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.

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

Jump to bottom

Fix mAP calculations #7714

Closed
wants to merge 3 commits into from
Closed

Fix mAP calculations #7714

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ad25966
Fix mAP calucation
comlhj1114 May 6, 2022
f73e549
Merge remote-tracking branch 'upstream/master' into fix/mAP
comlhj1114 May 6, 2022
6e2a35a
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] May 6, 2022
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
Next Next commit
Fix mAP calucation
  • Loading branch information
@comlhj1114
comlhj1114 committed May 6, 2022
commit ad25966c2ed636c2cdf4822618e74a916c65ce66
8 changes: 4 additions & 4 deletions utils/metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,11 +57,11 @@ def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names

# Recall
recall = tpc / (n_l + eps) # recall curve
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0, right=0) # negative x, xp because xp decreases

# Precision
precision = tpc / (tpc + fpc) # precision curve
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=0, right=0) # p at pr_score

# AP from recall-precision curve
for j in range(tp.shape[1]):
Expand Down Expand Up @@ -96,8 +96,8 @@ def compute_ap(recall, precision):
"""

# Append sentinel values to beginning and end
mrec = np.concatenate(([0.0], recall, [1.0]))
mpre = np.concatenate(([1.0], precision, [0.0]))
mrec = np.concatenate((recall, [recall[-1]+0.001]))
mpre = np.concatenate((precision, [0.0]))

# Compute the precision envelope
mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
Expand Down