News for hackers. Stuff that matters.

A comment on FastPhotoStyle from Nvidia. Parent comment

Re:FastPhotoStyle from Nvidia by yorwba on Wednesday February 21, 2018 @07:35AM (#16428969)
Haha, yes, I had to rewrite their code a bit. All the .unsqueeze(1).expand_as(...) in photo_wct.py need to be replaced by just .expand_as(...) and the return value of __feature_wct needs to be wrapped in torch.autograd.Variable.

I'm going to submit a PR, but it took me a bit of experimentation to fix these errors, so the code is a bit messier than I'd like.

[ Parent | on HN ]
Re:FastPhotoStyle from Nvidia by IanCal on Wednesday February 21, 2018 @07:47AM (#16429032)
Ahh that looks like the error I was hitting, thanks. I might try replacing the bits as well, though I just upgraded pytorch from 0.1.12 to 0.3 and it became much slower (I killed it after 5-6 minutes of setup).
[ Parent | on HN ]
Re:FastPhotoStyle from Nvidia by yorwba on Wednesday February 21, 2018 @08:33AM (#16429296)
My fork is here: https://github.com/Yorwba/FastPhotoStyle

I was using the pytorch 0.1.12 installed with conda (following their USAGE.md) and it took ~30s total for the transfer.

[ Parent | on HN ]
Re:FastPhotoStyle from Nvidia by IanCal on Wednesday February 21, 2018 @09:06AM (#16429494)
Much appreciated thanks!

For some reason it's taking me about 4-5 minutes for the transfer, but the code now runs and the rest of the runtime is only a few seconds.

[ Parent | on HN ]