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

[Fix] Associative Embedding inference align with master #1960

Draft
wants to merge 3 commits into
base: dev-1.x
Choose a base branch
from

Conversation

ly015
Copy link
Member

@ly015 ly015 commented Feb 7, 2023

Motivation

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist

Before PR:

  • I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
  • Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
  • Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
  • New functionalities are covered by complete unit tests. If not, please add more unit tests to ensure correctness.
  • The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

  • CLA has been signed and all committers have signed the CLA in this PR.

@@ -478,6 +478,7 @@ def transform(self, results: Dict) -> Optional[dict]:
output_size=actual_input_size)
else:
center = np.array([img_w / 2, img_h / 2], dtype=np.float32)
center = np.round(center)
Copy link
Member Author

Choose a reason for hiding this comment

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

@Ben-Louis This rounding is implemented in the master branch, but missing in the 1.x branch. It will affect the performance of AE models. Could you please check its influence on DEKR?

Copy link
Collaborator

Choose a reason for hiding this comment

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

@Ben-Louis This rounding is implemented in the master branch, but missing in the 1.x branch. It will affect the performance of AE models. Could you please check its influence on DEKR?

For DEKR models, rounding the center can result in a reduction of about 0.1 AP on COCO

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.

3 participants