How to improve the accuracy of some of the 80 classes in the Coco dataset for YoloV5? #10894
Unanswered
MarcoPrassel
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello everyone, I would like to have better accuracy for the bus and person classes. I am using yolov5m network, I would not like to use other types of network like yolovx because they are not good for performance. I was thinking of adding images to the COCO dataset and doing the retrain from the yolov5m weights. Will this lead to overfitting?
Can you suggest other solutions?
Beta Was this translation helpful? Give feedback.
All reactions