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