Merge branch 'sun_22.10' into 'main'

Sun 22.10

See merge request dcutoolkit/deeplearing/dlexamples_new!54

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/metafile.yml

+Collections:
+- Name: AVA
+  README: configs/detection/ava/README.md
+  Paper:
+    URL: https://arxiv.org/abs/1705.08421
+    Title: "AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions"
+Models:
+- Config: configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 16
+    Epochs: 20
+    Input: 4x16
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 8 GPUs
+  Modality: RGB
+  Name: slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 20.1
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201127.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201127.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201217-40061d5f.pth
+- Config: configs/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 16
+    Epochs: 20
+    Input: 4x16
+    Pretrained: OmniSource
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 8 GPUs
+  Modality: RGB
+  Name: slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 21.8
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb_20201127.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb_20201127.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb_20201217-0c6d2e98.pth
+- Config: configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 12
+    Epochs: 10
+    Input: 4x16
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 8 GPUs
+  Modality: RGB
+  Name: slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 21.75
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/20210316_122517.log.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/20210316_122517.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb_20210316-959829ec.pth
+- Config: configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 6
+    Epochs: 10
+    Input: 8x8
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 16 GPUs
+  Modality: RGB
+  Name: slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 23.79
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/20210316_122517.log.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/20210316_122517.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb_20210316-5742e4dd.pth
+- Config: configs/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet101
+    Batch Size: 6
+    Epochs: 20
+    Input: 8x8
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 16 GPUs
+  Modality: RGB
+  Name: slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 24.6
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb_20201127.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb_20201127.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb_20201217-1c9b4117.pth
+- Config: configs/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet101
+    Batch Size: 6
+    Epochs: 20
+    Input: 8x8
+    Pretrained: OmniSource
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 16 GPUs
+  Modality: RGB
+  Name: slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 25.9
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb_20201127.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb_20201127.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb_20201217-16378594.pth
+- Config: configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 9
+    Epochs: 20
+    Input: 32x2
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 16 GPUs
+  Modality: RGB
+  Name: slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 24.4
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201217.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201217.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201217-6e7c704d.pth
+- Config: configs/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 9
+    Epochs: 20
+    Input: 32x2
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 16 GPUs
+  Modality: RGB
+  Name: slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 25.4
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201222.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201222.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201222-f4d209c9.pth
+- Config: configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 5
+    Epochs: 20
+    Input: 32x2
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.1
+    Training Resources: 16 GPUs
+  Modality: RGB
+  Name: slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 25.5
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb_20201217.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb_20201217.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb_20201217-ae225e97.pth
+- Config: configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 6
+    Epochs: 10
+    Input: 32x2
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.2
+    Training Resources: 8 GPUs
+  Modality: RGB
+  Name: slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb
+  Results:
+  - Dataset: AVA v2.2
+    Metrics:
+      mAP: 26.1
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb-b987b516.pth
+- Config: configs/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 6
+    Epochs: 10
+    Input: 32x2
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.2
+    Training Resources: 8 GPUs
+  Modality: RGB
+  Name: slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb
+  Results:
+  - Dataset: AVA v2.2
+    Metrics:
+      mAP: 26.8
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb-345618cd.pth
+- Config: configs/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py
+  In Collection: AVA
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 6
+    Epochs: 10
+    Input: 32x2
+    Pretrained: Kinetics-400
+    Resolution: short-side 256
+    Training Data: AVA v2.2
+    Training Resources: 8 GPUs
+  Modality: RGB
+  Name: slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb
+  Results:
+  - Dataset: AVA v2.2
+    Metrics:
+      mAP: 26.4
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.log
+  Weights: https://download.openmmlab.com/mmaction/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb-874e0845.pth

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=8,
+        speed_ratio=8,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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,
+            with_global=True),
+        bbox_head=dict(
+            type='BBoxHeadAVA',
+            in_channels=4608,
+            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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=9,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.1125, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowfast/'
+             'slowfast_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=8,
+        speed_ratio=8,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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=2304,
+            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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=9,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.1125, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowfast/'
+             'slowfast_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py

