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

added find_detection_score_threshold #973

Conversation

itaylevy-deci
Copy link
Contributor

computes the best threshold for each class in an efficient manner without added loops

@dagshub
Copy link

dagshub bot commented May 10, 2023

Copy link
Collaborator

@shaydeci shaydeci left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very nice work!

  • See one comment inline.
  • There's still a missing piece we spoke of - we get the different thresholds per class, then we wish to use these in our NMS.
  • It would also be great to just have the threshold that maximizes F1.
  • Nice to have: same mechanism for the other metrics (mAP etc).

src/super_gradients/training/utils/detection_utils.py Outdated Show resolved Hide resolved
@shaydeci
Copy link
Collaborator

@itaylevy-deci This PR has been open for quite a while now and has some comments that were not addressed.

Copy link
Collaborator

@BloodAxe BloodAxe left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Collaborator

@shaydeci shaydeci left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@shaydeci shaydeci merged commit 2ea6a14 into Deci-AI:master Jun 29, 2023
4 checks passed
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

Successfully merging this pull request may close these issues.

None yet

4 participants