pytorch-YOLOv4
pytorch-YOLOv4 copied to clipboard
different loss functions for loss_xy and loss_wh
May I ask why you use F.binary_cross_entropy for loss_xy while you use F.mse_loss for loss_wh? And, (1) why did you divide by 2 for loss_wh? (you didn't divide by 2 for loss_xy) (2) I thought that yolov4 uses CIoU loss for bbox regression (x, y, w, h), no?
Thank you for your help.
Hi. Same doubt here. Please let me know if you have any extra information regarding the same.