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/_base_/models/tsn_r50.py

+# model settings
+model = dict(
+    type='Recognizer2D',
+    backbone=dict(
+        type='ResNet',
+        pretrained='torchvision://resnet50',
+        depth=50,
+        norm_eval=False),
+    cls_head=dict(
+        type='TSNHead',
+        num_classes=400,
+        in_channels=2048,
+        spatial_type='avg',
+        consensus=dict(type='AvgConsensus', dim=1),
+        dropout_ratio=0.4,
+        init_std=0.01),
+    # model training and testing settings
+    train_cfg=None,
+    test_cfg=dict(average_clips=None))

openmmlab_test/mmaction2-0.24.1/configs/_base_/models/tsn_r50_audio.py

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

openmmlab_test/mmaction2-0.24.1/configs/_base_/models/x3d.py

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

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/adam_20e.py

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

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_100e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_150e_warmup.py

+# optimizer
+optimizer = dict(
+    type='SGD', lr=0.01, momentum=0.9,
+    weight_decay=0.0001)  # this lr is used for 8 gpus
+optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
+# learning policy
+lr_config = dict(
+    policy='step',
+    step=[90, 130],
+    warmup='linear',
+    warmup_by_epoch=True,
+    warmup_iters=10)
+total_epochs = 150

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_50e.py

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

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_tsm_100e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_tsm_50e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[20, 40])
+total_epochs = 50

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_tsm_mobilenet_v2_100e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.00002)
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[40, 80])
+total_epochs = 100

openmmlab_test/mmaction2-0.24.1/configs/_base_/schedules/sgd_tsm_mobilenet_v2_50e.py

+# optimizer
+optimizer = dict(
+    type='SGD',
+    constructor='TSMOptimizerConstructor',
+    paramwise_cfg=dict(fc_lr5=True),
+    lr=0.01,  # this lr is used for 8 gpus
+    momentum=0.9,
+    weight_decay=0.00002)
+optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2))
+# learning policy
+lr_config = dict(policy='step', step=[20, 40])
+total_epochs = 50

openmmlab_test/mmaction2-0.24.1/configs/detection/_base_/models/slowonly_r50.py

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

openmmlab_test/mmaction2-0.24.1/configs/detection/_base_/models/slowonly_r50_nl.py

+# model setting
+model = dict(
+    type='FastRCNN',
+    backbone=dict(
+        type='ResNet3dSlowOnly',
+        depth=50,
+        pretrained=None,
+        pretrained2d=False,
+        lateral=False,
+        num_stages=4,
+        conv1_kernel=(1, 7, 7),
+        conv1_stride_t=1,
+        pool1_stride_t=1,
+        spatial_strides=(1, 2, 2, 1),
+        norm_cfg=dict(type='BN3d', requires_grad=True),
+        non_local=((0, 0, 0), (1, 0, 1, 0), (1, 0, 1, 0, 1, 0), (0, 0, 0)),
+        non_local_cfg=dict(
+            sub_sample=True,
+            use_scale=True,
+            norm_cfg=dict(type='BN3d', requires_grad=True),
+            mode='embedded_gaussian')),
+    roi_head=dict(
+        type='AVARoIHead',
+        bbox_roi_extractor=dict(
+            type='SingleRoIExtractor3D',
+            roi_layer_type='RoIAlign',
+            output_size=8,
+            with_temporal_pool=True),
+        bbox_head=dict(
+            type='BBoxHeadAVA',
+            in_channels=2048,
+            num_classes=81,
+            multilabel=True,
+            dropout_ratio=0.5)),
+    train_cfg=dict(
+        rcnn=dict(
+            assigner=dict(
+                type='MaxIoUAssignerAVA',
+                pos_iou_thr=0.9,
+                neg_iou_thr=0.9,
+                min_pos_iou=0.9),
+            sampler=dict(
+                type='RandomSampler',
+                num=32,
+                pos_fraction=1,
+                neg_pos_ub=-1,
+                add_gt_as_proposals=True),
+            pos_weight=1.0,
+            debug=False)),
+    test_cfg=dict(rcnn=dict(action_thr=0.002)))

