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

lob_epoch_trainer tiny bug #1

Open

alfredyuan opened this issue Jan 13, 2020 · 1 comment

alfredyuan commented Jan 13, 2020

In line 39 of train_utils.py

It should be:

loss = (train_loss / counter ).cpu().data.numpy()

otherwise train_loss is not used and loss seems to be a pretty small number.

Can you please double check?

breznak commented Oct 29, 2020

This could be closed as it seems to be correct in the current code:

    loss = (loss / counter).cpu().data.numpy()
    return loss

Thanks for providing the solution!

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