Skip to content

Commit

Permalink
update README
Browse files Browse the repository at this point in the history
  • Loading branch information
@MzeroMiko
MzeroMiko committed May 26, 2024
1 parent 304039e commit 5b3bb7d
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 4 deletions.
2 changes: 1 addition & 1 deletion README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ Designing computationally efficient network architectures persists as an ongoing
| Swin-B | ImageNet-1K | 224x224 | 83.5 | 88M | 15.4G | 458 |496 | -- |
| VMamba-S[`s2l15`] | ImageNet-1K | 224x224 | 83.6 | 50M | 8.7G | 877 | 314| [config](../classification/configs/vssm/vmambav2_small_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_small_0229.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_small_0229_ckpt_epoch_222.pth) |
| VMamba-B[`s2l15`] | ImageNet-1K | 224x224 | 83.9 | 89M | 15.4G | 646 | 247 | [config](../classification/configs/vssm/vmambav2_base_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_base_0229.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_base_0229_ckpt_epoch_237.pth) |
| VMamba-T[`s1l8`] | ImageNet-1K | 224x224 | 82.6 | 30M | 4.9G | 1686| 571| [config](../classification/configs/vssm/vmambav2v_tiny_224.yaml)/[log](#)/[ckpt](#) |
| VMamba-T[`s1l8`] | ImageNet-1K | 224x224 | 82.6 | 30M | 4.9G | 1686| 571| [config](../classification/configs/vssm/vmambav2v_tiny_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_tiny_0230s.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_tiny_0230s_ckpt_epoch_264.pth) |


* *Models in this subsection is trained from scratch with random or manual initialization. The hyper-parameters are inherited from Swin, except for `drop_path_rate` and `EMA`. All models are trained with EMA except for the `Vanilla-VMamba-T`.*
Expand Down
6 changes: 3 additions & 3 deletions assets/performance.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,9 @@
| VMamba-T[`s2l5`] | ImageNet-1K | 224x224 | 82.5 | 31M | 4.9G | 1340 | 464 | [config](../classification/configs/vssm/vmambav2_tiny_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_tiny_0230.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_tiny_0230_ckpt_epoch_262.pth) |
| VMamba-S[`s2l15`] | ImageNet-1K | 224x224 | 83.6 | 50M | 8.7G | 877 | 314| [config](../classification/configs/vssm/vmambav2_small_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_small_0229.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_small_0229_ckpt_epoch_222.pth) |
| VMamba-B[`s2l15`] | ImageNet-1K | 224x224 | 83.9 | 89M | 15.4G | 646 | 247 | [config](../classification/configs/vssm/vmambav2_base_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_base_0229.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm_base_0229_ckpt_epoch_237.pth) |
| VMamba-T[`s1l8`] | ImageNet-1K | 224x224 | 82.6 | 30M | 4.9G | 1686| 571| [config](../classification/configs/vssm/vmambav2v_tiny_224.yaml)/[log](#)/[ckpt](#) |
| VMamba-S[`s1l20`] | ImageNet-1K | 224x224 | 83.3 | 49M | 8.6G | 1106| 390 | [config](../classification/configs/vssm/vmambav2v_small_224.yaml)/[log](#)/[ckpt](#) |
| VMamba-B[`s1l20`] | ImageNet-1K | 224x224 | 83.8 | 87M | 15.2G | 827 | 313| [config](../classification/configs/vssm/vmambav2v_base_224.yaml)/[log](#)/[ckpt](#) |
| VMamba-T[`s1l8`] | ImageNet-1K | 224x224 | 82.6 | 30M | 4.9G | 1686| 571| [config](../classification/configs/vssm/vmambav2v_tiny_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_tiny_0230s.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_tiny_0230s_ckpt_epoch_264.pth) |
| VMamba-S[`s1l20`] | ImageNet-1K | 224x224 | 83.3 | 49M | 8.6G | 1106| 390 | [config](../classification/configs/vssm/vmambav2v_small_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_small_0229s.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_small_0229s_ckpt_epoch_240.pth) |
| VMamba-B[`s1l20`] | ImageNet-1K | 224x224 | 83.8 | 87M | 15.2G | 827 | 313| [config](../classification/configs/vssm/vmambav2v_base_224.yaml)/[log](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_base_0229s.txt)/[ckpt](https://github.com/MzeroMiko/VMamba/releases/download/%2320240316/vssm1_base_0229s_ckpt_epoch_225.pth) |

* *Models in this subsection is trained from scratch with random or manual initialization. The hyper-parameters are inherited from Swin, except for `drop_path_rate` and `EMA`. All models are trained with EMA except for the `Vanilla-VMamba-T`.*
* *`TP.(Throughput)` and `Train TP. (Train Throughput)` are assessed on an A100 GPU paired with an AMD EPYC 7542 CPU, with batch size 128. `Train TP.` is tested with mix-resolution, excluding the time consumption of optimizers.*
Expand Down

0 comments on commit 5b3bb7d

Please sign in to comment.