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

Why use neg_avg_factor = (1 - p_neg_weight).sum() ? #30

Open

Icecream-blue-sky opened this issue Nov 28, 2022 · 1 comment

Icecream-blue-sky commented Nov 28, 2022

In loss function:

neg_avg_factor = (1 - p_neg_weight).sum()
...
cls_neg_loss = sum(cls_neg_loss_list) / neg_avg_factor

Why not use neg_avg_factor = (p_neg_weight).sum() ?

Owner

strongwolf commented Jan 14, 2023

The value of (p_neg_weight).sum() is too small and it will cause unstable training.

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