One of the judgment criteria for line 267 in the val.py seems less rigorous

[JiannBai]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

No response

Bug

Maybe not a bug, when I was in the verification phase of the last epoch, if I didn't have a true positive, it would be wrong on line 294 under the "if plot" condition

Environment

No response

Minimal Reproducible Example

if len(stats) and stats[0].any():
tp, fp, p, r, f1, ap, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
ap50, ap = ap[:, 0], ap.mean(1) # AP@0.5, AP@0.5:0.95
mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()

if plots:
confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
callbacks.run('on_val_end', nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix)

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[glenn-jocher]

@jianbaiwuqing your code is likely out of date as val.py L294 is an empty line:

yolov5/val.py

Lines 290 to 294 in 1323b48

	# Plots
	if plots:
	confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
	callbacks.run('on_val_end', nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix)

If you are able to reproduce this in master please provide a minimum reproducible example so we can start debugging. Thanks!

[glenn-jocher]

@jianbaiwuqing I'm able to reproduce an error by setting --conf 1.0. Working on a fix in #9431

[glenn-jocher]

@jianbaiwuqing good news 😃! Your original issue may now be fixed ✅ in PR #9431. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!