search

DmitryUlyanov / deep-image-prior

Image restoration with neural networks but without learning.
https://dmitryulyanov.github.io/deep_image_prior
Other
7.79k stars 1.42k forks source link

Error inpainting for CUDA #99

Open June-phy opened 2 years ago

June-phy commented 2 years ago

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.