[Improvement] Add links to download Kinetics400 validation

configs/recognition/csn/README.md

@@ -43,6 +43,7 @@ Notes:
    e.g., lr=0.01 for 4 GPUs x 2 video/gpu and lr=0.08 for 16 GPUs x 4 video/gpu.
 2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
    not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+3. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
 
 For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
 

configs/recognition/csn/README_zh-CN.md

@@ -43,6 +43,7 @@ doi = {10.1109/ICCV.2019.00565}
    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. 这里的 **推理时间** 是根据 [基准测试脚本](/tools/analysis/benchmark.py) 获得的，采用测试时的采帧策略，且只考虑模型的推理时间，
    并不包括 IO 时间以及预处理时间。对于每个配置，MMAction2 使用 1 块 GPU 并设置批大小（每块 GPU 处理的视频个数）为 1 来计算推理时间。
+3. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
 
 对于数据集准备的细节，用户可参考 [数据集准备文档](/docs_zh_CN/data_preparation.md) 中的 Kinetics400 部分。
 

configs/recognition/i3d/README.md

@@ -48,8 +48,8 @@ Notes:
 1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
    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. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
-   not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time, not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+3. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
 
 For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
 

configs/recognition/i3d/README_zh-CN.md

@@ -50,6 +50,7 @@
    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. 这里的 **推理时间** 是根据 [基准测试脚本](/tools/analysis/benchmark.py) 获得的，采用测试时的采帧策略，且只考虑模型的推理时间，
    并不包括 IO 时间以及预处理时间。对于每个配置，MMAction2 使用 1 块 GPU 并设置批大小（每块 GPU 处理的视频个数）为 1 来计算推理时间。
+3. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
 
 对于数据集准备的细节，用户可参考 [数据集准备文档](/docs_zh_CN/data_preparation.md) 中的 Kinetics400 部分。
 

configs/recognition/omnisource/README.md

@@ -19,6 +19,8 @@ We currently released 4 models trained with OmniSource framework, including both
 | SlowOnly |   RGB    |  Scratch   | ResNet50  | 4x16  | short-side 320 |          72.9 / 76.8 (+ 3.9)          |          90.9 / 92.5 (+ 1.6)           | [Baseline](https://download.openmmlab.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth) / [OmniSource](https://download.openmmlab.com/mmaction/recognition/slowonly/omni/slowonly_r50_omni_4x16x1_kinetics400_rgb_20200926-51b1f7ea.pth) |
 | SlowOnly |   RGB    |  Scratch   | ResNet101 |  8x8  | short-side 320 |          76.5 / 80.4 (+ 3.9)          |          92.7 / 94.4 (+ 1.7)           | [Baseline](https://download.openmmlab.com/mmaction/recognition/slowonly/omni/slowonly_r101_without_omni_8x8x1_kinetics400_rgb_20200926-0c730aef.pth) / [OmniSource](https://download.openmmlab.com/mmaction/recognition/slowonly/omni/slowonly_r101_omni_8x8x1_kinetics400_rgb_20200926-b5dbb701.pth) |
 
+1. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
+
 ## Benchmark on Mini-Kinetics
 
 We release a subset of web dataset used in the OmniSource paper. Specifically, we release the web data in the 200 classes of [Mini-Kinetics](https://arxiv.org/pdf/1712.04851.pdf). The statistics of those datasets is detailed in [preparing_omnisource](/tools/data/omnisource/README.md). To obtain those data, you need to fill in a [data request form](https://docs.google.com/forms/d/e/1FAIpQLSd8_GlmHzG8FcDbW-OEu__G7qLgOSYZpH-i5vYVJcu7wcb_TQ/viewform?usp=sf_link). After we received your request, the download link of these data will be send to you. For more details on the released OmniSource web dataset, please refer to [preparing_omnisource](/tools/data/omnisource/README.md).

configs/recognition/omnisource/README_zh-CN.md

@@ -19,6 +19,8 @@ MMAction2 当前公开了 4 个 OmniSource 框架训练的模型，包含 2D 架
 | SlowOnly | RGB  |   None   | ResNet50  | 4x16 | short-side 320 |             72.9 / 76.8 (+ 3.9)             |             90.9 / 92.5 (+ 1.6)              | [Baseline](https://download.openmmlab.com/mmaction/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb/slowonly_r50_4x16x1_256e_kinetics400_rgb_20200704-a69556c6.pth) / [OmniSource](https://download.openmmlab.com/mmaction/recognition/slowonly/omni/slowonly_r50_omni_4x16x1_kinetics400_rgb_20200926-51b1f7ea.pth) |
 | SlowOnly | RGB  |   None   | ResNet101 | 8x8  | short-side 320 |             76.5 / 80.4 (+ 3.9)             |             92.7 / 94.4 (+ 1.7)              | [Baseline](https://download.openmmlab.com/mmaction/recognition/slowonly/omni/slowonly_r101_without_omni_8x8x1_kinetics400_rgb_20200926-0c730aef.pth) / [OmniSource](https://download.openmmlab.com/mmaction/recognition/slowonly/omni/slowonly_r101_omni_8x8x1_kinetics400_rgb_20200926-b5dbb701.pth) |
 
