yolov1训练时loss为nan
lixiaoming0017 opened this issue · comments
lixiaoming0017 commented
您好,我在用yolov1的代码时候,用main.py训练,数据集合只用了VOC2007的数据,pytorch用的1.2,修改了total_loss += loss.data[0],改为total_loss += loss.item(),训练的时候loss一直是nan,别的参数没改,请问一下这是什么原因啊
boomboomgwx commented
我和你一样,不知道为啥
stale commented
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.(由于长期不活动,机器人自动关闭此问题,如果需要欢迎提问)