Initial add code.

configs/_base_/models/tanet_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='TANet',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        num_segments=8,
+        tam_cfg=dict()),
+    cls_head=dict(
+        type='TSMHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.001),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tin_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNetTIN',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False,
+        shift_div=4),
+    cls_head=dict(
+        type='TSMHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.001,
+        is_shift=False),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips=None))

configs/_base_/models/tpn_slowonly_r50.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained='torchvision://resnet50',
+        lateral=False,
+        out_indices=(2, 3),
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        inflate=(0, 0, 1, 1),
+        norm_eval=False),
+    neck=dict(
+        type='TPN',
+        in_channels=(1024, 2048),
+        out_channels=1024,
+        spatial_modulation_cfg=dict(
+            in_channels=(1024, 2048), out_channels=2048),
+        temporal_modulation_cfg=dict(downsample_scales=(8, 8)),
+        upsample_cfg=dict(scale_factor=(1, 1, 1)),
+        downsample_cfg=dict(downsample_scale=(1, 1, 1)),
+        level_fusion_cfg=dict(
+            in_channels=(1024, 1024),
+            mid_channels=(1024, 1024),
+            out_channels=2048,
+            downsample_scales=((1, 1, 1), (1, 1, 1))),
+        aux_head_cfg=dict(out_channels=400, loss_weight=0.5)),
+    cls_head=dict(
+        type='TPNHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tpn_tsm_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNetTSM',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        out_indices=(2, 3),
+        norm_eval=False,
+        shift_div=8),
+    neck=dict(
+        type='TPN',
+        in_channels=(1024, 2048),
+        out_channels=1024,
+        spatial_modulation_cfg=dict(
+            in_channels=(1024, 2048), out_channels=2048),
+        temporal_modulation_cfg=dict(downsample_scales=(8, 8)),
+        upsample_cfg=dict(scale_factor=(1, 1, 1)),
+        downsample_cfg=dict(downsample_scale=(1, 1, 1)),
+        level_fusion_cfg=dict(
+            in_channels=(1024, 1024),
+            mid_channels=(1024, 1024),
+            out_channels=2048,
+            downsample_scales=((1, 1, 1), (1, 1, 1))),
+        aux_head_cfg=dict(out_channels=174, loss_weight=0.5)),
+    cls_head=dict(
+        type='TPNHead',
+        num_classes=174,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob', fcn_test=True))

configs/_base_/models/trn_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNet',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False,
+        partial_bn=True),
+    cls_head=dict(
+        type='TRNHead',
+        num_classes=400,
+        in_channels=2048,
+        num_segments=8,
+        spatial_type='avg',
+        relation_type='TRNMultiScale',
+        hidden_dim=256,
+        dropout_ratio=0.8,
+        init_std=0.001),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tsm_mobilenet_v2.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='MobileNetV2TSM',
+        shift_div=8,
+        num_segments=8,
+        is_shift=True,
+        pretrained='mmcls://mobilenet_v2'),
+    cls_head=dict(
+        type='TSMHead',
+        num_segments=8,
+        num_classes=400,
+        in_channels=1280,
+        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=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tsm_r50.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=400,
+        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=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/tsn_r50.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=None,
+    test_cfg=dict(average_clips=None))

configs/_base_/models/tsn_r50_audio.py

+# model settings
+model = dict(
+    type='AudioRecognizer',
+    backbone=dict(type='ResNet', depth=50, in_channels=1, norm_eval=False),
+    cls_head=dict(
+        type='AudioTSNHead',
+        num_classes=400,
+        in_channels=2048,
+        dropout_ratio=0.5,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/models/x3d.py

+# model settings
+model = dict(
+    type='Recognizer3D',
+    backbone=dict(type='X3D', gamma_w=1, gamma_b=2.25, gamma_d=2.2),
+    cls_head=dict(
+        type='X3DHead',
+        in_channels=432,
+        num_classes=400,
+        spatial_type='avg',
+        dropout_ratio=0.5,
+        fc1_bias=False),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips='prob'))

configs/_base_/schedules/adam_20e.py

+# optimizer
+optimizer = dict(
+    type='Adam', lr=0.01, weight_decay=0.00001)  # this lr is used for 1 gpus
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(policy='step', step=10)
+total_epochs = 20

configs/_base_/schedules/sgd_100e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+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

configs/_base_/schedules/sgd_150e_warmup.py

+# optimizer
+optimizer = dict(
+    type='SGD', lr=0.01, 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=[90, 130],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=10)
+total_epochs = 150

configs/_base_/schedules/sgd_50e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[20, 40])
+total_epochs = 50

configs/_base_/schedules/sgd_tsm_100e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+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

configs/_base_/schedules/sgd_tsm_50e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+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

configs/_base_/schedules/sgd_tsm_mobilenet_v2_100e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.00002)
+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

configs/_base_/schedules/sgd_tsm_mobilenet_v2_50e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.00002)
+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

configs/detection/_base_/models/slowonly_r50.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained=None,
+        pretrained2d=False,
+        lateral=False,
+        num_stages=4,
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        spatial_strides=(1, 2, 2, 1)),
+    roi_head=dict(
+        type='AVARoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor3D',
+            roi_layer_type='RoIAlign',
+            output_size=8,
+            with_temporal_pool=True),
+        bbox_head=dict(
+            type='BBoxHeadAVA',
+            in_channels=2048,
+            num_classes=81,
+            multilabel=True,
+            dropout_ratio=0.5)),
+    train_cfg=dict(
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssignerAVA',
+                pos_iou_thr=0.9,
+                neg_iou_thr=0.9,
+                min_pos_iou=0.9),
+            sampler=dict(
+                type='RandomSampler',
+                num=32,
+                pos_fraction=1,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=1.0,
+            debug=False)),
+    test_cfg=dict(rcnn=dict(action_thr=0.002)))

configs/detection/_base_/models/slowonly_r50_nl.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained=None,
+        pretrained2d=False,
+        lateral=False,
+        num_stages=4,
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        spatial_strides=(1, 2, 2, 1),
+        norm_cfg=dict(type='BN3d', requires_grad=True),
+        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=True,
+            norm_cfg=dict(type='BN3d', requires_grad=True),
+            mode='embedded_gaussian')),
+    roi_head=dict(
+        type='AVARoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor3D',
+            roi_layer_type='RoIAlign',
+            output_size=8,
+            with_temporal_pool=True),
+        bbox_head=dict(
+            type='BBoxHeadAVA',
+            in_channels=2048,
+            num_classes=81,
+            multilabel=True,
+            dropout_ratio=0.5)),
+    train_cfg=dict(
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssignerAVA',
+                pos_iou_thr=0.9,
+                neg_iou_thr=0.9,
+                min_pos_iou=0.9),
+            sampler=dict(
+                type='RandomSampler',
+                num=32,
+                pos_fraction=1,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=1.0,
+            debug=False)),
+    test_cfg=dict(rcnn=dict(action_thr=0.002)))