New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Loss becomes NaN #9

Open

densechen opened this issue Oct 18, 2023 · 1 comment

densechen commented Oct 18, 2023

Hi, @asanakoy , Thanks for providing such nice work.

I am trying to train CINNS in another dataset, but I find that the loss always gets to NaN after optimizing. Can you provide some hints to debug it?

ctx2333 commented Nov 8, 2023

I've tried to large the batchsize to solve this problem, and it works.
Or you can check whether the log is printed correctly.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment