deep-image-prior icon indicating copy to clipboard operation
deep-image-prior copied to clipboard

Published 20 hours ago • verified publisher icon DmitryUlyanov

Error inpainting for CUDA

Open June-phy opened this issue 2 years ago • 0 comments

Hi, In inpainting.ipynb the loss is NAN from the beginning. However, if I turn off cuda:

  torch.backends.cudnn.enabled = False 
  torch.backends.cudnn.benchmark = False 
  dtype = torch.FloatTensor

All the loss is right. I was using RTX 3070 Ti, cuda 9.0.

Why the loss turns into 'nan' when running on GPU? Please help me with this problem.

June-phy avatar Mar 10 '22 11:03 June-phy