-
Notifications
You must be signed in to change notification settings - Fork 1.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Feature] Support MobileOne TSN/TSM (#2656)
- Loading branch information
Showing
18 changed files
with
643 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -66,6 +66,7 @@ jobs: | |
| mim install 'mmcv >= 2.0.0' | ||
| pip install git+https://[email protected]/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install -r requirements.txt | ||
| - run: | ||
|
|
@@ -126,6 +127,7 @@ jobs: | |
| docker exec mmaction pip install git+https://[email protected]/open-mmlab/[email protected] | ||
| docker exec mmaction pip install git+https://[email protected]/open-mmlab/[email protected] | ||
| docker exec mmaction pip install git+https://github.com/open-mmlab/[email protected] | ||
| docker exec mmaction pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| docker exec mmaction pip install -r requirements.txt | ||
| - run: | ||
| name: Build and install | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -60,6 +60,8 @@ jobs: | |
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install MMCls | ||
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install MMPretrain | ||
| run: pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| - name: Install MMPose | ||
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install PytorchVideo | ||
|
|
@@ -122,6 +124,8 @@ jobs: | |
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install MMCls | ||
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install MMPretrain | ||
| run: pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| - name: Install MMPose | ||
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install unittest dependencies | ||
|
|
@@ -186,6 +190,7 @@ jobs: | |
| mim install 'mmcv >= 2.0.0' | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install -r requirements.txt | ||
| - name: Install PytorchVideo | ||
|
|
@@ -228,6 +233,7 @@ jobs: | |
| mim install 'mmcv >= 2.0.0' | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install -r requirements.txt | ||
| - name: Install PytorchVideo | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -51,6 +51,8 @@ jobs: | |
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install MMCls | ||
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install MMPretrain | ||
| run: pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| - name: Install MMPose | ||
| run: pip install git+https://github.com/open-mmlab/[email protected] | ||
| - name: Install unittest dependencies | ||
|
|
@@ -119,6 +121,7 @@ jobs: | |
| mim install 'mmcv >= 2.0.0' | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install -r requirements.txt | ||
| - name: Install PytorchVideo | ||
|
|
@@ -168,6 +171,7 @@ jobs: | |
| mim install 'mmcv >= 2.0.0' | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install git+https://github.com/open-mmlab/mmpretrain.git@dev | ||
| pip install git+https://github.com/open-mmlab/[email protected] | ||
| pip install -r requirements.txt | ||
| - name: Install PytorchVideo | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,31 @@ | ||
| # model settings | ||
| preprocess_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]) | ||
|
|
||
| checkpoint = ('https://download.openmmlab.com/mmclassification/' | ||
| 'v0/mobileone/mobileone-s4_8xb32_in1k_20221110-28d888cb.pth') | ||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='MobileOneTSM', | ||
| arch='s4', | ||
| shift_div=8, | ||
| num_segments=8, | ||
| is_shift=True, | ||
| init_cfg=dict( | ||
| type='Pretrained', checkpoint=checkpoint, prefix='backbone')), | ||
| cls_head=dict( | ||
| type='TSMHead', | ||
| num_segments=8, | ||
| num_classes=400, | ||
| in_channels=2048, | ||
| spatial_type='avg', | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| dropout_ratio=0.5, | ||
| init_std=0.001, | ||
| is_shift=True, | ||
| average_clips='prob'), | ||
| # model training and testing settings | ||
| data_preprocessor=dict(type='ActionDataPreprocessor', **preprocess_cfg), | ||
| train_cfg=None, | ||
| test_cfg=None) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,26 @@ | ||
