some questions about the 'datasets' and 'yolo_loss' code about yolov3 HOT 2 CLOSED

Thank you so much, you are so careful, thanks again.
1、you are right , it's a bug. it should be min
2、i think this case is low probability，if it happens, i think no influence.but add a condition is better.
3、'Bag of Freebies' has three versions, this code follows v1
4、bbox_loss_scale follows the darknet, and GIOU don't have it.the reason for using it is to balance the impact of different scale boxes on the loss. this code only use one factor, no scale factor(alpha is 1.0) in the folcal loss, but worth to try as the paper.

from yolov3.

thanks for your reply. I found the bbox_loss_scale code in the darknet https://github.com/pjreddie/darknet/blob/master/src/yolo_layer.c line 219. For confidence loss, I will check the balance problem.

from yolov3.