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

Why the default training epoch is as large as 500? #29

Open

LuffysMan opened this issue Jan 24, 2021 · 1 comment

LuffysMan commented Jan 24, 2021

The paper claimed only need 80 epochs to train. Another reproduction from seathiefwang has the same problem.

Author

LuffysMan commented Jan 24, 2021

I know. It is because of the stategy of data sampling. You sampled part of the whole dataset for one epoch.

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