zhangsanfeng86

Hi @lisiyao21 I also found the video is 2D, as follow: how to generate video similar to your demo video?

In https://github.com/lisiyao21/Bailando/blob/125b529b3c596b58b9d70f22c05dc3f04a01895c/utils/metrics_new.py#L181 https://github.com/lisiyao21/Bailando/blob/125b529b3c596b58b9d70f22c05dc3f04a01895c/utils/metrics_new.py#L182 suggest as : gt_root = './data/aist_features_zero_start' pred_root = './experiments/actor_critic/eval/pkl/ep000010'

@Wuie 请问：'RightShoulder': [1, 0, 0], 1代表X正方向吗？

You can find my modified version [here](https://github.com/ErenBalatkan/HifiGan-TorchScript) I have also included a simple benchmark for comparing scripted version to PyTorch. @ErenBalatkan have you noticed any speed up for the scripted...

Thanks for your reply! I think the main reason is : Run Docker on WSL. When run docker enviroment on Ubuntu , no error!

I got the same Error, and Environment also same 

@zhisbug How to set "use cache=False"? I just run "train_mem.py"

Thank u, I'll try!

> Did you turn on the `gradient_checkpointing`? We need to turn on that for the `train_mem.py` as that will turn off the `use_cache` implicitly. --------------------------------------------------------- Hi @Michaelvll I turn on...