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

Implement metrics changes #13

Merged
merged 3 commits into from
Nov 12, 2021
Merged

Implement metrics changes #13

merged 3 commits into from
Nov 12, 2021

Conversation

timatcambrio
Copy link
Member

Changes:

  1. Allows for dropping detections in solver submissions that are matched to LOW confidence ground truth labels;
  2. Allows for increasing the cost for prediction-ground truth pairs whose distance is greater than the distance tolerance; related to Distance-based matching in metric.py is broken #9.

@favyen2
Copy link

favyen2 commented Nov 10, 2021

Is it intended that costly_dist is disabled in drop_low_confidence_preds even with --costly_dist flag (args.costly_dist is not passed to drop_low_confidence_preds)?

reference/metric.py Outdated Show resolved Hide resolved
reference/metric.py Outdated Show resolved Hide resolved
reference/metric.py Show resolved Hide resolved
reference/metric.py Show resolved Hide resolved
@timatcambrio
Copy link
Member Author

Is it intended that costly_dist is disabled in drop_low_confidence_preds even with --costly_dist flag (args.costly_dist is not passed to drop_low_confidence_preds)?

Nice catch! Thank you, @favyen2!

@timatcambrio timatcambrio merged commit 17325ae into main Nov 12, 2021
@timatcambrio timatcambrio linked an issue Nov 12, 2021 that may be closed by this pull request
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.

Distance-based matching in metric.py is broken
4 participants