how to get the .npz files of each input .bvh file?

[AWangji]

Hi, thanks for your great work. But I have a question when I try on my own dataset. In your inference_bvh_cfg.yaml, we should input the path of both the bvh and .npz file. But how should we get the .npz file?

And if I inference on my own dataset, do I need to change the "stats_path"?