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

+# ACRN
+
+[Actor-centric relation network](https://openaccess.thecvf.com/content_ECCV_2018/html/Chen_Sun_Actor-centric_Relation_Network_ECCV_2018_paper.html)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level and model temporal context with 3D ConvNets. Here, we go one step further and model spatio-temporal relations to capture the interactions between human actors, relevant objects and scene elements essential to differentiate similar human actions. Our approach is weakly supervised and mines the relevant elements automatically with an actor-centric relational network (ACRN). ACRN computes and accumulates pair-wise relation information from actor and global scene features, and generates relation features for action classification. It is implemented as neural networks and can be trained jointly with an existing action detection system. We show that ACRN outperforms alternative approaches which capture relation information, and that the proposed framework improves upon the state-of-the-art performance on JHMDB and AVA. A visualization of the learned relation features confirms that our approach is able to attend to the relevant relations for each action.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/34324155/142996406-09ac1b09-2a9e-478c-9035-5fe7a80bc80b.png" width="800"/>
+</div>
+
+## Results and Models
+
+### AVA2.1
+
+|                                                                            Model                                                                            | Modality |  Pretrained  | Backbone | Input | gpus | mAP  |                                                                                               log                                                                                               |                                                                                               json                                                                                                |                                                                                                   ckpt                                                                                                    |
+| :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :----------: | :------: | :---: | :--: | :--: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb](/configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.py) |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 27.1 | [log](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.log) | [json](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb-49b07bf2.pth) |
+
+### AVA2.2
+
+|                                                                              Model                                                                              | Modality |  Pretrained  | Backbone | Input | gpus | mAP  |                                                                                                 log                                                                                                 |                                                                                                 json                                                                                                  |                                                                                                     ckpt                                                                                                      |
+| :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :----------: | :------: | :---: | :--: | :--: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py) |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 27.8 | [log](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.log) | [json](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb-2be32625.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.
+
+:::
+
+For more details on data preparation, you can refer to AVA in [Data Preparation](/docs/data_preparation.md).
+
+## Train
+
+You can use the following command to train a model.
+
+```shell
+python tools/train.py ${CONFIG_FILE} [optional arguments]
+```
+
+Example: train ACRN with SlowFast backbone on AVA with periodic validation.
+
+```shell
+python tools/train.py configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py --validate
+```
+
+For more details and optional arguments infos, you can refer to **Training setting** part in [getting_started](/docs/getting_started.md#training-setting).
+
+## Test
+
+You can use the following command to test a model.
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
+```
+
+Example: test ACRN with SlowFast backbone on AVA and dump the result to a csv file.
+
+```shell
+python tools/test.py configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py checkpoints/SOME_CHECKPOINT.pth --eval mAP --out results.csv
+```
+
+For more details and optional arguments infos, 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{sun2018actor,
+  title={Actor-centric relation network},
+  author={Sun, Chen and Shrivastava, Abhinav and Vondrick, Carl and Murphy, Kevin and Sukthankar, Rahul and Schmid, Cordelia},
+  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+  pages={318--334},
+  year={2018}
+}
+```

