mirrors
/
mmpretrain
mirror of https://github.com/open-mmlab/mmpretrain.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
mmpretrain/mmcls/models/backbones/__init__.py

25 lines
838 B
Python
Raw Normal View History

Add AlexNet and LeNet5
2020-07-08 10:48:08 +08:00
from .alexnet import AlexNet
from .lenet import LeNet5
add mobilenetv2
2020-06-16 14:37:03 +08:00
from .mobilenet_v2 import MobileNetV2
Fix Mobilenetv3 structure and add pretrained model (#291) * Refactor Mobilenetv3 structure and add ConvClsHead. * Change model's name from 'MobileNetv3' to 'MobileNetV3' * Modify configs for MobileNetV3 on CIFAR10. And add MobileNetV3 configs for imagenet * Fix activate setting bugs in MobileNetV3. And remove bias in SELayer. * Modify unittest * Remove useless config and file. * Fix mobilenetv3-large arch setting * Add dropout option in ConvClsHead * Fix MobilenetV3 structure according to torchvision version. 1. Remove with_expand_conv option in InvertedResidual, it should be decided by channels. 2. Revert activation function, should before SE layer. * Format code. * Rename MobilenetV3 arch "big" to "large". * Add mobilenetv3_small torchvision training recipe * Modify default `out_indices` of MobilenetV3, now it will change according to `arch` if not specified. * Add MobilenetV3 large config. * Add mobilenetv3 README * Modify InvertedResidual unit test. * Refactor ConvClsHead to StackedLinearClsHead, and add unit tests. * Add unit test for `simple_test` of `StackedLinearClsHead`. * Fix typo Co-authored-by: Yidi Shao <ydshao@smail.nju.edu.cn>
2021-06-27 23:19:36 +08:00
from .mobilenet_v3 import MobileNetV3
Add RegNet
2020-07-01 14:21:45 +08:00
from .regnet import RegNet
Add ResNeSt (#25) * Add ResNeSt * fixed test * refactor * add ResNeSt base * update modelzoo * update modelzoo * Add S-200,S269 _base_
2020-09-22 10:41:51 +08:00
from .resnest import ResNeSt
Add Base and ResNet backbone
2020-06-12 14:40:27 +08:00
from .resnet import ResNet, ResNetV1d
Add ResNet_CIFAR
2020-07-09 14:19:15 +08:00
from .resnet_cifar import ResNet_CIFAR
Add ResNeXt
2020-06-14 12:08:37 +08:00
from .resnext import ResNeXt
Dev se resnet
2020-06-17 14:20:20 +08:00
from .seresnet import SEResNet
Dev se resnext
2020-06-19 11:45:42 +08:00
from .seresnext import SEResNeXt
add mobilenetv2
2020-06-16 14:37:03 +08:00
from .shufflenet_v1 import ShuffleNetV1
from .shufflenet_v2 import ShuffleNetV2
[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
from .swin_transformer import SwinTransformer
[Feature] Add transformer in transformer (#339) * add tnt_small configs * add tnt backbone * test tnt * add tnt to model_zoo * rename the config file name * add optimizor * move tnt backbone unitest * add metric * fix keyname in arch * encapsulate "inner transformer block" and "outer transformer block" * fix TnT * Use `inner_block_cfg` and `outer_block_cfg` instead of `args` and `kwargs`. Co-authored-by: mzr1996 <mzr1996@163.com>
2021-07-30 09:16:27 +08:00
from .tnt import TNT
Add VGG and pretained models (#27) * add vgg * add vgg model coversion tool * fix out_indices and docstr * add vgg models in configs * add params, flops and accuracy in docs * add pretrained models url * use ConvModule and refine var names * update vgg conversion tool * modify bn config * add docs for arch_setting * add unit test for vgg * rm debug code * update vgg pretrained models
2020-09-29 17:49:42 +08:00
from .vgg import VGG
[Feature]Add Vit (#214) * add imagenet bs 4096 * add vit_base_patch16_224_finetune * add vit_base_patch16_224_pretrain * add vit_base_patch16_384_finetune * add vit_base_patch16_384_finetune * add vit_b_p16_224_finetune_imagenet * add vit_b_p16_224_pretrain_imagenet * add vit_b_p16_384_finetune_imagenet * add vit * add vit * add vit head * vit unitest * keep up with ClsHead * test vit * add flag to determiine whether to calculate acc during training * Changes related to mmcv1.3.0 * change checkpoint saving interval to 10 * add label smooth * default_runtime.py recovery * docformatter * docformatter * delete 2 lines of comments * delete configs/_base_/schedules/imagenet_bs4096.py * add configs/_base_/schedules/imagenet_bs2048_AdamW.py * rename imagenet_bs4096.py to imagenet_bs2048_AdamW.py * add helpers.py * test vit hybrid backbone * fix HybridEmbed * use to_2tuple instead
2021-04-16 19:22:41 +08:00
from .vision_transformer import VisionTransformer
fix & add test
2020-06-03 15:51:17 +08:00
fix norm_eval & merge master
2020-06-15 02:16:13 +08:00
__all__ = [
Add VGG and pretained models (#27) * add vgg * add vgg model coversion tool * fix out_indices and docstr * add vgg models in configs * add params, flops and accuracy in docs * add pretrained models url * use ConvModule and refine var names * update vgg conversion tool * modify bn config * add docs for arch_setting * add unit test for vgg * rm debug code * update vgg pretrained models
2020-09-29 17:49:42 +08:00
'LeNet5', 'AlexNet', 'VGG', 'RegNet', 'ResNet', 'ResNeXt', 'ResNetV1d',
'ResNeSt', 'ResNet_CIFAR', 'SEResNet', 'SEResNeXt', 'ShuffleNetV1',
[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
'ShuffleNetV2', 'MobileNetV2', 'MobileNetV3', 'VisionTransformer',
[Feature] Add transformer in transformer (#339) * add tnt_small configs * add tnt backbone * test tnt * add tnt to model_zoo * rename the config file name * add optimizor * move tnt backbone unitest * add metric * fix keyname in arch * encapsulate "inner transformer block" and "outer transformer block" * fix TnT * Use `inner_block_cfg` and `outer_block_cfg` instead of `args` and `kwargs`. Co-authored-by: mzr1996 <mzr1996@163.com>
2021-07-30 09:16:27 +08:00
'SwinTransformer', 'TNT'
fix norm_eval & merge master
2020-06-15 02:16:13 +08:00
]