'When to stop training a object detection model ( YOLOV5 )
Hi I have three metrics on validation, obj_loss, vls_loss and box_loss, which one I should look at when deciding the timing to stop the model training?
Solution 1:[1]
In theory all three should start increasing at the same time, in practice it is difficult to achieve. I recommend that you see these issues on github.
[1]: <https://github.com/ultralytics/yolov5/issues/5199
[2]: <https://github.com/ultralytics/yolov5/issues/6731
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | Claudio Russo |