yolov8 cannot show P， R，mAP

[eggmakers]

Search before asking

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

Question

My yolov8 shows a warning when training the UA-DETRAC dataset: WARNING no labels found in detect set, can not compute metrics without labels, and the P, R, and mAP values are zero. My configuration is RTX4060, CuDA version 11.7, and python version 3.8

Additional

No response

[github-actions]

👋 Hello @eggmakers, thank you for raising an issue about Ultralytics HUB 🚀! Please visit our HUB Docs to learn more:

• Quickstart. Start training and deploying YOLO models with HUB in seconds.
• Datasets: Preparing and Uploading. Learn how to prepare and upload your datasets to HUB in YOLO format.
• Projects: Creating and Managing. Group your models into projects for improved organization.
• Models: Training and Exporting. Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment.
• Integrations. Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle.
• Ultralytics HUB App. Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device.
  • iOS. Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads.
  • Android. Explore TFLite acceleration on mobile devices.
• Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.

If this is a 🐛 Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.

If this is a ❓ Question, please provide as much information as possible, including dataset, model, environment details etc. so that we might provide the most helpful response.

We try to respond to all issues as promptly as possible. Thank you for your patience!

[UltralyticsAssistant]

@eggmakers it seems like the issue pertains to a lack of label data in your detect set. YOLOv8 is giving a warning because it can't find any labels in your detect set, so it can't compute the Precision, Recall, and mAP metrics. These metrics require ground truth labels for comparison with your model's predictions, to assess its performance.

You might want to re-check your dataset for any inconsistencies or errors in the label files. Be sure that any annotations correspond correctly to the images during training. It's also worth re-verifying if the path to your labels is directed correctly in your dataset.yaml file.

If you've recently changed, updated, or moved your data, it could have led to this issue. Always ensure you have the correct and full paths wherever your data is being accessed.

Let me know if this helps or if you have additional questions.

[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 ⭐