+# custom classes of ava dataset
+# Here we choose classes with AP in range [0.1, 0.3)
+# AP is calculated by **slowonly** ckpt, which is trained by all 80 classes
+custom_classes = [3, 6, 10, 27, 29, 38, 41, 48, 51, 53, 54, 59, 61, 64, 70, 72]
+num_classes = len(custom_classes) + 1
+
+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=8,
+        speed_ratio=8,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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=2304,
+            num_classes=num_classes,
+            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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=9,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        num_classes=num_classes,
+        custom_classes=custom_classes,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        num_classes=num_classes,
+        custom_classes=custom_classes,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.1125, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.05)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowfast/'
+             'slowfast_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=4,
+        speed_ratio=4,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            fusion_kernel=7,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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=2304,
+            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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=5,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.075, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowfast/'
+             'slowfast_r50_8x8x1_256e_kinetics400_rgb/'
+             'slowfast_r50_8x8x1_256e_kinetics400_rgb_20200704-73547d2b.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py

+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=4,
+        speed_ratio=4,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            fusion_kernel=7,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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',
+            dropout_ratio=0.5,
+            in_channels=2304,
+            num_classes=81,
+            multilabel=True)),
+    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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.2.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.2.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.2.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.2.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.2_for_activitynet_2019.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=6,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+# optimizer
+optimizer = dict(type='SGD', lr=0.075, momentum=0.9, weight_decay=0.00001)
+# 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',
+    by_epoch=False,
+    min_lr=0,
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=2,
+    warmup_ratio=0.1)
+total_epochs = 10
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1)
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb'  # noqa: E501
+load_from = 'https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth'  # noqa: E501
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py

+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=4,
+        speed_ratio=4,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            fusion_kernel=7,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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,
+            temporal_pool_mode='max'),
+        bbox_head=dict(
+            type='BBoxHeadAVA',
+            dropout_ratio=0.5,
+            in_channels=2304,
+            focal_alpha=3.0,
+            focal_gamma=1.0,
+            num_classes=81,
+            multilabel=True)),
+    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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.2.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.2.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.2.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.2.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.2_for_activitynet_2019.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=6,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+# optimizer
+optimizer = dict(type='SGD', lr=0.075, momentum=0.9, weight_decay=0.00001)
+# 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',
+    by_epoch=False,
+    min_lr=0,
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=2,
+    warmup_ratio=0.1)
+total_epochs = 10
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1)
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb'  # noqa: E501
+load_from = 'https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth'  # noqa: E501
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py

+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowFast',
+        pretrained=None,
+        resample_rate=4,
+        speed_ratio=4,
+        channel_ratio=8,
+        slow_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=True,
+            fusion_kernel=7,
+            conv1_kernel=(1, 7, 7),
+            dilations=(1, 1, 1, 1),
+            conv1_stride_t=1,
+            pool1_stride_t=1,
+            inflate=(0, 0, 1, 1),
+            spatial_strides=(1, 2, 2, 1)),
+        fast_pathway=dict(
+            type='resnet3d',
+            depth=50,
+            pretrained=None,
+            lateral=False,
+            base_channels=8,
+            conv1_kernel=(5, 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,
+            temporal_pool_mode='max'),
+        bbox_head=dict(
+            type='BBoxHeadAVA',
+            dropout_ratio=0.5,
+            in_channels=2304,
+            num_classes=81,
+            multilabel=True)),
+    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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.2.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.2.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.2.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.2.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.2_for_activitynet_2019.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=32, frame_interval=2),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=32, frame_interval=2, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=6,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+# optimizer
+optimizer = dict(type='SGD', lr=0.075, momentum=0.9, weight_decay=0.00001)
+# 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',
+    by_epoch=False,
+    min_lr=0,
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=2,
+    warmup_ratio=0.1)
+total_epochs = 10
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1)
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb'  # noqa: E501
+load_from = 'https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200716-73547d2b.pth'  # noqa: E501
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=101,
+        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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=8, frame_interval=8),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(type='SampleAVAFrames', clip_len=8, frame_interval=8, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=6,
+    workers_per_gpu=2,
+    # During testing, each video may have different shape
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.075, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'omni/slowonly_r101_without_omni_8x8x1_'
+             'kinetics400_rgb_20200926-0c730aef.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=16,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.2, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py

