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