfort</a>)</p></li>
 </ul>
 </section>
-<section id="id18">
-<h3>Bugs<a class="headerlink" href="#id18" title="Link to this heading">#</a></h3>
+<section id="id8">
+<h3>Bugs<a class="headerlink" href="#id8" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Correctly computing recording length in <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.windowers.create_fixed_length_windows()</span></code> in case recording was cropped (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/304">#304</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
 <li><p>Fixing <a class="reference internal" href="generated/braindecode.datasets.SleepPhysionet.html#braindecode.datasets.SleepPhysionet" title="braindecode.datasets.SleepPhysionet"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datasets.SleepPhysionet</span></code></a> to allow serialization and avoid mismatch in channel names attributes (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/327">#327</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p>Propagating <cite>target_transform</cite> to all datasets when using <code class="xref py py-meth docutils literal notranslate"><span class="pre">braindecode.datasets.BaseConcatDataset.subset()</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/261">#261</a> by <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a>)</p></li>
 </ul>
 </section>
-<section id="id19">
-<h3>API changes<a class="headerlink" href="#id19" title="Link to this heading">#</a></h3>
+<section id="id9">
+<h3>API changes<a class="headerlink" href="#id9" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Removing the default sampling frequency sfreq value in <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.datasets.create_windows_from_events()</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/256">#256</a> by <a class="reference external" href="https://github.com/Ann-KathrinKiessner">Ann-Kathrin Kiessner</a>, <a class="reference external" href="https://github.com/dcwil">Daniel Wilson</a>, <a class="reference external" href="https://github.com/HenrikBons">Henrik Bonsmann</a>, <a class="reference external" href="https://github.com/vytjan">Vytautas Jankauskas</a>)</p></li>
-<li><p>Made windowing arguments optional in <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.windowers.create_fixed_length_windows()</span></code> &amp; <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.windowers.create_windows_from_events()</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/269">#269</a> by <a class="reference external" href="https://github.com/Ann-KathrinKiessner">Ann-Kathrin Kiessner</a>, <a href="#id29"><span class="problematic" id="id30">`Dan Wilson`_</span></a>, <a class="reference external" href="https://github.com/HenrikBons">Henrik Bonsmann</a>, <a class="reference external" href="https://github.com/vytjan">Vytautas Jankauskas</a>)</p></li>
+<li><p>Made windowing arguments optional in <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.windowers.create_fixed_length_windows()</span></code> &amp; <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.windowers.create_windows_from_events()</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/269">#269</a> by <a class="reference external" href="https://github.com/Ann-KathrinKiessner">Ann-Kathrin Kiessner</a>, <a class="reference external" href="https://github.com/dcwil">Daniel Wilson</a>, <a class="reference external" href="https://github.com/HenrikBons">Henrik Bonsmann</a>, <a class="reference external" href="https://github.com/vytjan">Vytautas Jankauskas</a>)</p></li>
 <li><p>Deprecating preprocessing functions <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.zscore()</span></code> and <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.scale()</span></code> in favour of sklearn’s implementation (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/292">#292</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p><a class="reference internal" href="generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess"><code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.preprocessing.preprocess()</span></code></a> now returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.dataset.BaseConcatDataset</span></code> object (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/277">#277</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 </ul>
@@ -675,8 +668,8 @@ <h3>API changes<a class="headerlink" href="#id19" title="Link to this heading">#
 </section>
 <section id="version-0-5-1-2021-07-14">
 <span id="changes-0-5-1"></span><h2>Version 0.5.1 (2021-07-14)<a class="headerlink" href="#version-0-5-1-2021-07-14" title="Link to this heading">#</a></h2>
-<section id="id20">
-<h3>Enhancements<a class="headerlink" href="#id20" title="Link to this heading">#</a></h3>
+<section id="id10">
+<h3>Enhancements<a class="headerlink" href="#id10" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Adding <cite>n_jobs</cite> parameter to windowers <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.datautil.create_windows_from_events()</span></code> and <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.datautil.create_fixed_length_windows()</span></code> to allow for parallelization of the windowing process (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/199">#199</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p>Adding support for on-the-fly transforms (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/198">#198</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
@@ -691,12 +684,12 @@ <h3>Enhancements<a class="headerlink" href="#id20" title="Link to this heading">
 <li><p>Removing code duplicate in BaseDataset and WindowsDataset (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/159">#159</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
 <li><p>Only load data if needed during preprocessing (e.g., allow timecrop without loading) (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/164">#164</a> by <a class="reference external" href="https://github.com/robintibor">Robin Tibor Schirrmeister</a>)</p></li>
 <li><p>Adding option to sort filtered channels by frequency band for the filterbank in <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.datautil.filterbank()</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/185">#185</a> by <a class="reference external" href="https://github.com/gemeinl">Lukas Gemein</a>)</p></li>