+# custom classes of ava dataset
+# Here we choose classes with AP in range [0.1, 0.3)
+# AP is calculated by original ckpt, which is trained by all 80 classes
+custom_classes = [3, 6, 10, 27, 29, 38, 41, 48, 51, 53, 54, 59, 61, 64, 70, 72]
+num_classes = len(custom_classes) + 1
+
+# 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=num_classes,
+            multilabel=True,
+            topk=(3, 5),
+            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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=16,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        num_classes=num_classes,
+        custom_classes=custom_classes,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        num_classes=num_classes,
+        custom_classes=custom_classes,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.2, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb.py

+_base_ = ['../_base_/models/slowonly_r50_nl.py']
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=12,
+    workers_per_gpu=2,
+    # During testing, each video may have different shape
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(
+    type='SGD', lr=0.3, momentum=0.9, weight_decay=1e-06, nesterov=True)
+# 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=[4, 6, 8],
+    warmup='linear',
+    warmup_iters=800,
+    warmup_ratio=0.01)
+total_epochs = 10
+
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb')
+load_from = (
+    'https://download.openmmlab.com/mmaction/recognition/slowonly/'
+    'slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb/'
+    'slowonly_nl_embedded_gaussian_r50_4x16x1_150e_kinetics400_rgb_20210308-0d6e5a69.pth'  # noqa: E501
+)
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb.py

+_base_ = ['../_base_/models/slowonly_r50_nl.py']
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=8, frame_interval=8),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(type='SampleAVAFrames', clip_len=8, frame_interval=8, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=6,
+    workers_per_gpu=2,
+    # During testing, each video may have different shape
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(
+    type='SGD', lr=0.15, momentum=0.9, weight_decay=1e-06, nesterov=True)
+# this lr is used for 8x2 gpus
+
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+
+lr_config = dict(
+    policy='step',
+    step=[4, 6, 8],
+    warmup='linear',
+    warmup_iters=1600,
+    warmup_ratio=0.01)
+total_epochs = 10
+
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb')
+load_from = (
+    'https://download.openmmlab.com/mmaction/recognition/slowonly/'
+    'slowonly_nl_embedded_gaussian_r50_8x8x1_150e_kinetics400_rgb/'
+    'slowonly_nl_embedded_gaussian_r50_8x8x1_150e_kinetics400_rgb_20210308-e8dd9e82.pth'  # noqa: E501
+)
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=101,
+        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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=8, frame_interval=8),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(type='SampleAVAFrames', clip_len=8, frame_interval=8, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+data = dict(
+    videos_per_gpu=6,
+    workers_per_gpu=2,
+    # During testing, each video may have different shape
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.075, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'omni/'
+             'slowonly_r101_omni_8x8x1_kinetics400_rgb_20200926-b5dbb701.pth')
+
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb.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)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=16,
+    workers_per_gpu=2,
+    # During testing, each video may have different shape
+    val_dataloader=dict(videos_per_gpu=1),
+    test_dataloader=dict(videos_per_gpu=1),
+    train=dict(
+        type=dataset_type,
+        ann_file=ann_file_train,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+
+optimizer = dict(type='SGD', lr=0.2, momentum=0.9, weight_decay=0.00001)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = ('./work_dirs/ava/'
+            'slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb')
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'omni/'
+             'slowonly_r50_omni_4x16x1_kinetics400_rgb_20200926-51b1f7ea.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/lfb/README.md

