the loss is nan
bbbeach opened this issue · comments
bbbeach commented
I train the yolov3 model with voc2007 and voc 2012.In the second epoch,the loss turn up nan
Jianhua Yang commented
Could you tell what your batch size is?
bbbeach commented
my batch size is 16, using the original learning rate with warmup strategy
Jianhua Yang commented
Ok, I see. I will check the nan problem. Before that, you can try my another YOLO project: https://github.com/yjh0410/yolov2-yolov3_PyTorch. @bbbeach
bbbeach commented
thanks