-<li><p>Adding the USleep model <a class="reference internal" href="generated/braindecode.models.USleep.html#braindecode.models.USleep" title="braindecode.models.USleep"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.USleep</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/282">#282</a> by <a class="reference external" href="https://github.com/Tgnassou">Theo Gnassounou</a> and <a class="reference external" href="https://github.com/l-omar-chehab">Omar Chehab</a>)</p></li>
+<li><p>Adding the USleep model <a class="reference internal" href="generated/braindecode.models.USleep.html#braindecode.models.USleep" title="braindecode.models.USleep"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.USleep</span></code></a> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/282">#282</a> by <a class="reference external" href="https://github.com/Tgnassou">Théo Gnassounou</a> and <a class="reference external" href="https://github.com/l-omar-chehab">Omar Chehab</a>)</p></li>
 <li><p>Adding <a class="reference internal" href="generated/braindecode.models.SleepStagerEldele2021.html#braindecode.models.SleepStagerEldele2021" title="braindecode.models.SleepStagerEldele2021"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.SleepStagerEldele2021</span></code></a> and <a class="reference internal" href="generated/braindecode.models.SleepStagerBlanco2020.html#braindecode.models.SleepStagerBlanco2020" title="braindecode.models.SleepStagerBlanco2020"><code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.models.SleepStagerBlanco2020</span></code></a> models for sleep staging  (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/341">#341</a> by <a class="reference external" href="https://github.com/Div12345">Divyesh Narayanan</a>)</p></li>
 </ul>
 </section>
-<section id="id21">
-<h3>Bugs<a class="headerlink" href="#id21" title="Link to this heading">#</a></h3>
+<section id="id11">
+<h3>Bugs<a class="headerlink" href="#id11" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Amplitude gradients are correctly computed for layers with multiple filters
 (before, they were accidentally summed over all previous filters in the layer) (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/167">#167</a> by <a class="reference external" href="https://github.com/robintibor">Robin Tibor Schirrmeister</a>)</p></li>
@@ -710,8 +703,8 @@ <h3>Bugs<a class="headerlink" href="#id21" title="Link to this heading">#</a></h
 <li><p>Make EEGResNet work for <code class="code docutils literal notranslate"><span class="pre">final_pool_length='auto'</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/223">#223</a> by <a class="reference external" href="https://github.com/robintibor">Robin Tibor Schirrmeister</a> and <a class="reference external" href="https://github.com/sliwy">Maciej Śliwowski</a>)</p></li>
 </ul>
 </section>
-<section id="id22">
-<h3>API changes<a class="headerlink" href="#id22" title="Link to this heading">#</a></h3>
+<section id="id12">
+<h3>API changes<a class="headerlink" href="#id12" title="Link to this heading">#</a></h3>
 <ul class="simple">
 <li><p>Preprocessor classes <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datautil.MNEPreproc</span></code> and <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datautil.NumpyPreproc</span></code> are deprecated in favor of <code class="xref py py-class docutils literal notranslate"><span class="pre">braindecode.datautil.Preprocessor</span></code> (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/197">#197</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
 <li><p>Parameter <cite>stop_offset_samples</cite> of <code class="xref py py-func docutils literal notranslate"><span class="pre">braindecode.datautil.create_fixed_length_windows()</span></code> must now be set to <cite>None</cite> instead of 0 to indicate the end of the recording (<a class="reference external" href="https://github.com/braindecode/braindecode/issues/152">#152</a> by <a class="reference external" href="https://github.com/hubertjb">Hubert Banville</a>)</p></li>
@@ -768,27 +761,27 @@ <h3>Authors<a class="headerlink" href="#authors" title="Link to this heading">#<
 </ul>
 </li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#current-0-8-11-2022">Current 0.8 (11-2022)</a><ul class="nav section-nav flex-column">
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id7">Enhancements</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id12">Bugs</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id13">API changes</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id1">Enhancements</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id2">Bugs</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id3">API changes</a></li>
 </ul>
 </li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#current-0-7-10-2022">Current 0.7 (10-2022)</a><ul class="nav section-nav flex-column">
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id14">Enhancements</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id15">Bugs</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id16">API changes</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id4">Enhancements</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id5">Bugs</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id6">API changes</a></li>
 </ul>
 </li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#version-0-6-2021-12-06">Version 0.6 (2021-12-06)</a><ul class="nav section-nav flex-column">
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id17">Enhancements</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id18">Bugs</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id19">API changes</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id7">Enhancements</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id8">Bugs</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id9">API changes</a></li>
 </ul>
 </li>
 <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#version-0-5-1-2021-07-14">Version 0.5.1 (2021-07-14)</a><ul class="nav section-nav flex-column">
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id20">Enhancements</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id21">Bugs</a></li>
-<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id22">API changes</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id10">Enhancements</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id11">Bugs</a></li>
+<li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#id12">API changes</a></li>
 <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#authors">Authors</a></li>
 </ul>
 </li>