+# LFB
+
+[Long-term feature banks for detailed video understanding](https://openaccess.thecvf.com/content_CVPR_2019/html/Wu_Long-Term_Feature_Banks_for_Detailed_Video_Understanding_CVPR_2019_paper.html)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank---supportive information extracted over the entire span of a video---to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/34324155/143016220-21d90fb3-fd9f-499c-820f-f6c421bda7aa.png" width="800"/>
+</div>
+
+## Results and Models
+
+### AVA2.1
+
+|                                                                          Model                                                                          | Modality |  Pretrained  |                                               Backbone                                               | Input | gpus |   Resolution   |  mAP  |                                                                     log                                                                      |                                                                        json                                                                        |                                                                                                    ckpt                                                                                                     |
+| :-----------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :----------: | :--------------------------------------------------------------------------------------------------: | :---: | :--: | :------------: | :---: | :------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|  [lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py](/configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py)  |   RGB    | Kinetics-400 | [slowonly_r50_4x16x1](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | 4x16  |  8   | short-side 256 | 24.11 | [log](https://download.openmmlab.com/mmaction/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210224_125052.log)  | [json](https://download.openmmlab.com/mmaction/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210224_125052.log.json)  |  [ckpt](https://download.openmmlab.com/mmaction/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb_20210224-2ae136d9.pth)  |
+| [lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py](/configs/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py) |   RGB    | Kinetics-400 | [slowonly_r50_4x16x1](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | 4x16  |  8   | short-side 256 | 20.17 | [log](https://download.openmmlab.com/mmaction/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log) | [json](https://download.openmmlab.com/mmaction/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb_20210301-19c330b7.pth) |
+| [lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py](/configs/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py) |   RGB    | Kinetics-400 | [slowonly_r50_4x16x1](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | 4x16  |  8   | short-side 256 | 22.15 | [log](https://download.openmmlab.com/mmaction/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log) | [json](https://download.openmmlab.com/mmaction/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb_20210301-37efcd15.pth) |
+
+:::{note}
+
+1. The **gpus** indicates the number of gpu we used to get the checkpoint.
+   According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
+   e.g., lr=0.01 for 4 GPUs x 2 video/gpu and lr=0.08 for 16 GPUs x 4 video/gpu.
+2. We use `slowonly_r50_4x16x1` instead of `I3D-R50-NL` in the original paper as the backbone of LFB, but we have achieved the similar improvement: (ours: 20.1 -> 24.11 vs. author: 22.1 -> 25.8).
+3. Because the long-term features are randomly sampled in testing, the test accuracy may have some differences.
+4. Before train or test lfb, you need to infer feature bank with the [lfb_slowonly_r50_ava_infer.py](/configs/detection/lfb/lfb_slowonly_r50_ava_infer.py). For more details on infer feature bank, you can refer to [Train](#Train) part.
+5. You can also dowonload long-term feature bank from [AVA_train_val_float32_lfb](https://download.openmmlab.com/mmaction/detection/lfb/AVA_train_val_float32_lfb.rar) or [AVA_train_val_float16_lfb](https://download.openmmlab.com/mmaction/detection/lfb/AVA_train_val_float16_lfb.rar), and then put them on `lfb_prefix_path`.
+6. The ROIHead now supports single-label classification (i.e. the network outputs at most
+   one-label per actor). This can be done by (a) setting multilabel=False during training and
+   the test_cfg.rcnn.action_thr for testing.
+
+:::
+
+## Train
+
+### a. Infer long-term feature bank for training
+
+Before train or test lfb, you need to infer long-term feature bank first.
+
+Specifically, run the test on the training, validation, testing dataset with the config file [lfb_slowonly_r50_ava_infer](/configs/detection/lfb/lfb_slowonly_r50_ava_infer.py) (The config file will only infer the feature bank of training dataset and you need set `dataset_mode = 'val'` to infer the feature bank of validation dataset in the config file.), and the shared head [LFBInferHead](/mmaction/models/heads/lfb_infer_head.py) will generate the feature bank.
+
+A long-term feature bank file of AVA training and validation datasets with float32 precision occupies 3.3 GB. If store the features with float16 precision, the feature bank occupies 1.65 GB.
+
+You can use the following command to infer feature bank of AVA training and validation dataset and the feature bank will be stored in `lfb_prefix_path/lfb_train.pkl` and `lfb_prefix_path/lfb_val.pkl`.
+
+```shell
+# set `dataset_mode = 'train'` in lfb_slowonly_r50_ava_infer.py
+python tools/test.py configs/detection/lfb/lfb_slowonly_r50_ava_infer.py \
+    checkpoints/YOUR_BASELINE_CHECKPOINT.pth --eval mAP
+
+# set `dataset_mode = 'val'` in lfb_slowonly_r50_ava_infer.py
+python tools/test.py configs/detection/lfb/lfb_slowonly_r50_ava_infer.py \
+    checkpoints/YOUR_BASELINE_CHECKPOINT.pth --eval mAP
+```
+
+We use [slowonly_r50_4x16x1 checkpoint](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201217-40061d5f.pth) from [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) to infer feature bank.
+
+### b. Train LFB
+
+You can use the following command to train a model.
+
+```shell
+python tools/train.py ${CONFIG_FILE} [optional arguments]
+```
+
+Example: train LFB model on AVA with half-precision long-term feature bank.
+
+```shell
+python tools/train.py configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py \
+  --validate --seed 0 --deterministic
+```
+
+For more details and optional arguments infos, you can refer to **Training setting** part in [getting_started](/docs/getting_started.md#training-setting).
+
+## Test
+
+### a. Infer long-term feature bank for testing
+
+Before train or test lfb, you also need to infer long-term feature bank first. If you have generated the feature bank file, you can skip it.
+
+The step is the same with **Infer long-term feature bank for training** part in [Train](#Train).
+
+### b. Test LFB
+
+You can use the following command to test a model.
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
+```
+
+Example: test LFB model on AVA with half-precision long-term feature bank and dump the result to a csv file.
+
+```shell
+python tools/test.py configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py \
+    checkpoints/SOME_CHECKPOINT.pth --eval mAP --out results.csv
+```
+
+For more details, you can refer to **Test a dataset** part in [getting_started](/docs/getting_started.md#test-a-dataset).
+
+## Citation
+
+<!-- [DATASET] -->
+
+```BibTeX
+@inproceedings{gu2018ava,
+  title={Ava: A video dataset of spatio-temporally localized atomic visual actions},
+  author={Gu, Chunhui and Sun, Chen and Ross, David A and Vondrick, Carl and Pantofaru, Caroline and Li, Yeqing and Vijayanarasimhan, Sudheendra and Toderici, George and Ricco, Susanna and Sukthankar, Rahul and others},
+  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
+  pages={6047--6056},
+  year={2018}
+}
+```
+
+```BibTeX
+@inproceedings{wu2019long,
+  title={Long-term feature banks for detailed video understanding},
+  author={Wu, Chao-Yuan and Feichtenhofer, Christoph and Fan, Haoqi and He, Kaiming and Krahenbuhl, Philipp and Girshick, Ross},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={284--293},
+  year={2019}
+}
+```

