The conf parameter setting in the pose task.

[HXB-1997]

Search before asking

• I have searched the YOLOv8 issues and discussions and found no similar questions.

Question

In the pose detection task of YOLOv8, how can individual confidence thresholds be set for each keypoint? How can a lower limit for the conf parameter be set for all keypoints as a whole, similar to setting the conf parameter in the detect task?

Additional

No response

[glenn-jocher]

Hello! In YOLOv8 pose estimation tasks, individual keypoint confidence thresholds cannot be set directly via the model's configuration or command-line interface. Instead, the model uses a single confidence threshold for all keypoints.

To set a global confidence threshold for all keypoints, you can modify the conf parameter when calling the predict method, similar to other detection tasks. Here's an example using the Python interface:

from ultralytics import YOLO

# Load your model
model = YOLO('yolov8n-pose.pt')

# Run predictions with a global confidence threshold
results = model.predict('path/to/image.jpg', conf=0.25)

This sets a confidence threshold of 0.25 for all keypoints detected in the image. Adjust the conf value as needed to meet your specific requirements. 🌟

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

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 YOLO 🚀 and Vision AI ⭐

[HXB-1997]

I understand, each key point cannot set the confidence level individually. Thank you for your response.

[glenn-jocher]

@HXB-1997 you're welcome! If you have any more questions or need further assistance with YOLOv8, feel free to ask. We're here to help! 😊

For more detailed information on configuring and using YOLOv8, you can always refer to our documentation. Happy coding! 🚀