Data Preparation阶段

Besides the skeleton annotations, you also need RGB videos to train RGBPoseConv3D. You need to download them from the official website of NTURGB+D

 ROSE Lab

 除了骨架注释，您还需要 RGB 视频来训练 RGBPoseConv3D。您需要从 NTURGB+D 的官方网站下载它们。

and put these videos in $PYSKL/data/nturgbd_raw

并将这些视频放在 $PYSKL/data/nturgbd_raw 

After that, you need to use the provided script to compress the raw videos (from 1920x1080 to 960x540) and switch the suffix to .mp4:

 之后，您需要使用提供的脚本压缩原始视频（从 1920x1080 到 960x540）并将后缀切换为 .mp4：

 

# That step is mandatory, unless you know how to modify the code & config to make it work for raw videos!
python compress_nturgbd.py

After that, you will find processed videos in $PYSKL/data/nturgbd_videos, named like S001C001P001R001A001.mp4.

之后，您将在 $PYSKL/data/nturgbd_videos 中找到经过处理的视频，名称类似于 S001C001P001R001A001.mp4。

参考：

pyskl/configs/rgbpose_conv3d/compress_nturgbd.py at main · kennymckormick/pyskl · GitHub