openmmlab_test/mmaction2-0.24.1/configs/detection/lfb/README_zh-CN.md

+# LFB
+
+## 简介
+
+<!-- [ALGORITHM] -->
+
+```BibTeX
+@inproceedings{wu2019long,
+  title={Long-term feature banks for detailed video understanding},
+  author={Wu, Chao-Yuan and Feichtenhofer, Christoph and Fan, Haoqi and He, Kaiming and Krahenbuhl, Philipp and Girshick, Ross},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={284--293},
+  year={2019}
+}
+```
+
+## 模型库
+
+### AVA2.1
+
+|                                                                        配置文件                                                                         | 模态 |    预训练    |                                               主干网络                                               | 输入 | GPU 数量 |  分辨率  | 平均精度 |                                                                     log                                                                      |                                                                        json                                                                        |                                                                                                    ckpt                                                                                                     |
+| :-----------------------------------------------------------------------------------------------------------------------------------------------------: | :--: | :----------: | :--------------------------------------------------------------------------------------------------: | :--: | :------: | :------: | :------: | :------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|  [lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py](/configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py)  | RGB  | Kinetics-400 | [slowonly_r50_4x16x1](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | 4x16 |    8     | 短边 256 |  24.11   | [log](https://download.openmmlab.com/mmaction/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210224_125052.log)  | [json](https://download.openmmlab.com/mmaction/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210224_125052.log.json)  |  [ckpt](https://download.openmmlab.com/mmaction/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb_20210224-2ae136d9.pth)  |
+| [lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py](/configs/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py) | RGB  | Kinetics-400 | [slowonly_r50_4x16x1](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | 4x16 |    8     | 短边 256 |  20.17   | [log](https://download.openmmlab.com/mmaction/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log) | [json](https://download.openmmlab.com/mmaction/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb_20210301-19c330b7.pth) |
+| [lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py](/configs/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py) | RGB  | Kinetics-400 | [slowonly_r50_4x16x1](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | 4x16 |    8     | 短边 256 |  22.15   | [log](https://download.openmmlab.com/mmaction/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log) | [json](https://download.openmmlab.com/mmaction/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/20210301_124812.log.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb_20210301-37efcd15.pth) |
