NVlabs / few-shot-vid2vid

Pytorch implementation for few-shot photorealistic video-to-video translation.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

hi, @yashasbharadwaj111

mamunctg opened this issue · comments

hi, @yashasbharadwaj111
I'm sorry. I can't share our model because our data set is divided into two parts:

  1. Collected from youtube, we have not obtained the consent of the host
  2. I don’t have the right to share the video data of our lab

Originally posted by @AaronWong in #14 (comment)

could you please share me the configurations of packeges ? I trired with following configurations: python3.6, pytorch 1.2.0, torchvision 0.4.0, cuda 10.0, gcc4.9 in ubuntu-20
But i am encountering by the errors :
##############
class GradScaler(torch.cuda.amp.GradScaler):
AttributeError: module 'torch.cuda' has no attribute 'amp'

@mamunctg I also encountered this problem. How did you solve it?