| checkpoint = ('https://download.openmmlab.com/mmclassification/' | ||
| 'v0/mobileone/mobileone-s0_8xb32_in1k_20221110-0bc94952.pth') | ||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='mmpretrain.MobileOne', | ||
| arch='s0', | ||
| init_cfg=dict( | ||
| type='Pretrained', checkpoint=checkpoint, prefix='backbone'), | ||
| norm_eval=False), | ||
| cls_head=dict( | ||
| type='TSNHead', | ||
| num_classes=400, | ||
| in_channels=1024, | ||
| spatial_type='avg', | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| dropout_ratio=0.4, | ||
| init_std=0.01, | ||
| average_clips='prob'), | ||
| data_preprocessor=dict( | ||
| type='ActionDataPreprocessor', | ||
| mean=[123.675, 116.28, 103.53], | ||
| std=[58.395, 57.12, 57.375], | ||
| format_shape='NCHW'), | ||
| train_cfg=None, | ||
| test_cfg=None) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
126 changes: 126 additions & 0 deletions
126
.../recognition/tsm/tsm_imagenet-pretrained-mobileone-s4_8xb16-1x1x16-50e_kinetics400-rgb.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,126 @@ | ||
| _base_ = [ | ||
| '../../_base_/models/tsm_mobileone_s4.py', | ||
| '../../_base_/default_runtime.py' | ||
| ] | ||
|
|
||
| model = dict(cls_head=dict(num_segments=16)) | ||
| # dataset settings | ||
| dataset_type = 'VideoDataset' | ||
| data_root = 'data/kinetics400/videos_train' | ||
| data_root_val = 'data/kinetics400/videos_val' | ||
| ann_file_train = 'data/kinetics400/kinetics400_train_list_videos.txt' | ||
| ann_file_val = 'data/kinetics400/kinetics400_val_list_videos.txt' | ||
|
|
||
| file_client_args = dict(io_backend='disk') | ||
|
|
||
| train_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=16), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict( | ||
| type='MultiScaleCrop', | ||
| input_size=224, | ||
| scales=(1, 0.875, 0.75, 0.66), | ||
| random_crop=False, | ||
| max_wh_scale_gap=1, | ||
| num_fixed_crops=13), | ||
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
| val_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=16, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=16, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=8, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=dict(video=data_root), | ||
| pipeline=train_pipeline)) | ||
| val_dataloader = dict( | ||
| batch_size=8, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=dict(video=data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True)) | ||
| test_dataloader = dict( | ||
| batch_size=1, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=dict(video=data_root_val), | ||
| pipeline=test_pipeline, | ||
| test_mode=True)) | ||
|
|
||
| val_evaluator = dict(type='AccMetric') | ||
| test_evaluator = val_evaluator | ||
|
|
||
| default_hooks = dict(checkpoint=dict(interval=3, max_keep_ckpts=3)) | ||
|
|
||
| train_cfg = dict( | ||
| type='EpochBasedTrainLoop', max_epochs=50, val_begin=1, val_interval=1) | ||
| val_cfg = dict(type='ValLoop') | ||
| test_cfg = dict(type='TestLoop') | ||
|
|
||
| param_scheduler = [ | ||
| dict(type='LinearLR', start_factor=0.1, by_epoch=True, begin=0, end=5), | ||
| dict( | ||
| type='MultiStepLR', | ||
| begin=0, | ||
| end=50, | ||
| by_epoch=True, | ||
| milestones=[25, 45], | ||
| gamma=0.1) | ||
| ] | ||
|
|
||
| optim_wrapper = dict( | ||
| constructor='TSMOptimWrapperConstructor', | ||
| paramwise_cfg=dict(fc_lr5=True), | ||
| optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.00002), | ||
| clip_grad=dict(max_norm=20, norm_type=2)) | ||
|
|
||
| # Default setting for scaling LR automatically | ||
| # - `enable` means enable scaling LR automatically | ||
| # or not by default. | ||
| # - `base_batch_size` = (8 GPUs) x (16 samples per GPU). | ||
| auto_scale_lr = dict(enable=True, base_batch_size=128) |
5 changes: 5 additions & 0 deletions
5
...ition/tsm/tsm_imagenet-pretrained-mobileone-s4_deploy_8xb16-1x1x16-50e_kinetics400-rgb.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| _base_ = [ | ||
| './tsm_imagenet-pretrained-mobileone-s4_8xb16-1x1x16-50e_kinetics400-rgb.py', # noqa: E501 | ||
| ] | ||
|
|
||
| model = dict(backbone=dict(deploy=True)) |
Oops, something went wrong.