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

The Loss becomes negative #15

Closed

BD-MF opened this issue Nov 16, 2021 · 1 comment

BD-MF commented Nov 16, 2021

As the network is trained, the loss value becomes negative. Can you give some solutions?

Owner

shengliu66 commented Dec 2, 2021

It becomes negative as the regularization term is negative to compensate the CE loss, but could you specify why this is a problem?

shengliu66 closed this as completed

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