search

mlfoundations / open-diffusion

Simple large-scale training of stable diffusion with multi-node support.
122 stars 8 forks source link

Relative symlink issue #1

Closed mehdidc closed 1 year ago

mehdidc commented 1 year ago

Thanks @vramanuj for this really nice repo!

I started to experiment with it and had an issue with symlinks that are used to indicate the current pipeline folder. In my case, the symlinks were dead because they are pointing to relative path, so resuming did not work. Simply adding .absolute() to save_path in https://github.com/mlfoundations/open-diffusion/blob/main/train.py#L311 and https://github.com/mlfoundations/open-diffusion/blob/main/train.py#L509 makes it work fine.

Or did you do anything else that made it work anyway?

vkramanuj commented 1 year ago

Hi Mehdi, I believe that fix should work. In my configs I used only absolute paths, so I didn’t come across this issue. You could also use .absolute().resolve() so your path ends up cleaner. Thanks for pointing this out! Feel free to submit a PR to this effect if you get the chance. Otherwise I can update the code later :-)

mehdidc commented 1 year ago

Thanks, I see, sure will open a PR!

vkramanuj commented 1 year ago

Closed with #3