Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Feature] Support Mixup and Cutmix for Recognizers. (#681)
* add todo list * codes of mixup/cutmix/register/recognizers * add unittest * add demo config * fix unittest * remove toto list * update changelog * fix unittest and training bug * fix * fix unittest * add todo * remove useless codes * update comments * update docs * fix * fix a bug * update configs * update sthv1 training results * add tsn config and modify default alpha value * fix lint * add unittest * fix tin sthv2 config * update links * remove useless docs Co-authored-by: Kenny <dhd.efz@gmail.com>
- Loading branch information
1 parent
3268fee
commit fbe62f6
Showing
14 changed files
with
604 additions
and
6 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
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
114 changes: 114 additions & 0 deletions
114
configs/recognition/tsm/tsm_r50_cutmix_1x1x8_50e_sthv1_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 +1,114 @@ | ||
| _base_ = [ | ||
| '../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py' | ||
| ] | ||
|
|
||
| # model settings | ||
| # model settings# model settings | ||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='ResNetTSM', | ||
| pretrained='torchvision://resnet50', | ||
| depth=50, | ||
| norm_eval=False, | ||
| shift_div=8), | ||
| cls_head=dict( | ||
| type='TSMHead', | ||
| num_classes=174, | ||
| in_channels=2048, | ||
| spatial_type='avg', | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| dropout_ratio=0.5, | ||
| init_std=0.001, | ||
| is_shift=True), | ||
| # model training and testing settings | ||
| train_cfg=dict( | ||
| blending=dict(type='CutmixBlending', num_classes=174, alpha=.2)), | ||
| test_cfg=dict(average_clips='prob')) | ||
|
|
||
| # dataset settings | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/sthv1/rawframes' | ||
| data_root_val = 'data/sthv1/rawframes' | ||
| ann_file_train = 'data/sthv1/sthv1_train_list_rawframes.txt' | ||
| ann_file_val = 'data/sthv1/sthv1_val_list_rawframes.txt' | ||
| ann_file_test = 'data/sthv1/sthv1_val_list_rawframes.txt' | ||
| img_norm_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) | ||
| train_pipeline = [ | ||
| dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), | ||
| dict(type='RawFrameDecode'), | ||
| 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='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| twice_sample=True, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=8, | ||
| workers_per_gpu=4, | ||
| train=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| filename_tmpl='{:05}.jpg', | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| filename_tmpl='{:05}.jpg', | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| filename_tmpl='{:05}.jpg', | ||
| pipeline=test_pipeline)) | ||
| evaluation = dict( | ||
| interval=2, metrics=['top_k_accuracy', 'mean_class_accuracy']) | ||
|
|
||
| # optimizer | ||
| optimizer = dict(weight_decay=0.0005) | ||
|
|
||
| # runtime settings | ||
| work_dir = './work_dirs/tsm_r50_cutmix_1x1x8_50e_sthv1_rgb/' |
114 changes: 114 additions & 0 deletions
114
configs/recognition/tsm/tsm_r50_mixup_1x1x8_50e_sthv1_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 +1,114 @@ | ||
| _base_ = [ | ||
| '../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py' | ||
| ] | ||
|
|
||
| # model settings | ||
| # model settings# model settings | ||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='ResNetTSM', | ||
| pretrained='torchvision://resnet50', | ||
| depth=50, | ||
| norm_eval=False, | ||
| shift_div=8), | ||
| cls_head=dict( | ||
| type='TSMHead', | ||
| num_classes=174, | ||
| in_channels=2048, | ||
| spatial_type='avg', | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| dropout_ratio=0.5, | ||
| init_std=0.001, | ||
| is_shift=True), | ||
| # model training and testing settings | ||
| train_cfg=dict( | ||
| blending=dict(type='MixupBlending', num_classes=174, alpha=.2)), | ||
| test_cfg=dict(average_clips='prob')) | ||
|
|
||
| # dataset settings | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/sthv1/rawframes' | ||
| data_root_val = 'data/sthv1/rawframes' | ||
| ann_file_train = 'data/sthv1/sthv1_train_list_rawframes.txt' | ||
| ann_file_val = 'data/sthv1/sthv1_val_list_rawframes.txt' | ||
| ann_file_test = 'data/sthv1/sthv1_val_list_rawframes.txt' | ||
| img_norm_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) | ||
| train_pipeline = [ | ||
| dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), | ||
| dict(type='RawFrameDecode'), | ||
| 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='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| twice_sample=True, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=8, | ||
| workers_per_gpu=4, | ||
| train=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| filename_tmpl='{:05}.jpg', | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| filename_tmpl='{:05}.jpg', | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| filename_tmpl='{:05}.jpg', | ||
| pipeline=test_pipeline)) | ||
| evaluation = dict( | ||
| interval=2, metrics=['top_k_accuracy', 'mean_class_accuracy']) | ||
|
|
||
| # optimizer | ||
| optimizer = dict(weight_decay=0.0005) | ||
|
|
||
| # runtime settings | ||
| work_dir = './work_dirs/tsm_r50_mixup_1x1x8_50e_sthv1_rgb/' |
110 changes: 110 additions & 0 deletions
110
configs/recognition/tsn/tsn_r50_video_mixup_1x1x8_100e_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 +1,110 @@ | ||
| _base_ = [ | ||
| '../../_base_/schedules/sgd_100e.py', '../../_base_/default_runtime.py' | ||
| ] | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='ResNet', | ||
| pretrained='torchvision://resnet50', | ||
| depth=50, | ||
| norm_eval=False), | ||
| cls_head=dict( | ||
| type='TSNHead', | ||
| num_classes=400, | ||
| in_channels=2048, | ||
| spatial_type='avg', | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| dropout_ratio=0.4, | ||
| init_std=0.01), | ||
| # model training and testing settings | ||
| # train_cfg=dict( | ||
| # blending=dict(type="CutmixBlending", num_classes=400, alpha=.2)), | ||
| train_cfg=dict( | ||
| blending=dict(type='MixupBlending', num_classes=400, alpha=.2)), | ||
| test_cfg=dict(average_clips=None)) | ||
|
|
||
| # 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' | ||
| ann_file_test = 'data/kinetics400/kinetics400_val_list_videos.txt' | ||
| img_norm_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) | ||
| train_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), | ||
| dict(type='DecordDecode'), | ||
| dict( | ||
| type='MultiScaleCrop', | ||
| input_size=224, | ||
| scales=(1, 0.875, 0.75, 0.66), | ||
| random_crop=False, | ||
| max_wh_scale_gap=1), | ||
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=25, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=32, | ||
| workers_per_gpu=4, | ||
| train=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| pipeline=test_pipeline)) | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy']) | ||
|
|
||
| # runtime settings | ||
| work_dir = './work_dirs/tsn_r50_video_mixup_1x1x8_100e_kinetics400_rgb/' |
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
Oops, something went wrong.