Skip to content

Fix AP/mAP degradation due to unsorted prediction confidence scores & Add IoU Zero-Division Safeguard #545

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

Open
shardulmahamulkar wants to merge 2 commits into
base: master
Choose a base branch
from
+7 −3
Open

Fix AP/mAP degradation due to unsorted prediction confidence scores & Add IoU Zero-Division Safeguard #545

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c886e08
Fix AP/mAP calculations by sorting prediction confidence scores and h…
shardulmahamulkar Apr 9, 2026
0d7b131
Merge branch 'master' into fix-evaluation-metrics
shardulmahamulkar Apr 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions perceptionmetrics/utils/detection_metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,9 +127,13 @@ def _match_predictions(

ious = compute_iou_matrix(pred_boxes, gt_boxes) # shape: (num_preds, num_gts)

for i, (p_box, p_label, score) in enumerate(
zip(pred_boxes, pred_labels, pred_scores)
):
# Sort predictions by descending score to ensure highest-confidence predictions match first
sorted_indices = np.argsort([-s for s in pred_scores])

for i in sorted_indices:
p_box = pred_boxes[i]
p_label = pred_labels[i]
score = pred_scores[i]
max_iou = 0
max_j = -1

Expand Down