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

use max-epoch5 v.s. early stop #8

Open

yitang opened this issue Mar 11, 2018 · 1 comment

yitang commented Mar 11, 2018

Hi, I am new to DL and i wonder what's the reason behind using small epoch (5) and not using early stop?

Thanks,

Owner

chenyuntc commented Mar 11, 2018

Actually I use another kind of early stop:

if val acc rises: save the model, keep training
if val acc drops: load previous best model, decay lr

see here

5 epochs are not enough, Usually, I will finetune another 2 epochs with smaller lr.

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