How to improve the accuracy of some of the 80 classes for YoloV5?


I would like to have better accuracy for the bus and person classes of the COCO Dataset. I am using yolov5m network, I would not like to use other types of network like yolovx because they are not good for performance.
Can samples be added to improve accuracy without doing retraining from scratch ?
What’s the best way to do it?
p.s: I collected a lot of new images with persons and bus.


This forum talks more about updates and issues related to the TensorRT.
We recommend you to please reach out to Issues · ultralytics/yolov5 · GitHub to get better help.

Thank you.

1 Like