+
+- 注:
+
+1. 这里的 **GPU 数量** 指的是得到模型权重文件对应的 GPU 个数。默认地，MMAction2 所提供的配置文件对应使用 8 块 GPU 进行训练的情况。
+   依据 [线性缩放规则](https://arxiv.org/abs/1706.02677)，当用户使用不同数量的 GPU 或者每块 GPU 处理不同视频个数时，需要根据批大小等比例地调节学习率。
+   如，lr=0.01 对应 4 GPUs x 2 video/gpu，以及 lr=0.08 对应 16 GPUs x 4 video/gpu。
+2. 本 LFB 模型暂没有使用原论文中的 `I3D-R50-NL` 作为主干网络，而是用 `slowonly_r50_4x16x1` 替代，但取得了同样的提升效果：（本模型：20.1 -> 24.11 而原论文模型：22.1 -> 25.8）。
+3. 因为测试时，长时特征是被随机采样的，所以测试精度可能有一些偏差。
+4. 在训练或测试 LFB 之前，用户需要使用配置文件特征库 [lfb_slowonly_r50_ava_infer.py](/configs/detection/lfb/lfb_slowonly_r50_ava_infer.py) 来推导长时特征库。有关推导长时特征库的更多细节，请参照[训练部分](#%E8%AE%AD%E7%BB%83)。
+5. 用户也可以直接从 [AVA_train_val_float32_lfb](https://download.openmmlab.com/mmaction/detection/lfb/AVA_train_val_float32_lfb.rar) 或者 [AVA_train_val_float16_lfb](https://download.openmmlab.com/mmaction/detection/lfb/AVA_train_val_float16_lfb.rar) 下载 float32 或 float16 的长时特征库，并把它们放在 `lfb_prefix_path` 上。
+
+## 训练
+
+### a. 为训练 LFB 推导长时特征库
+
+在训练或测试 LFB 之前，用户首先需要推导长时特征库。
+
+具体来说，使用配置文件 [lfb_slowonly_r50_ava_infer](/configs/detection/lfb/lfb_slowonly_r50_ava_infer.py)，在训练集、验证集、测试集上都运行一次模型测试。
+
+配置文件的默认设置是推导训练集的长时特征库，用户需要将 `dataset_mode` 设置成 `'val'` 来推导验证集的长时特征库，在推导过程中。共享头 [LFBInferHead](/mmaction/models/heads/lfb_infer_head.py) 会生成长时特征库。
+
+AVA 训练集和验证集的 float32 精度的长时特征库文件大约占 3.3 GB。如果以半精度来存储长时特征，文件大约占 1.65 GB。
+
+用户可以使用以下命令来推导 AVA 训练集和验证集的长时特征库，而特征库会被存储为 `lfb_prefix_path/lfb_train.pkl` 和 `lfb_prefix_path/lfb_val.pkl`。
+
+```shell
+# 在 lfb_slowonly_r50_ava_infer.py 中 设置 `dataset_mode = 'train'`
+python tools/test.py configs/detection/lfb/lfb_slowonly_r50_ava_infer.py \
+    checkpoints/YOUR_BASELINE_CHECKPOINT.pth --eval mAP
+
+# 在 lfb_slowonly_r50_ava_infer.py 中 设置 `dataset_mode = 'val'`
+python tools/test.py configs/detection/lfb/lfb_slowonly_r50_ava_infer.py \
+    checkpoints/YOUR_BASELINE_CHECKPOINT.pth --eval mAP
+```
+
+MMAction2 使用来自配置文件 [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) 的模型权重文件 [slowonly_r50_4x16x1 checkpoint](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_20201217-40061d5f.pth)作为推导长时特征库的 LFB 模型的主干网络的预训练模型。
+
+### b. 训练 LFB
+
+用户可以使用以下指令进行模型训练。
+
+```shell
+python tools/train.py ${CONFIG_FILE} [optional arguments]
+```
+
+例如：使用半精度的长时特征库在 AVA 数据集上训练 LFB 模型。
+
+```shell
+python tools/train.py configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py \
+  --validate --seed 0 --deterministic
+```
+
+更多训练细节，可参考 [基础教程](/docs_zh_CN/getting_started.md#%E8%AE%AD%E7%BB%83%E9%85%8D%E7%BD%AE) 中的 **训练配置** 部分。
+
+## 测试
+
+### a. 为测试 LFB 推导长时特征库
+
+在训练或测试 LFB 之前，用户首先需要推导长时特征库。如果用户之前已经生成了特征库文件，可以跳过这一步。
+
+这一步做法与[训练部分](#Train)中的 **为训练 LFB 推导长时特征库** 相同。
+
+### b. 测试 LFB
+
+用户可以使用以下指令进行模型测试。
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
+```
+
+例如：使用半精度的长时特征库在 AVA 数据集上测试 LFB 模型，并将结果导出为一个 json 文件。
+
+```shell
+python tools/test.py configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py \
+    checkpoints/SOME_CHECKPOINT.pth --eval mAP --out results.csv
+```
+
+更多测试细节，可参考 [基础教程](/docs_zh_CN/getting_started.md#%E6%B5%8B%E8%AF%95%E6%9F%90%E4%B8%AA%E6%95%B0%E6%8D%AE%E9%9B%86) 中的 **测试某个数据集** 部分。

