-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
31 changed files
with
1,469 additions
and
739 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
138 changes: 138 additions & 0 deletions
138
...tion/slowonly/slowonly_imagenet-pretrained-r50_32xb8-8x8x1-steplr-150e_kinetics710-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 +1,138 @@ | ||
| _base_ = [('slowonly_imagenet-pretrained-r50_16xb16-' | ||
| '4x16x1-steplr-150e_kinetics700-rgb.py')] | ||
|
|
||
| model = dict(cls_head=dict(num_classes=710)) | ||
|
|
||
| file_client_args = dict(io_backend='disk') | ||
|
|
||
| train_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict(type='SampleFrames', clip_len=8, frame_interval=8, num_clips=1), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='RandomResizedCrop'), | ||
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
|
|
||
| val_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=8, | ||
| frame_interval=8, | ||
| num_clips=1, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
|
|
||
| test_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=8, | ||
| frame_interval=8, | ||
| num_clips=10, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
|
|
||
| k400_data_root = 'data/kinetics400/videos_train' | ||
| k600_data_root = 'data/kinetics600/videos' | ||
| k700_data_root = 'data/kinetics700/videos' | ||
| k400_data_root_val = 'data/kinetics400/videos_val' | ||
| k600_data_root_val = k600_data_root | ||
| k700_data_root_val = k700_data_root | ||
|
|
||
| k400_ann_file_train = 'data/kinetics710/k400_train_list_videos.txt' | ||
| k600_ann_file_train = 'data/kinetics710/k600_train_list_videos.txt' | ||
| k700_ann_file_train = 'data/kinetics710/k700_train_list_videos.txt' | ||
|
|
||
| k400_ann_file_val = 'data/kinetics710/k400_val_list_videos.txt' | ||
| k600_ann_file_val = 'data/kinetics710/k600_val_list_videos.txt' | ||
| k700_ann_file_val = 'data/kinetics710/k700_val_list_videos.txt' | ||
|
|
||
| k400_trainset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k400_ann_file_train, | ||
| data_prefix=dict(video=k400_data_root), | ||
| pipeline=train_pipeline) | ||
| k600_trainset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k600_ann_file_train, | ||
| data_prefix=dict(video=k600_data_root), | ||
| pipeline=train_pipeline) | ||
| k700_trainset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k700_ann_file_train, | ||
| data_prefix=dict(video=k700_data_root), | ||
| pipeline=train_pipeline) | ||
|
|
||
| k400_valset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k400_ann_file_val, | ||
| data_prefix=dict(video=k400_data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True) | ||
| k600_valset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k600_ann_file_val, | ||
| data_prefix=dict(video=k600_data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True) | ||
| k700_valset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k700_ann_file_val, | ||
| data_prefix=dict(video=k700_data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True) | ||
|
|
||
| k400_testset = k400_valset.copy() | ||
| k600_testset = k600_valset.copy() | ||
| k700_testset = k700_valset.copy() | ||
| k400_testset['pipeline'] = test_pipeline | ||
| k600_testset['pipeline'] = test_pipeline | ||
| k700_testset['pipeline'] = test_pipeline | ||
|
|
||
| k710_trainset = dict( | ||
| type='ConcatDataset', | ||
| datasets=[k400_trainset, k600_trainset, k700_trainset], | ||
| _delete_=True) | ||
| k710_valset = dict( | ||
| type='ConcatDataset', | ||
| datasets=[k400_valset, k600_valset, k700_valset], | ||
| _delete_=True) | ||
| k710_testset = dict( | ||
| type='ConcatDataset', | ||
| datasets=[k400_testset, k600_testset, k700_testset], | ||
| _delete_=True, | ||
| ) | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=8, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=k710_trainset) | ||
| val_dataloader = dict( | ||
| batch_size=8, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=k710_valset) | ||
| test_dataloader = dict( | ||
| batch_size=1, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=k710_testset) |
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
144 changes: 144 additions & 0 deletions
144
...gs/recognition/swin/swin-small-p244-w877_in1k-pre_32xb4-amp-32x2x1-30e_kinetics710-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 +1,144 @@ | ||
