Export output graph pb remains same size even after trained common voice datasets 60k steps

[JRMeyer]

>>> javi.rahman
[September 8, 2019, 10:46am]

Hi,

I have been Training common voice dataset from pre-trained model 0.5.1.
I have downloaded checkpoint of 0.5.1 and started the training from
that.

I am using Ubuntu 18.04 slash
RTX 4000 slash
Deepspeech 0.5.1 slash
CUDA 10.0 and CUDNN 7.5.1

Here is my command slash
export TF_FORCE_GPU_ALLOW_GROWTH=true

python -u DeepSpeech.py slash
--n_hidden 2048 slash
--epochs 3 slash
--checkpoint_dir /home/karthik/speech/DeepSpeech/data/checkpoint/ slash
--train_files /home/karthik/speech/DeepSpeech/data/corpus/clips/train.csv slash
--dev_files /home/karthik/speech/DeepSpeech/data/corpus/clips/dev.csv slash
--test_files /home/karthik/speech/DeepSpeech/data/corpus/clips/test.csv slash
--train_batch_size 8 slash
--dev_batch_size 10 slash
--test_batch_size 10 slash
--dropout_rate 0.15 slash
--lm_alpha 0.75 slash
--lm_beta 1.85 slash
--learning_rate 0.0001 slash
--lm_binary_path /home/karthik/speech/DeepSpeech/data/originalLmBinary/lm.binary slash
--lm_trie_path /home/karthik/speech/DeepSpeech/data/originalLmBinary/trie slash
--export_dir /home/karthik/speech/DeepSpeech/data/export/ slash
'$'

Everything is working fine and model has been trained and exported. slash
But the exported file output_graph.pb file size remains the same size
as deepspeech pre-trained model size 188.9mb.

I don't know whether my training files has been concatenated with the
pre-trained models. I assume the file size will get increased while i am
training common voice datasets. But i see from the pre-trained 467356
steps has been increased with 487573 after the export.

Please clarify.

[This is an archived TTS discussion thread from discourse.mozilla.org/t/export-output-graph-pb-remains-same-size-even-after-trained-common-voice-datasets-60k-steps]

[JRMeyer]

>>> lissyx
[September 8, 2019, 12:55pm]



> But the exported file output_graph.pb file size remains the same
> size as deepspeech pre-trained model size 188.9mb.

Model size depends on the number of parameters, not on the amount of
data. Since you kept the same geometry, this is expected.

[Archived Post]

[JRMeyer]

>>> javi.rahman
[September 8, 2019, 1:44pm]

Is there any documentation for how to use the parameters. I see
util/flags.py but not more detail.

I will would like to fine tune the checkpoints oftenly. slash
Any suggestions please.

[Archived Post]

[JRMeyer]

>>> lissyx
[September 8, 2019, 2:33pm]

That depends on the meaning of your questions. How to use parameters is
documented in util/flags.py. If you mean how in the sense of what
values you should select, that depends on your use-case ...

If you mean something else, please explain what is missing in the
current code.

[Archived Post]

[JRMeyer]

>>> javi.rahman
[September 8, 2019, 6:08pm]

,

I would like to train from the pre-trained model, I have been using
these parameters.

python -u DeepSpeech.py slash
--n_hidden 2048 slash
--epochs 3 slash
--checkpoint_dir /home/karthik/speech/DeepSpeech/data/checkpoint/ slash
--train_files /home/karthik/speech/DeepSpeech/data/corpus/clips/train.csv slash
--dev_files /home/karthik/speech/DeepSpeech/data/corpus/clips/dev.csv slash
--test_files /home/karthik/speech/DeepSpeech/data/corpus/clips/test.csv slash
--train_batch_size 8 slash
--dev_batch_size 10 slash
--test_batch_size 10 slash
--dropout_rate 0.15 slash
--lm_alpha 0.75 slash
--lm_beta 1.85 slash
--learning_rate 0.0001 slash
--lm_binary_path /home/karthik/speech/DeepSpeech/data/originalLmBinary/lm.binary slash
--lm_trie_path /home/karthik/speech/DeepSpeech/data/originalLmBinary/trie slash
--export_dir /home/karthik/speech/DeepSpeech/data/export/ slash
'$'

Could you please correct parameters if I have specified anything wrong
here or any parameters missed. Also, I have used the param what
deepspeech 0.5.1 models used.

Note:: For understanding those parameters usage in detail, should I
learn deep learning or machine learning in detail.

[Archived Post]

[JRMeyer]

>>> lissyx
[September 8, 2019, 6:10pm]



> Note:: For understanding those parameters usage in detail, should I
> learn deep learning or machine learning in detail.

Yeah, this is not black magic, you need to understand what you are doing
...

[Archived Post]