+1. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
+
 ## Mini-Kinetics 上的基准测试
 
 OmniSource 项目当前公开了所采集网络数据的一个子集，涉及 [Mini-Kinetics](https://arxiv.org/pdf/1712.04851.pdf) 中的 200 个动作类别。[OmniSource 数据集准备](/tools/data/omnisource/README_zh-CN.md) 中记录了这些数据集的详细统计信息。用户可以通过填写 [申请表](https://docs.google.com/forms/d/e/1FAIpQLSd8_GlmHzG8FcDbW-OEu__G7qLgOSYZpH-i5vYVJcu7wcb_TQ/viewform?usp=sf_link) 获取这些数据，在完成填写后，数据下载链接会被发送至用户邮箱。更多关于 OmniSource 网络数据集的信息请参照 [OmniSource 数据集准备](/tools/data/omnisource/README_zh-CN.md)。

configs/recognition/r2plus1d/README.md

@@ -30,8 +30,8 @@ Notes:
 1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
    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. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
-   not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time, not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+3. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
 
 For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
 

configs/recognition/r2plus1d/README_zh-CN.md

@@ -32,6 +32,7 @@
    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. 这里的 **推理时间** 是根据 [基准测试脚本](/tools/analysis/benchmark.py) 获得的，采用测试时的采帧策略，且只考虑模型的推理时间，
    并不包括 IO 时间以及预处理时间。对于每个配置，MMAction2 使用 1 块 GPU 并设置批大小（每块 GPU 处理的视频个数）为 1 来计算推理时间。
+3. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
 
 对于数据集准备的细节，用户可参考 [数据集准备文档](/docs_zh_CN/data_preparation.md) 中的 Kinetics400 部分。
 

configs/recognition/slowfast/README.md

@@ -34,8 +34,8 @@ Notes:
 1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
    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. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
-   not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time, not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+3. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
 
 For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
 

configs/recognition/slowfast/README_zh-CN.md

@@ -36,6 +36,7 @@
    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. 这里的 **推理时间** 是根据 [基准测试脚本](/tools/analysis/benchmark.py) 获得的，采用测试时的采帧策略，且只考虑模型的推理时间，
    并不包括 IO 时间以及预处理时间。对于每个配置，MMAction2 使用 1 块 GPU 并设置批大小（每块 GPU 处理的视频个数）为 1 来计算推理时间。
+3. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
 
 对于数据集准备的细节，用户可参考 [数据集准备文档](/docs_zh_CN/data_preparation.md) 中的 Kinetics400 部分。
 

configs/recognition/slowonly/README.md

@@ -82,8 +82,8 @@ Notes:
 1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
    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. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time,
-   not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+2. The **inference_time** is got by this [benchmark script](/tools/analysis/benchmark.py), where we use the sampling frames strategy of the test setting and only care about the model inference time, not including the IO time and pre-processing time. For each setting, we use 1 gpu and set batch size (videos per gpu) to 1 to calculate the inference time.
+3. The validation set of Kinetics400 we used consists of 19796 videos. These videos are available at [Kinetics400-Validation](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB). The corresponding [data list](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) (each line is of the format 'video_id, num_frames, label_index') and the [label map](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) are also available.
 
 For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
 

configs/recognition/slowonly/README_zh-CN.md

@@ -84,6 +84,7 @@
    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. 这里的 **推理时间** 是根据 [基准测试脚本](/tools/analysis/benchmark.py) 获得的，采用测试时的采帧策略，且只考虑模型的推理时间，
    并不包括 IO 时间以及预处理时间。对于每个配置，MMAction2 使用 1 块 GPU 并设置批大小（每块 GPU 处理的视频个数）为 1 来计算推理时间。
+3. 我们使用的 Kinetics400 验证集包含 19796 个视频，用户可以从 [验证集视频](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155136485_link_cuhk_edu_hk/EbXw2WX94J1Hunyt3MWNDJUBz-nHvQYhO9pvKqm6g39PMA?e=a9QldB) 下载这些视频。同时也提供了对应的 [数据列表](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_val_list.txt) （每行格式为：视频 ID，视频帧数目，类别序号）以及 [标签映射](https://download.openmmlab.com/mmaction/dataset/k400_val/kinetics_class2ind.txt) （类别序号到类别名称）。
 
 对于数据集准备的细节，用户可参考 [数据集准备文档](/docs_zh_CN/data_preparation.md) 中的 Kinetics400 部分。