Skip to content
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.

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

About test_criterion #44

Open
wuqun-tju opened this issue Sep 23, 2024 · 1 comment
Open

About test_criterion #44

wuqun-tju opened this issue Sep 23, 2024 · 1 comment

Comments

@wuqun-tju
Copy link

Hello, I wanna know why the sign of MatchingLoss in the test_criterion is negtivate:

Regr3D(L21, norm_mode='?avg_dis', gt_scale=True, sky_loss_value=0) + -1.*MatchingLoss(APLoss(nq='torch', fp=torch.float16), negatives_padding=12288)"

@yocabon
Copy link
Contributor

yocabon commented Sep 24, 2024

Hi,
the comment in the code about the APLoss was wrong, it returns AP, not 1-AP.
Since for AP, higher is better, and it is the opposite for Regr3D, it's logical that the loss is Regr3D - AP.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants