JunyaoHu / common_metrics_on_video_quality

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
232 stars 9 forks source link

If you are running demo.py on a multi-GPU machine, remember to export CUDA_VISIBLE_DEVICES=0, otherwise an error will occur #13

Closed pixeli99 closed 5 months ago

pixeli99 commented 5 months ago

If you are running demo.py on a multi-GPU machine, remember to export CUDA_VISIBLE_DEVICES=0, otherwise an error will occur.

RuntimeError: forward() is missing value for argument 'x'. Declaration: forward(__torch__.src.i3dpt_jit.I3D self, Tensor x, bool rescale=False, bool resize=False, bool return_features=False) -> Tensor

Hope this helps

JunyaoHu commented 5 months ago

thanks, I will update it in the readme