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

confusion in OhemCrossEntropy loss function #15

Open

Srutsth opened this issue Apr 3, 2021 · 1 comment

Srutsth commented Apr 3, 2021 •

edited

Loading

pred = prob[label, np.arange(len(label), dtype=np.int32)]

What does this line do in OhemCrossEntropy do?

Owner

Serge-weihao commented Apr 6, 2021 •

edited

Loading

CCNet-Pure-Pytorch/loss/loss.py

Line 68 in ff51a27

pred = prob[label, np.arange(len(label), dtype=np.int32)]

I guess that means to get the gt class related predicted score for each (valid) pixel.

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