add model TSM

configs/recognition/tsm/tsm_nl_gaussian_r50_1x1x8_50e_kinetics400_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    backbone=dict(
+        non_local=((0, 0, 0), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 0, 0)),
+        non_local_cfg=dict(
+            sub_sample=True,
+            use_scale=False,
+            norm_cfg=dict(type='BN3d', requires_grad=True),
+            mode='gaussian')))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_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='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='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,
+        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'])
+]
+data = dict(
+    videos_per_gpu=8,
+    workers_per_gpu=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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/tsm_nl_gaussian_r50_1x1x8_50e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv1_rgb.py

+_base_ = ['./tsm_r50_1x1x8_50e_sthv1_rgb.py']
+
+# model settings
+model = dict(backbone=dict(pretrained='torchvision://resnet101', depth=101))
+
+# runtime settings
+work_dir = './work_dirs/tsm_r101_1x1x8_50e_sthv1_rgb/'

configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb.py

+_base_ = ['./tsm_r50_1x1x8_50e_sthv2_rgb.py']
+
+# model settings
+model = dict(backbone=dict(pretrained='torchvision://resnet101', depth=101))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/sthv2/rawframes'
+data_root_val = 'data/sthv2/rawframes'
+ann_file_train = 'data/sthv2/sthv2_train_list_rawframes.txt'
+ann_file_val = 'data/sthv2/sthv2_val_list_rawframes.txt'
+ann_file_test = 'data/sthv2/sthv2_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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+
+# optimizer
+optimizer = dict(
+    lr=0.01,  # this lr is used for 8 gpus
+)
+# runtime settings
+work_dir = './work_dirs/tsm_r101_1x1x8_50e_sthv2_rgb/'

configs/recognition/tsm/tsm_r50_1x1x16_100e_kinetics400_rgb.py

+_base_ = ['tsm_r50_1x1x16_50e_kinetics400_rgb.py']
+
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100
+work_dir = './work_dirs/tsm_r50_1x1x16_100e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(backbone=dict(num_segments=16), cls_head=dict(num_segments=16))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_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=16),
+    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='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='SampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=16,
+        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=16,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='TenCrop', 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'])
+]
+data = dict(
+    videos_per_gpu=6,
+    workers_per_gpu=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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'])
+
+# optimizer
+optimizer = dict(
+    lr=0.0075,  # this lr is used for 8 gpus
+)
+
+# runtime settings
+checkpoint_config = dict(interval=5)
+work_dir = './work_dirs/tsm_r50_1x1x16_50e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv1_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    backbone=dict(num_segments=16),
+    cls_head=dict(num_classes=174, num_segments=16))
+
+# 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=16),
+    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=16,
+        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=16,
+        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=6,
+    workers_per_gpu=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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(
+    lr=0.0075,  # this lr is used for 8 gpus
+    weight_decay=0.0005)
+
+# runtime settings
+work_dir = './work_dirs/tsm_r50_1x1x16_50e_sthv1_rgb/'

configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    backbone=dict(num_segments=16),
+    cls_head=dict(num_classes=174, num_segments=16))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/sthv2/rawframes'
+data_root_val = 'data/sthv2/rawframes'
+ann_file_train = 'data/sthv2/sthv2_train_list_rawframes.txt'
+ann_file_val = 'data/sthv2/sthv2_val_list_rawframes.txt'
+ann_file_test = 'data/sthv2/sthv2_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=16),
+    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=16,
+        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=16,
+        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=6,
+    workers_per_gpu=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+
+# optimizer
+optimizer = dict(
+    lr=0.0075,  # this lr is used for 8 gpus
+    weight_decay=0.0005)
+
+# runtime settings
+work_dir = './work_dirs/tsm_r50_1x1x16_50e_sthv2_rgb/'

configs/recognition/tsm/tsm_r50_1x1x8_100e_kinetics400_rgb.py

+_base_ = ['./tsm_r50_1x1x8_50e_kinetics400_rgb.py']
+
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100
+work_dir = './work_dirs/tsm_r50_1x1x8_100e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_1x1x8_50e_jester_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=27))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/jester/rawframes'
+data_root_val = 'data/jester/rawframes'
+ann_file_train = 'data/jester/jester_train_list_rawframes.txt'
+ann_file_val = 'data/jester/jester_val_list_rawframes.txt'
+ann_file_test = 'data/jester/jester_val_list_rawframes.txt'
+jester_flip_label_map = {0: 1, 1: 0, 6: 7, 7: 6}
+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='RandomResizedCrop'),
+    dict(type='Resize', scale=(224, 224), keep_ratio=False),
+    dict(type='Flip', flip_ratio=0.5, flip_label_map=jester_flip_label_map),
+    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=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'])
+]
+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=2,
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    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_1x1x8_50e_jester_rgb/'

configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_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='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='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,
+        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'])
+]
+data = dict(
+    videos_per_gpu=8,
+    workers_per_gpu=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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
+checkpoint_config = dict(interval=5)
+work_dir = './work_dirs/tsm_r50_1x1x8_100e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=174))
+
+# 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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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_1x1x8_50e_sthv1_rgb/'

configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv2_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=174))
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/sthv2/rawframes'
+data_root_val = 'data/sthv2/rawframes'
+ann_file_train = 'data/sthv2/sthv2_train_list_rawframes.txt'
+ann_file_val = 'data/sthv2/sthv2_val_list_rawframes.txt'
+ann_file_test = 'data/sthv2/sthv2_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=6,
+    workers_per_gpu=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+
+# optimizer
+optimizer = dict(
+    lr=0.0075,  # this lr is used for 8 gpus
+    weight_decay=0.0005)
+
+# runtime settings
+work_dir = './work_dirs/tsm_r50_1x1x8_50e_sthv2_rgb/'

configs/recognition/tsm/tsm_r50_cutmix_1x1x8_50e_sthv1_rgb.py

+_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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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/'

configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_100e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_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='DenseSampleFrames', 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='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='DenseSampleFrames',
+        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='DenseSampleFrames',
+        clip_len=1,
+        frame_interval=1,
+        num_clips=8,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='TenCrop', 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'])
+]
+data = dict(
+    videos_per_gpu=8,
+    workers_per_gpu=2,
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    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=2, metrics=['top_k_accuracy', 'mean_class_accuracy'])
+
+# runtime settings
+work_dir = './work_dirs/tsm_r50_dense_1x1x8_100e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_dense_1x1x8_50e_kinetics400_rgb.py

+_base_ = ['tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py']
+
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[20, 40])
+total_epochs = 50
+work_dir = './work_dirs/tsm_r50_dense_1x1x8_50e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_flip_1x1x8_50e_sthv1_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=174))
+
+# 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'
+
+sthv1_flip_label_map = {2: 4, 4: 2, 30: 41, 41: 30, 52: 66, 66: 52}
+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='Flip', flip_ratio=0.5, flip_label_map=sthv1_flip_label_map),
+    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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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_flip_1x1x8_50e_sthv1_rgb/'

configs/recognition/tsm/tsm_r50_flip_randaugment_1x1x8_50e_sthv1_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=174))
+
+# 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'
+
+sthv1_flip_label_map = {2: 4, 4: 2, 30: 41, 41: 30, 52: 66, 66: 52}
+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='Flip', flip_ratio=0.5, flip_label_map=sthv1_flip_label_map),
+    dict(type='Imgaug', transforms='default'),
+    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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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_flip_randaugment_1x1x8_50e_sthv1_rgb/'

configs/recognition/tsm/tsm_r50_gpu_normalize_1x1x8_50e_kinetics400_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+module_hooks = [
+    dict(
+        type='GPUNormalize',
+        hooked_module='backbone',
+        hook_pos='forward_pre',
+        input_format='NCHW',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375])
+]
+
+# dataset settings
+dataset_type = 'RawframeDataset'
+data_root = 'data/kinetics400/rawframes_train'
+data_root_val = 'data/kinetics400/rawframes_val'
+ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt'
+ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt'
+
+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='Flip', flip_ratio=0.5),
+    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='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,
+        test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='CenterCrop', crop_size=224),
+    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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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
+checkpoint_config = dict(interval=5)
+work_dir = './work_dirs/tsm_r50_gpu_normalize_1x1x8_100e_kinetics400_rgb/'

configs/recognition/tsm/tsm_r50_mixup_1x1x8_50e_sthv1_rgb.py

+_base_ = [
+    '../../_base_/schedules/sgd_tsm_50e.py', '../../_base_/default_runtime.py'
+]
+
+# 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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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/'

configs/recognition/tsm/tsm_r50_ptv_augmix_1x1x8_50e_sthv1_rgb.py

+_base_ = [
+    '../../_base_/models/tsm_r50.py', '../../_base_/schedules/sgd_tsm_50e.py',
+    '../../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(cls_head=dict(num_classes=174))
+
+# 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='pytorchvideo.AugMix'),
+    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=2,
+    test_dataloader=dict(videos_per_gpu=1),
+    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_ptv_augmix_1x1x8_50e_sthv1_rgb/'