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

+# ACRN
+
+## 简介
+
+<!-- [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}
+}
+```
+
+<!-- [ALGORITHM] -->
+
+```BibTeX
+@inproceedings{sun2018actor,
+  title={Actor-centric relation network},
+  author={Sun, Chen and Shrivastava, Abhinav and Vondrick, Carl and Murphy, Kevin and Sukthankar, Rahul and Schmid, Cordelia},
+  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+  pages={318--334},
+  year={2018}
+}
+```
+
+## 模型库
+
+### AVA2.1
+
+|                                                                          配置文件                                                                           | 模态 |    预训练    | 主干网络 | 输入 | GPU 数量 | mAP  |                                                                                               log                                                                                               |                                                                                               json                                                                                                |                                                                                                   ckpt                                                                                                    |
+| :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :--: | :----------: | :------: | :--: | :------: | :--: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb](/configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.py) | RGB  | Kinetics-400 | ResNet50 | 32x2 |    8     | 27.1 | [log](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.log) | [json](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb-49b07bf2.pth) |
+
+### AVA2.2
+
+|                                                                            配置文件                                                                             | 模态 |    预训练    | 主干网络 | 输入 | GPU 数量 | mAP  |                                                                                                 log                                                                                                 |                                                                                                 json                                                                                                  |                                                                                                     ckpt                                                                                                      |
+| :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--: | :----------: | :------: | :--: | :------: | :--: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py) | RGB  | Kinetics-400 | ResNet50 | 32x2 |    8     | 27.8 | [log](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.log) | [json](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb-2be32625.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。
+
+对于数据集准备的细节，用户可参考 [数据准备](/docs_zh_CN/data_preparation.md)。
+
+## 如何训练
+
+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：在 AVA 数据集上训练 ACRN 辅以 SlowFast 主干网络，并定期验证。
+
+```shell
+python tools/train.py configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py --validate
+```
+
+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。
+
+## 如何测试
+
+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：在 AVA 上测试 ACRN 辅以 SlowFast 主干网络，并将结果存为 csv 文件。
+
+```shell
+python tools/test.py configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_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/acrn/metafile.yml

+Collections:
+- Name: ACRN
+  README: configs/detection/acrn/README.md
+  Paper:
+    URL: https://arxiv.org/abs/1807.10982
+    Title: Actor-Centric Relation Network
+Models:
+- Config: configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.py
+  In Collection: ACRN
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 6
+    Epochs: 10
+    Input: 32x2
+    Modality: RGB
+    Parameters: 92232057
+    Pretrained: Kinetics-400
+    Training Data: AVA v2.1
+    Training Resources: 8 GPUs
+  Name: slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb
+  Results:
+  - Dataset: AVA v2.1
+    Metrics:
+      mAP: 27.1
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb.log
+  Weights: https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_rgb-49b07bf2.pth
+- Config: configs/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py
+  In Collection: ACRN
+  Metadata:
+    Architecture: ResNet50
+    Batch Size: 6
+    Epochs: 10
+    Input: 32x2
+    Modality: RGB
+    Parameters: 92232057
+    Pretrained: Kinetics-400
+    Training Data: AVA v2.2
+    Training Resources: 8 GPUs
+  Name: slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb
+  Results:
+  - Dataset: AVA v2.2
+    Metrics:
+      mAP: 27.8
+    Task: Spatial Temporal Action Detection
+  Training Json Log: https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.json
+  Training Log: https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.log
+  Weights: https://download.openmmlab.com/mmaction/detection/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb-2be32625.pth

openmmlab_test/mmaction2-0.24.1/configs/detection/acrn/slowfast_acrn_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'),
+        shared_head=dict(type='ACRNHead', in_channels=4608, out_channels=2304),
+        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_acrn_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/acrn/slowfast_acrn_kinetics_pretrained_r50_8x8x1_cosine_10e_ava_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'),
+        shared_head=dict(type='ACRNHead', in_channels=4608, out_channels=2304),
+        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_v2.1.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),
+    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_acrn_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/README.md

