lin zhong
Results
3
comments of
lin zhong
I solve this by running: `# TORCH_CUDA_ARCH_LIST="6.1+PTX" python setup.py install ` for my GTX1080ti. The GPU_CC number6.1 is according to 1080ti refer to https://developer.nvidia.com/cuda-gpus
i think it's "mean per joint position error" for evaluating the reconstruction quality of the trained vae.
There is a closed issue figured it out. Just find a humanml3d data which has nan and delete it. There were only *007975.npy has nan.