openmmlab_test/mmaction2-0.24.1/configs/detection/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py

+_base_ = ['../_base_/models/slowonly_r50.py']
+
+# model settings
+lfb_prefix_path = 'data/ava/lfb_half'
+max_num_sampled_feat = 5
+window_size = 60
+lfb_channels = 2048
+dataset_modes = ('train', 'val')
+
+model = dict(
+    roi_head=dict(
+        shared_head=dict(
+            type='FBOHead',
+            lfb_cfg=dict(
+                lfb_prefix_path=lfb_prefix_path,
+                max_num_sampled_feat=max_num_sampled_feat,
+                window_size=window_size,
+                lfb_channels=lfb_channels,
+                dataset_modes=dataset_modes,
+                device='gpu'),
+            fbo_cfg=dict(type='avg')),
+        bbox_head=dict(in_channels=4096)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids', 'img_key'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape', 'img_key'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=12,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+
+optimizer = dict(type='SGD', lr=0.15, momentum=0.9, weight_decay=1e-05)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/lfb/lfb_avg_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb'  # noqa E501
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py

+_base_ = ['../_base_/models/slowonly_r50.py']
+
+# model settings
+lfb_prefix_path = 'data/ava/lfb_half'
+max_num_sampled_feat = 5
+window_size = 60
+lfb_channels = 2048
+dataset_modes = ('train', 'val')
+
+model = dict(
+    roi_head=dict(
+        shared_head=dict(
+            type='FBOHead',
+            lfb_cfg=dict(
+                lfb_prefix_path=lfb_prefix_path,
+                max_num_sampled_feat=max_num_sampled_feat,
+                window_size=window_size,
+                lfb_channels=lfb_channels,
+                dataset_modes=dataset_modes,
+                device='gpu'),
+            fbo_cfg=dict(type='max')),
+        bbox_head=dict(in_channels=4096)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids', 'img_key'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape', 'img_key'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=12,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+
+optimizer = dict(type='SGD', lr=0.15, momentum=0.9, weight_decay=1e-05)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/lfb/lfb_max_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb'  # noqa E501
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth')
+resume_from = None
+find_unused_parameters = False

openmmlab_test/mmaction2-0.24.1/configs/detection/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb.py