+# AVA
+
+[Ava: A video dataset of spatio-temporally localized atomic visual actions](https://openaccess.thecvf.com/content_cvpr_2018/html/Gu_AVA_A_Video_CVPR_2018_paper.html)
+
+<!-- [ALGORITHM] -->
+
+<div align="center">
+  <img src="https://github.com/open-mmlab/mmaction2/raw/master/resources/spatio-temporal-det.gif" width="800px"/>
+</div>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations. This departs from existing datasets for spatio-temporal action recognition, which typically provide sparse annotations for composite actions in short video clips. We will release the dataset publicly.
+AVA, with its realistic scene and action complexity, exposes the intrinsic difficulty of action recognition. To benchmark this, we present a novel approach for action localization that builds upon the current state-of-the-art methods, and demonstrates better performance on JHMDB and UCF101-24 categories. While setting a new state of the art on existing datasets, the overall results on AVA are low at 15.6% mAP, underscoring the need for developing new approaches for video understanding.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/34324155/143015933-36eb7abd-d38f-4be6-a327-4d34c6f4edc1.png" width="800"/>
+</div>
+
+<!-- [ALGORITHM] -->
+
+```BibTeX
+@inproceedings{feichtenhofer2019slowfast,
+  title={Slowfast networks for video recognition},
+  author={Feichtenhofer, Christoph and Fan, Haoqi and Malik, Jitendra and He, Kaiming},
+  booktitle={Proceedings of the IEEE international conference on computer vision},
+  pages={6202--6211},
+  year={2019}
+}
+```
+
+## Results and Models
+
+### AVA2.1
+
+|                                                                        Model                                                                         | Modality |  Pretrained  | Backbone  | Input | gpus |   Resolution   |  mAP  |                                                                                                log                                                                                                |                                                                                                json                                                                                                 |                                                                                                    ckpt                                                                                                     |
+| :--------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :----------: | :-------: | :---: | :--: | :------------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|         [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)         |   RGB    | Kinetics-400 | ResNet50  | 4x16  |  8   | short-side 256 | 20.1  |         [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)         |         [json](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)         |         [ckpt](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)         |
+|       [slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb.py)       |   RGB    |  OmniSource  | ResNet50  | 4x16  |  8   | short-side 256 | 21.8  |       [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)       |       [json](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)       |       [ckpt](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)       |
+|      [slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb](/configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb.py)      |   RGB    | Kinetics-400 | ResNet50  | 4x16  |  8   | short-side 256 | 21.75 |                              [log](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/20210316_122517.log)                              |                            [json](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/20210316_122517.log.json)                            |      [ckpt](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)      |
+|       [slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb](/configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb.py)       |   RGB    | Kinetics-400 | ResNet50  |  8x8  | 8x2  | short-side 256 | 23.79 |                              [log](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/20210316_122517.log)                               |                            [json](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/20210316_122517.log.json)                             |       [ckpt](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)       |
+|         [slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb.py)         |   RGB    | Kinetics-400 | ResNet101 |  8x8  | 8x2  | short-side 256 | 24.6  |         [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)         |         [json](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)         |         [ckpt](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)         |
+|       [slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb](/configs/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb.py)       |   RGB    |  OmniSource  | ResNet101 |  8x8  | 8x2  | short-side 256 | 25.9  |       [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)       |       [json](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)       |       [ckpt](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)       |
+|         [slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)         |   RGB    | Kinetics-400 | ResNet50  | 32x2  | 8x2  | short-side 256 | 24.4  |         [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)         |         [json](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)         |         [ckpt](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)         |
+| [slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) |   RGB    | Kinetics-400 | ResNet50  | 32x2  | 8x2  | short-side 256 | 25.4  | [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) | [json](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) | [ckpt](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) |
+|          [slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py)          |   RGB    | Kinetics-400 | ResNet50  | 32x2  | 8x2  | short-side 256 | 25.5  |          [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)          |          [json](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)          |          [ckpt](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)          |
+
+### AVA2.2
+
+|                                                                                                         Model                                                                                                          | Modality |  Pretrained  | Backbone | Input | gpus | mAP  |                                                                                                                            log                                                                                                                             |                                                                                                                             json                                                                                                                             |                                                                                                                                 ckpt                                                                                                                                 |
+| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :----------: | :------: | :---: | :--: | :--: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|                                  [slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py)                                  |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 26.1 |                                  [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)                                  |                                  [json](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)                                  |                                  [ckpt](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)                                  |
+|                     [slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py)                     |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 26.4 |                     [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)                     |                     [json](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)                     |                     [ckpt](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)                     |
+| [slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py) |   RGB    | Kinetics-400 | ResNet50 | 32x2  |  8   | 26.8 | [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) | [json](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) | [ckpt](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) |
+
+:::{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. **Context** indicates that using both RoI feature and global pooled feature for classification, which leads to around 1% mAP improvement in general.
+
+:::
+
+For more details on data preparation, you can refer to AVA in [Data Preparation](/docs/data_preparation.md).
+
+## Train
+
+You can use the following command to train a model.
+
+```shell
+python tools/train.py ${CONFIG_FILE} [optional arguments]
+```
+
+Example: train SlowOnly model on AVA with periodic validation.
+
+```shell
+python tools/train.py configs/detection/ava/slowonly_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py --validate
+```
+
+For more details and optional arguments infos, you can refer to **Training setting** part in [getting_started](/docs/getting_started.md#training-setting) .
+
+### Train Custom Classes From Ava Dataset
+
+You can train custom classes from ava. Ava suffers from class imbalance. There are more then 100,000 samples for classes like `stand`/`listen to (a person)`/`talk to (e.g., self, a person, a group)`/`watch (a person)`, whereas half of all classes has less than 500 samples. In most cases, training custom classes with fewer samples only will lead to better results.
+
+Three steps to train custom classes:
+
+- Step 1: Select custom classes from original classes, named `custom_classes`. Class `0` should not be selected since it is reserved for further usage (to identify whether a proposal is positive or negative, not implemented yet) and will be added automatically.
+- Step 2: Set `num_classes`. In order to be compatible with current codes, Please make sure `num_classes == len(custom_classes) + 1`.
+  - The new class `0` corresponds to original class `0`. The new class `i`(i > 0) corresponds to original class `custom_classes[i-1]`.
+  - There are three `num_classes` in ava config, `model -> roi_head -> bbox_head -> num_classes`, `data -> train -> num_classes` and `data -> val -> num_classes`.
+  - If `num_classes <= 5`, input arg `topk` of `BBoxHeadAVA` should be modified. The default value of `topk` is `(3, 5)`, and all elements of `topk` must be smaller than `num_classes`.
+- Step 3: Make sure all custom classes are in `label_file`. It is worth mentioning that there are two label files, `ava_action_list_v2.1_for_activitynet_2018.pbtxt`(contains 60 classes, 20 classes are missing) and `ava_action_list_v2.1.pbtxt`(contains all 80 classes).
+
+Take `slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb` as an example, training custom classes with AP in range `(0.1, 0.3)`, aka `[3, 6, 10, 27, 29, 38, 41, 48, 51, 53, 54, 59, 61, 64, 70, 72]`. Please note that, the previously mentioned AP is calculated by original ckpt, which is trained by all 80 classes. The results are listed as follows.
+
+| training classes | mAP(custom classes) |                                                                               config                                                                               |                                                                                                       log                                                                                                       |                                                                                                       json                                                                                                        |                                                                                                           ckpt                                                                                                            |
+| :--------------: | :-----------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|  All 80 classes  |       0.1948        |                [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)                |                [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)                |                [json](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)                |                [ckpt](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)                |
+|  custom classes  |       0.3311        | [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py) |     [log](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.log)      |     [json](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.json)      |     [ckpt](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes-4ab80419.pth)      |
+|  All 80 classes  |       0.1864        |              [slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py](/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)               |                [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)                |                [json](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)                |                [ckpt](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)                |
+|  custom classes  |       0.3785        | [slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes](/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py) | [log](https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes_20210305.log) | [json](https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes_20210305.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes_20210305-c6225546.pth) |
+
+## Test
+
+You can use the following command to test a model.
+
+```shell
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
+```
+
+Example: test SlowOnly model on AVA and dump the result to a csv file.
+
+```shell
+python tools/test.py configs/detection/ava/slowonly_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py checkpoints/SOME_CHECKPOINT.pth --eval mAP --out results.csv
+```
+
+For more details and optional arguments infos, 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
+@article{duan2020omni,
+  title={Omni-sourced Webly-supervised Learning for Video Recognition},
+  author={Duan, Haodong and Zhao, Yue and Xiong, Yuanjun and Liu, Wentao and Lin, Dahua},
+  journal={arXiv preprint arXiv:2003.13042},
+  year={2020}
+}
+```

