Open AlexeyAB opened 4 years ago
Thank you. Im preparing push a newer version with improvements, which include CIoU loss and yolov4-tiny
Thank you. Im preparing push a newer version with improvements, which include CIoU loss and yolov4-tiny
the loss is nan, has this problem been solved ?
Thank you. Im preparing push a newer version with improvements, which include CIoU loss and yolov4-tiny
the loss is nan, has this problem been solved ?
I updated mish activation to fix nan loss issue.
Thank you. Im preparing push a newer version with improvements, which include CIoU loss and yolov4-tiny
the loss is nan, has this problem been solved ?
I updated mish activation to fix nan loss issue.
great !!
@hunglc007 Hi, Are you planning to implement CIoU?
Examples:
C: https://github.com/AlexeyAB/darknet/blob/a71b9a6e9a009cf94900c53deb344c5204835700/src/box.c#L233-L256
Matlab: https://github.com/Zzh-tju/DIoU/blob/master/simulation%20experiment/dCIOU.m
Python: https://github.com/VCasecnikovs/Yet-Another-YOLOv4-Pytorch/blob/2e18612e1852abbf35b4dac55a00f2a3b2d814ed/model.py#L527-L561
Python: https://github.com/ultralytics/yolov3/blob/eca5b9c1d36e4f73bf2f94e141d864f1c2739e23/utils/utils.py#L262-L282
Desctiption: https://medium.com/@jonathan_hui/yolov4-c9901eaa8e61