+_base_ = ['../_base_/models/slowonly_r50.py']
+
+# model settings
+lfb_prefix_path = 'data/ava/lfb_half'
+max_num_sampled_feat = 5
+window_size = 60
+lfb_channels = 2048
+dataset_modes = ('train', 'val')
+
+model = dict(
+    roi_head=dict(
+        shared_head=dict(
+            type='FBOHead',
+            lfb_cfg=dict(
+                lfb_prefix_path=lfb_prefix_path,
+                max_num_sampled_feat=max_num_sampled_feat,
+                window_size=window_size,
+                lfb_channels=lfb_channels,
+                dataset_modes=dataset_modes,
+                device='gpu'),
+            fbo_cfg=dict(
+                type='non_local',
+                st_feat_channels=2048,
+                lt_feat_channels=lfb_channels,
+                latent_channels=512,
+                num_st_feat=1,
+                num_lt_feat=window_size * max_num_sampled_feat,
+                num_non_local_layers=2,
+                st_feat_dropout_ratio=0.2,
+                lt_feat_dropout_ratio=0.2,
+                pre_activate=True)),
+        bbox_head=dict(in_channels=2560)))
+
+dataset_type = 'AVADataset'
+data_root = 'data/ava/rawframes'
+anno_root = 'data/ava/annotations'
+
+ann_file_train = f'{anno_root}/ava_train_v2.1.csv'
+ann_file_val = f'{anno_root}/ava_val_v2.1.csv'
+
+exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv'
+exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv'
+
+label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt'
+
+proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.'
+                       'recall_93.9.pkl')
+proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl'
+
+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='SampleAVAFrames', clip_len=4, frame_interval=16),
+    dict(type='RawFrameDecode'),
+    dict(type='RandomRescale', scale_range=(256, 320)),
+    dict(type='RandomCrop', size=256),
+    dict(type='Flip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']),
+    dict(
+        type='ToDataContainer',
+        fields=[
+            dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False)
+        ]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'],
+        meta_keys=['scores', 'entity_ids', 'img_key'])
+]
+# The testing is w/o. any cropping / flipping
+val_pipeline = [
+    dict(
+        type='SampleAVAFrames', clip_len=4, frame_interval=16, test_mode=True),
+    dict(type='RawFrameDecode'),
+    dict(type='Resize', scale=(-1, 256)),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='FormatShape', input_format='NCTHW', collapse=True),
+    # Rename is needed to use mmdet detectors
+    dict(type='Rename', mapping=dict(imgs='img')),
+    dict(type='ToTensor', keys=['img', 'proposals']),
+    dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]),
+    dict(
+        type='Collect',
+        keys=['img', 'proposals'],
+        meta_keys=['scores', 'img_shape', 'img_key'],
+        nested=True)
+]
+
+data = dict(
+    videos_per_gpu=12,
+    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,
+        exclude_file=exclude_file_train,
+        pipeline=train_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_train,
+        person_det_score_thr=0.9,
+        data_prefix=data_root),
+    val=dict(
+        type=dataset_type,
+        ann_file=ann_file_val,
+        exclude_file=exclude_file_val,
+        pipeline=val_pipeline,
+        label_file=label_file,
+        proposal_file=proposal_file_val,
+        person_det_score_thr=0.9,
+        data_prefix=data_root))
+data['test'] = data['val']
+evaluation = dict(interval=1, save_best='mAP@0.5IOU')
+
+optimizer = dict(type='SGD', lr=0.15, momentum=0.9, weight_decay=1e-05)
+# 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=[10, 15],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=5,
+    warmup_ratio=0.1)
+total_epochs = 20
+
+checkpoint_config = dict(interval=1)
+workflow = [('train', 1)]
+log_config = dict(
+    interval=20, hooks=[
+        dict(type='TextLoggerHook'),
+    ])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/lfb/lfb_nl_kinetics_pretrained_slowonly_r50_4x16x1_20e_ava_rgb'  # noqa E501
+load_from = ('https://download.openmmlab.com/mmaction/recognition/slowonly/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb/'
+             'slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth')
+resume_from = None
+find_unused_parameters = False