training stops due to NaN loss value

12 次查看（过去 30 天）

Shoaib Ali 2022-8-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1782970-training-stops-due-to-nan-loss-value

评论： Shoaib Ali 2022-8-26

The training process stops due NaN loss... How to avoid this to complete the training ..and what is the possible issue that causses..

5 个评论
显示 3更早的评论隐藏 3更早的评论

Shoaib Ali 2022-8-23

Weighted cross entropy loss

Chunru 2022-8-23

try "dbstop error" and then run the program. Check if the network output is 0. There might be a problem if network output is 0 since entropy loss has term of T*log(Y) where T is target and Y is the network output.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Shoaib Ali 2022-8-24

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1782970-training-stops-due-to-nan-loss-value#answer_1031740

Can you explain, where to use this inside the loss funtion or before the training command??

2 个评论
显示无隐藏无

Chunru 2022-8-25

"dbstop error" can be used in command line before you train the network. Then it should stop when error occurs and then you check out what is wrong at which part of program.

Shoaib Ali 2022-8-26