Training process output

[rongvang17]

No description provided.

[rongvang17]

What does the parameter mAP50: 0.988 and 0.804 mean, and how to calculate it. Can you explain it to me?

[pderrenger]

mAP50 refers to the mean Average Precision at an IoU threshold of 0.50, indicating the model's precision in detecting objects. A score of 0.988 suggests high accuracy. The second value, 0.804, likely represents mAP at a different IoU threshold, such as mAP @rongvang17.5:0.95, which averages precision across multiple thresholds. For more details, you can check the YOLOv5 documentation.

[rongvang17]

mAP50 refers to the mean Average Precision at an IoU threshold of 0.50, indicating the model's precision in detecting objects. A score of 0.988 suggests high accuracy. The second value, 0.804, likely represents mAP at a different IoU threshold, such as mAP @rongvang17.5:0.95, which averages precision across multiple thresholds. For more details, you can check the YOLOv5 documentation.

Thank you very much for your answer

[pderrenger]

You're welcome! If you have any more questions about YOLOv5, feel free to ask. The YOLO community and Ultralytics team are always here to help.