0
$\begingroup$

I'm having trouble using Yolov8 to work properly. I have my own custom dataset and an online dataset that I am using. Yolov8 trains on these datasets. However, the only metric that converges is the cls_loss.

It seems like the model isn't giving me any sort of bounding boxes to compute box_loss. When I go into the results file, I can see that the model sees the labels and bounding box properly, so I'm not sure what is going wrong.

$\endgroup$
1
  • $\begingroup$ Please check bounding box format , Yolo algorithm required bounding box coordinates in (x, y, width, height) format. $\endgroup$ Apr 16, 2023 at 14:20

1 Answer 1

0
$\begingroup$

Make sure the 'classes' parameter in the yaml file is blank. classes: As that parameter will filter out the classes listed there. Meaning if you set classes: [], it will not take in any classes when performing the Non Max Suppression function.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.