search

NVlabs / few-shot-vid2vid

Pytorch implementation for few-shot photorealistic video-to-video translation.
Other
1.79k stars 276 forks source link

hi, @yashasbharadwaj111 #88

Open mamunctg opened 2 years ago

mamunctg commented 2 years ago

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 https://github.com/NVlabs/few-shot-vid2vid/issues/14#issuecomment-570766853

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'

songyn95 commented 2 years ago

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