| _base_ = [ | ||
| 'swin-small-p244-w877_in1k-pre_8xb8-amp-32x2x1-30e_kinetics400-rgb.py' | ||
| ] | ||
|
|
||
| model = dict(cls_head=dict(num_classes=710)) | ||
|
|
||
| file_client_args = dict(io_backend='disk') | ||
| train_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='RandomResizedCrop'), | ||
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
| val_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=32, | ||
| frame_interval=2, | ||
| num_clips=1, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='DecordInit', **file_client_args), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=32, | ||
| frame_interval=2, | ||
| num_clips=4, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='Resize', scale=(-1, 224)), | ||
| dict(type='ThreeCrop', crop_size=224), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='PackActionInputs') | ||
| ] | ||
|
|
||
| k400_data_root = 'data/kinetics400/videos_train' | ||
| k600_data_root = 'data/kinetics600/videos' | ||
| k700_data_root = 'data/kinetics700/videos' | ||
| k400_data_root_val = 'data/kinetics400/videos_val' | ||
| k600_data_root_val = k600_data_root | ||
| k700_data_root_val = k700_data_root | ||
|
|
||
| k400_ann_file_train = 'data/kinetics710/k400_train_list_videos.txt' | ||
| k600_ann_file_train = 'data/kinetics710/k600_train_list_videos.txt' | ||
| k700_ann_file_train = 'data/kinetics710/k700_train_list_videos.txt' | ||
|
|
||
| k400_ann_file_val = 'data/kinetics710/k400_val_list_videos.txt' | ||
| k600_ann_file_val = 'data/kinetics710/k600_val_list_videos.txt' | ||
| k700_ann_file_val = 'data/kinetics710/k700_val_list_videos.txt' | ||
|
|
||
| k400_trainset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k400_ann_file_train, | ||
| data_prefix=dict(video=k400_data_root), | ||
| pipeline=train_pipeline) | ||
| k600_trainset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k600_ann_file_train, | ||
| data_prefix=dict(video=k600_data_root), | ||
| pipeline=train_pipeline) | ||
| k700_trainset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k700_ann_file_train, | ||
| data_prefix=dict(video=k700_data_root), | ||
| pipeline=train_pipeline) | ||
|
|
||
| k400_valset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k400_ann_file_val, | ||
| data_prefix=dict(video=k400_data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True) | ||
| k600_valset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k600_ann_file_val, | ||
| data_prefix=dict(video=k600_data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True) | ||
| k700_valset = dict( | ||
| type='VideoDataset', | ||
| ann_file=k700_ann_file_val, | ||
| data_prefix=dict(video=k700_data_root_val), | ||
| pipeline=val_pipeline, | ||
| test_mode=True) | ||
|
|
||
| k400_testset = k400_valset.copy() | ||
| k600_testset = k600_valset.copy() | ||
| k700_testset = k700_valset.copy() | ||
| k400_testset['pipeline'] = test_pipeline | ||
| k600_testset['pipeline'] = test_pipeline | ||
| k700_testset['pipeline'] = test_pipeline | ||
|
|
||
| k710_trainset = dict( | ||
| type='ConcatDataset', | ||
| datasets=[k400_trainset, k600_trainset, k700_trainset], | ||
| _delete_=True) | ||
| k710_valset = dict( | ||
| type='ConcatDataset', | ||
| datasets=[k400_valset, k600_valset, k700_valset], | ||
| _delete_=True) | ||
| k710_testset = dict( | ||
| type='ConcatDataset', | ||
| datasets=[k400_testset, k600_testset, k700_testset], | ||
| _delete_=True, | ||
| ) | ||
|
|
||
| train_dataloader = dict( | ||
| batch_size=4, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=True), | ||
| dataset=k710_trainset) | ||
| val_dataloader = dict( | ||
| batch_size=4, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=k710_valset) | ||
| test_dataloader = dict( | ||
| batch_size=1, | ||
| num_workers=8, | ||
| persistent_workers=True, | ||
| sampler=dict(type='DefaultSampler', shuffle=False), | ||
| dataset=k710_testset) | ||
|
|
||
| optim_wrapper = dict(optimizer=dict(lr=2e-3)) | ||
|
|
||
| # Default setting for scaling LR automatically | ||
| # - `enable` means enable scaling LR automatically | ||
| # or not by default. | ||
| # - `base_batch_size` = (16 GPUs) x (8 samples per GPU). | ||
| auto_scale_lr = dict(enable=False, base_batch_size=128) |
Oops, something went wrong.