-
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.
[Modelzoo] Add K600, K700 baselines (#259)
- Loading branch information
1 parent
363fe9a
commit 6ec17b8
Showing
8 changed files
with
491 additions
and
8 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
114 changes: 114 additions & 0 deletions
114
configs/recognition/slowonly/slowonly_r50_video_8x8x1_256e_kinetics600_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 @@ | ||
| model = dict( | ||
| type='Recognizer3D', | ||
| backbone=dict( | ||
| type='ResNet3dSlowOnly', | ||
| depth=50, | ||
| pretrained=None, | ||
| lateral=False, | ||
| conv1_kernel=(1, 7, 7), | ||
| conv1_stride_t=1, | ||
| pool1_stride_t=1, | ||
| inflate=(0, 0, 1, 1), | ||
| norm_eval=False), | ||
| cls_head=dict( | ||
| type='I3DHead', | ||
| in_channels=2048, | ||
| num_classes=600, | ||
| spatial_type='avg', | ||
| dropout_ratio=0.5)) | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips='prob') | ||
| dataset_type = 'VideoDataset' | ||
| data_root = 'data/kinetics600/videos_train' | ||
| data_root_val = 'data/kinetics600/videos_val' | ||
| ann_file_train = 'data/kinetics600/kinetics600_train_list_videos.txt' | ||
| ann_file_val = 'data/kinetics600/kinetics600_val_list_videos.txt' | ||
| ann_file_test = 'data/kinetics600/kinetics600_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=8, frame_interval=8, num_clips=1), | ||
| dict(type='DecordDecode'), | ||
| dict(type='RandomResizedCrop'), | ||
| 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='NCTHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=8, | ||
| frame_interval=8, | ||
| num_clips=1, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=8, | ||
| frame_interval=8, | ||
| num_clips=10, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=12, | ||
| 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)) | ||
| # optimizer | ||
| optimizer = dict( | ||
| type='SGD', lr=0.15, momentum=0.9, | ||
| weight_decay=0.0001) # this lr is used for 8 gpus | ||
| optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2)) | ||
| # learning policy | ||
| lr_config = dict(policy='CosineAnnealing', min_lr=0) | ||
| total_epochs = 256 | ||
| checkpoint_config = dict(interval=4) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5)) | ||
| log_config = dict( | ||
| interval=20, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook'), | ||
| ]) | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = './work_dirs/slowonly_r50_video_8x8x1_256e_kinetics600_rgb' | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |
114 changes: 114 additions & 0 deletions
114
configs/recognition/slowonly/slowonly_r50_video_8x8x1_256e_kinetics700_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 @@ | ||
| model = dict( | ||
| type='Recognizer3D', | ||
| backbone=dict( | ||
| type='ResNet3dSlowOnly', | ||
| depth=50, | ||
| pretrained=None, | ||
| lateral=False, | ||
| conv1_kernel=(1, 7, 7), | ||
| conv1_stride_t=1, | ||
| pool1_stride_t=1, | ||
| inflate=(0, 0, 1, 1), | ||
| norm_eval=False), | ||
| cls_head=dict( | ||
| type='I3DHead', | ||
| in_channels=2048, | ||
| num_classes=700, | ||
| spatial_type='avg', | ||
| dropout_ratio=0.5)) | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips='prob') | ||
| dataset_type = 'VideoDataset' | ||
| data_root = 'data/kinetics700/videos_train' | ||
| data_root_val = 'data/kinetics700/videos_val' | ||
| ann_file_train = 'data/kinetics700/kinetics700_train_list_videos.txt' | ||
| ann_file_val = 'data/kinetics700/kinetics700_val_list_videos.txt' | ||
| ann_file_test = 'data/kinetics700/kinetics700_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=8, frame_interval=8, num_clips=1), | ||
| dict(type='DecordDecode'), | ||
| dict(type='RandomResizedCrop'), | ||
| 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='NCTHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=8, | ||
| frame_interval=8, | ||
| num_clips=1, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='DecordInit'), | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=8, | ||
| frame_interval=8, | ||
| num_clips=10, | ||
| test_mode=True), | ||
| dict(type='DecordDecode'), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCTHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=12, | ||
| 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)) | ||
| # optimizer | ||
| optimizer = dict( | ||
| type='SGD', lr=0.15, momentum=0.9, | ||
| weight_decay=0.0001) # this lr is used for 8 gpus | ||
| optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2)) | ||
| # learning policy | ||
| lr_config = dict(policy='CosineAnnealing', min_lr=0) | ||
| total_epochs = 256 | ||
| checkpoint_config = dict(interval=4) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5)) | ||
| log_config = dict( | ||
| interval=20, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook'), | ||
| ]) | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = './work_dirs/slowonly_r50_video_8x8x1_256e_kinetics700_rgb' | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |
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
116 changes: 116 additions & 0 deletions
116
configs/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics600_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 +1,116 @@ | ||
| # 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=600, | ||
| 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 = None | ||
| test_cfg = dict(average_clips=None) | ||
| # dataset settings | ||
| dataset_type = 'VideoDataset' | ||
| data_root = 'data/kinetics600/videos_train' | ||
| data_root_val = 'data/kinetics600/videos_val' | ||
| ann_file_train = 'data/kinetics600/kinetics600_train_list_videos.txt' | ||
| ann_file_val = 'data/kinetics600/kinetics600_val_list_videos.txt' | ||
| ann_file_test = 'data/kinetics600/kinetics600_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='RandomResizedCrop'), | ||
| 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=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']) | ||
| ] | ||
| 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=12, | ||
| 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)) | ||
| # optimizer | ||
| optimizer = dict( | ||
| type='SGD', lr=0.00375, momentum=0.9, | ||
| weight_decay=0.0001) # this lr is used for 8 gpus | ||
| optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2)) | ||
| # learning policy | ||
| lr_config = dict(policy='step', step=[40, 80]) | ||
| total_epochs = 100 | ||
| checkpoint_config = dict(interval=5) | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5)) | ||
| log_config = dict( | ||
| interval=20, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook'), | ||
| ]) | ||
| # runtime settings | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = './work_dirs/tsn_r50_1x1x3_100e_kinetics600_rgb/' | ||
| load_from = None | ||
| resume_from = None | ||
| workflow = [('train', 1)] |
Oops, something went wrong.