I have a question about training object detection models especially using the YOLOv7 algorithm.

I use a Soccer Players Dataset from the Roboflow. The dataset is very unbalanced.

I trained the model using basic hyperparameters and it detects all objects on images but the predicted label is invalid. The model predicts everything as a player (but for example one person on an image is a referee).

How can I improve label prediction accuracy?

  • $\begingroup$ Maybe you should explain for how long you trained your model and what these basic hyper-parameters are. $\endgroup$
    – nbro
    Jan 29 at 23:52
  • $\begingroup$ I trained for 100 epochs, Basic hyperparameters are from the hyp.scratch.custom.yaml, but I wasn't changed values in this file. $\endgroup$
    – ofevy
    Jan 30 at 8:24


You must log in to answer this question.

Browse other questions tagged .