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

+# AVA
+
+<div align="center">
+  <img src="https://github.com/open-mmlab/mmaction2/raw/master/resources/spatio-temporal-det.gif" width="800px"/>
+</div>
+
+## 简介
+
+<!-- [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}
+}
+```
+
+<!-- [ALGORITHM] -->
+
+```BibTeX
+@article{duan2020omni,
+  title={Omni-sourced Webly-supervised Learning for Video Recognition},
+  author={Duan, Haodong and Zhao, Yue and Xiong, Yuanjun and Liu, Wentao and Lin, Dahua},
+  journal={arXiv preprint arXiv:2003.13042},
+  year={2020}
+}
+```
+
+<!-- [ALGORITHM] -->
+
+```BibTeX
+@inproceedings{feichtenhofer2019slowfast,
+  title={Slowfast networks for video recognition},
+  author={Feichtenhofer, Christoph and Fan, Haoqi and Malik, Jitendra and He, Kaiming},
+  booktitle={Proceedings of the IEEE international conference on computer vision},
+  pages={6202--6211},
+  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  |  mAP  |                                                                                                log                                                                                                |                                                                                                json                                                                                                 |                                                                                                    ckpt                                                                                                     |
+| :--------------------------------------------------------------------------------------------------------------------------------------------------: | :--: | :----------: | :-------: | :--: | :------: | :------: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|         [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)         | RGB  | Kinetics-400 | ResNet50  | 4x16 |    8     | 短边 256 | 20.1  |         [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)         |         [json](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)         |         [ckpt](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)         |
+|       [slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_omnisource_pretrained_r50_4x16x1_20e_ava_rgb.py)       | RGB  |  OmniSource  | ResNet50  | 4x16 |    8     | 短边 256 | 21.8  |       [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)       |       [json](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)       |       [ckpt](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)       |
+|      [slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb](/configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb.py)      | RGB  | Kinetics-400 | ResNet50  | 4x16 |    8     | 短边 256 | 21.75 |                              [log](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/20210316_122517.log)                              |                            [json](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_4x16x1_10e_ava_rgb/20210316_122517.log.json)                            |      [ckpt](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)      |
+|       [slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb](/configs/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb.py)       | RGB  | Kinetics-400 | ResNet50  | 8x8  |   8x2    | 短边 256 | 23.79 |                              [log](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/20210316_122517.log)                               |                            [json](https://download.openmmlab.com/mmaction/detection/ava/slowonly_nl_kinetics_pretrained_r50_8x8x1_10e_ava_rgb/20210316_122517.log.json)                             |       [ckpt](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)       |
+|         [slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r101_8x8x1_20e_ava_rgb.py)         | RGB  | Kinetics-400 | ResNet101 | 8x8  |   8x2    | 短边 256 | 24.6  |         [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)         |         [json](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)         |         [ckpt](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)         |
+|       [slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb](/configs/detection/ava/slowonly_omnisource_pretrained_r101_8x8x1_20e_ava_rgb.py)       | RGB  |  OmniSource  | ResNet101 | 8x8  |   8x2    | 短边 256 | 25.9  |       [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)       |       [json](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)       |       [ckpt](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)       |
+|         [slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)         | RGB  | Kinetics-400 | ResNet50  | 32x2 |   8x2    | 短边 256 | 24.4  |         [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)         |         [json](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)         |         [ckpt](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)         |
+| [slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py) | RGB  | Kinetics-400 | ResNet50  | 32x2 |   8x2    | 短边 256 | 25.4  | [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) | [json](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) | [ckpt](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) |
+|          [slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py)          | RGB  | Kinetics-400 | ResNet50  | 32x2 |   8x2    | 短边 256 | 25.5  |          [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)          |          [json](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)          |          [ckpt](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)          |
+
+### AVA2.2
+
+|                                                                                                        配置文件                                                                                                        | 模态 |    预训练    | 主干网络 | 输入 | GPU 数量 | mAP  |                                                                                                                            log                                                                                                                             |                                                                                                                             json                                                                                                                             |                                                                                                                                 ckpt                                                                                                                                 |
+| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--: | :----------: | :------: | :--: | :------: | :--: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|                                  [slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py)                                  | RGB  | Kinetics-400 | ResNet50 | 32x2 |    8     | 26.1 |                                  [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)                                  |                                  [json](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)                                  |                                  [ckpt](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)                                  |
+|                     [slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/ava/slowfast_temporal_max_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py)                     | RGB  | Kinetics-400 | ResNet50 | 32x2 |    8     | 26.4 |                     [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)                     |                     [json](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)                     |                     [ckpt](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)                     |
+| [slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb](/configs/detection/ava/slowfast_temporal_max_focal_alpha3_gamma1_kinetics_pretrained_r50_8x8x1_cosine_10e_ava22_rgb.py) | RGB  | Kinetics-400 | ResNet50 | 32x2 |    8     | 26.8 | [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) | [json](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) | [ckpt](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) |
+
+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. **Context** 表示同时使用 RoI 特征与全局特征进行分类，可带来约 1% mAP 的提升。
+
+对于数据集准备的细节，用户可参考 [数据准备](/docs_zh_CN/data_preparation.md)。
+
+## 如何训练
+
+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：在 AVA 数据集上训练 SlowOnly，并定期验证。
+
+```shell
+python tools/train.py configs/detection/ava/slowonly_kinetics_pretrained_r50_8x8x1_20e_ava_rgb.py --validate
+```
+
+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。
+
+### 训练 AVA 数据集中的自定义类别
+
+用户可以训练 AVA 数据集中的自定义类别。AVA 中不同类别的样本量很不平衡：其中有超过 100000 样本的类别： `stand`/`listen to (a person)`/`talk to (e.g., self, a person, a group)`/`watch (a person)`，也有样本较少的类别（半数类别不足 500 样本）。大多数情况下，仅使用样本较少的类别进行训练将在这些类别上得到更好精度。
+
+训练 AVA 数据集中的自定义类别包含 3 个步骤：
+
+1. 从原先的类别中选择希望训练的类别，将其填写至配置文件的 `custom_classes` 域中。其中 `0` 不表示具体的动作类别，不应被选择。
+2. 将 `num_classes` 设置为 `num_classes = len(custom_classes) + 1`。
+   - 在新的类别到编号的对应中，编号 `0` 仍对应原类别 `0`，编号 `i` (i > 0) 对应原类别 `custom_classes[i-1]`。
+   - 配置文件中 3 处涉及 `num_classes` 需要修改：`model -> roi_head -> bbox_head -> num_classes`， `data -> train -> num_classes`， `data -> val -> num_classes`.
+   - 若 `num_classes <= 5`， 配置文件 `BBoxHeadAVA` 中的 `topk` 参数应被修改。`topk` 的默认值为 `(3, 5)`，`topk` 中的所有元素应小于 `num_classes`。
+3. 确认所有自定义类别在 `label_file` 中。
+
+以 `slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb` 为例，这一配置文件训练所有 AP 在 `(0.1, 0.3)` 间的类别（这里的 AP 为 AVA 80 类训出模型的表现），即 `[3, 6, 10, 27, 29, 38, 41, 48, 51, 53, 54, 59, 61, 64, 70, 72]`。下表列出了自定义类别训练的模型精度：
+
+|  训练类别  | mAP （自定义类别） |                                                                              配置文件                                                                              |                                                                                                       log                                                                                                       |                                                                                                       json                                                                                                        |                                                                                                           ckpt                                                                                                            |
+| :--------: | :----------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| 全部 80 类 |       0.1948       |                [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)                |                [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)                |                [json](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)                |                [ckpt](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)                |
+| 自定义类别 |       0.3311       | [slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes](/configs/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py) |     [log](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.log)      |     [json](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.json)      |     [ckpt](https://download.openmmlab.com/mmaction/detection/ava/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowonly_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes-4ab80419.pth)      |
+| 全部 80 类 |       0.1864       |                [slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb](/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb.py)                |                [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)                |                [json](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)                |                [ckpt](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)                |
+| 自定义类别 |       0.3785       | [slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes](/configs/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes.py) | [log](https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes_20210305.log) | [json](https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes_20210305.json) | [ckpt](https://download.openmmlab.com/mmaction/detection/ava/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes/slowfast_kinetics_pretrained_r50_4x16x1_20e_ava_rgb_custom_classes_20210305-c6225546.pth) |
+
+## 如何测试
+
+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：在 AVA 上测试 SlowOnly 模型，并将结果存为 csv 文件。
+
+```shell
+python tools/test.py configs/detection/ava/slowonly_kinetics_pretrained_r50_8x8x1_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。