mirrors/mmclassification
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmclassification.git synced 2025-06-03 21:53:55 +08:00
Code Issues Projects Releases Wiki Activity
mmclassification/docs/model_zoo.md
Ma Zerun 076ee10cac
[Feature] Add swin-transformer model. (#271) 
* Add swin transformer archs S, B and L.

* Add SwinTransformer configs

* Add train config files of swin.

* Align init method with original code

* Use nn.Unfold to merge patch

* Change all ConfigDict to dict

* Add init_cfg for all subclasses of BaseModule.

* Use mmcv version init function

* Add Swin README

* Use safer cfg copy method

* Improve docstring and variable name.

* Fix some difference in randaug

Fix BGR bug, align scheduler config.

Fix label smoothing parameter difference.

* Fix missing droppath in attn

* Fix bug of relative posititon table if window width is not equal to
height.

* Make `PatchMerging` more general, support kernel, stride, padding and
dilation.

* Rename `residual` to `identity` in attention and FFN.

* Add `auto_pad` option to auto pad feature map

* Improve docstring.

* Fix bug in ShiftWMSA padding.

* Remove unused `key` and `value` in ShiftWMSA

* Move `PatchMerging` into utils and use common `PatchEmbed`.

* Use latest `LinearClsHead`, train augments and label smooth settings.
And remove original `SwinLinearClsHead`.

* Mark some configs as "Evalution Only".

* Remove useless comment in config

* 1. Move ShiftWindowMSA and WindowMSA to `utils/attention.py`
2. Add docstrings of each module.
3. Fix some variables' names.
4. Other small improvement.

* Add unit tests of swin-transformer and patchmerging.

* Fix some bugs in unit tests.

* Fix bug of rel_position_index if window is not square.

* Make WindowMSA implicit, and add unit tests.

* Add metafile.yml, update readme and model_zoo.
2021-07-01 09:30:42 +08:00

16 KiB
Raw Blame History

Model Zoo

ImageNet

ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. The ResNet family models below are trained by standard data augmentations, i.e., RandomResizedCrop, RandomHorizontalFlip and Normalize.

Model Params(M) Flops(G) Top-1 (%) Top-5 (%) Config Download
VGG-11 132.86 7.63 68.75 88.87 config model | log
VGG-13 133.05 11.34 70.02 89.46 config model | log
VGG-16 138.36 15.5 71.62 90.49 config model | log
VGG-19 143.67 19.67 72.41 90.80 config model | log
VGG-11-BN 132.87 7.64 70.75 90.12 config model | log
VGG-13-BN 133.05 11.36 72.15 90.71 config model | log
VGG-16-BN 138.37 15.53 73.72 91.68 config model | log
VGG-19-BN 143.68 19.7 74.70 92.24 config model | log
ResNet-18 11.69 1.82 70.07 89.44 config model | log
ResNet-34 21.8 3.68 73.85 91.53 config model | log
ResNet-50 25.56 4.12 76.55 93.15 config model | log
ResNet-101 44.55 7.85 78.18 94.03 config model | log
ResNet-152 60.19 11.58 78.63 94.16 config model | log
ResNeSt-50* 27.48 5.41 81.13 95.59 model | log
ResNeSt-101* 48.28 10.27 82.32 96.24 model | log
ResNeSt-200* 70.2 17.53 82.41 96.22 model | log
ResNeSt-269* 110.93 22.58 82.70 96.28 model | log
ResNetV1D-50 25.58 4.36 77.54 93.57 config model | log
ResNetV1D-101 44.57 8.09 78.93 94.48 config model | log
ResNetV1D-152 60.21 11.82 79.41 94.7 config model | log
ResNeXt-32x4d-50 25.03 4.27 77.90 93.66 config model | log
ResNeXt-32x4d-101 44.18 8.03 78.71 94.12 config model | log
ResNeXt-32x8d-101 88.79 16.5 79.23 94.58 config model | log
ResNeXt-32x4d-152 59.95 11.8 78.93 94.41 config model | log
SE-ResNet-50 28.09 4.13 77.74 93.84 config model | log
SE-ResNet-101 49.33 7.86 78.26 94.07 config model | log
ShuffleNetV1 1.0x (group=3) 1.87 0.146 68.13 87.81 config model | log
ShuffleNetV2 1.0x 2.28 0.149 69.55 88.92 config model | log
MobileNet V2 3.5 0.319 71.86 90.42 config model | log
ViT-B/16* 86.86 33.03 84.20 97.18 config model | log
ViT-B/32* 88.3 8.56 81.73 96.13 config model | log
ViT-L/16* 304.72 116.68 85.08 97.38 config model | log
ViT-L/32* 306.63 29.66 81.52 96.06 config model | log
Swin-Transformer tiny 28.29 4.36 81.18 95.61 config model | log
Swin-Transformer small 49.61 8.52 83.02 96.29 config model | log
Swin-Transformer base 87.77 15.14 83.36 96.44 config model | log

Models with * are converted from other repos, others are trained by ourselves.

CIFAR10

Model Params(M) Flops(G) Top-1 (%) Config Download
ResNet-18-b16x8 11.17 0.56 94.82 config
ResNet-34-b16x8 21.28 1.16 95.34 config
ResNet-50-b16x8 23.52 1.31 95.55 config
ResNet-101-b16x8 42.51 2.52 95.58 config
ResNet-152-b16x8 58.16 3.74 95.76 config