conf_thres increased and then recall increases, data problem or others ?

[carptainhao]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hello, when I use val.py to test badcase data, I increase conf_thres and recall increases. I have not encountered such a problem on the original divided test set. Is this a data problem?

Additional

No response

[glenn-jocher]

@carptainhao val.py is invalid for any confidence threshold higher than the default. This is displayed to users here:

yolov5/val.py

Lines 364 to 365 in 9a7f289

	if opt.conf_thres > 0.001: # https://github.com/ultralytics/yolov5/issues/1466
	LOGGER.info(f'WARNING: confidence threshold {opt.conf_thres} >> 0.001 will produce invalid mAP values.')

[carptainhao]

But if i increase the confidence threshold, the result of recall is also invalid?

@carptainhao val.py is invalid for any confidence threshold higher than the default. This is displayed to users here:

yolov5/val.py

Lines 364 to 365 in 9a7f289

	if opt.conf_thres > 0.001: # https://github.com/ultralytics/yolov5/issues/1466
	LOGGER.info(f'WARNING: confidence threshold {opt.conf_thres} >> 0.001 will produce invalid mAP values.')

[glenn-jocher]

@carptainhao I don't know. In any case P and R are computed for all confidences and plotted as curves by val.py, i.e.:

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!