Best iou,confidence threshold for train and inference

[Miho-an-kou]

Search before asking

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

Question

1. How to find the best IOU threshold of custom dataset?
2. How to calculate the most appropriate confidence threshold under the condition of good precision and recall for inference?
   Thanks for advice!

Additional

No response

[glenn-jocher]

@Miho-an-kou select max F1 curve confidence from the val.py plots, i.e. about 0.35 here following YOLOv5s VOC training:

[Miho-an-kou]

@Miho-an-kou select max F1 curve confidence from the val.py plots, i.e. about 0.35 here following YOLOv5s VOC training:

Thanks

Similarly, is the best IOU in the following PR_curve generated by val.py is 0.5?

[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 ⭐!