what is causes NaN values in the validation accuracy and loss from traning convolutional neural network and how to avoid it?

Question

Salma Hassan 2017-12-31

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/375090-what-is-causes-nan-values-in-the-validation-accuracy-and-loss-from-traning-convolutional-neural-n

评论： Ismail Cem Tüzün 2023-2-20

I USE this line in matlab code [trainedNet,traininfo] = trainNetwork(trainMatrix,Layers,opts);

so the information about validation and traning accuracy/loss are storage in the variable traininfo.. when i open this variable i found only the first value in iteration number 1 and also the last value but between them the value are NAN. how to avoid this problem you know i need the whole values for plotting the learning curve after that

3 个评论
显示 1更早的评论隐藏 1更早的评论

Salma Hassan 2018-1-1

first of all thanks for your respond can you give me an example about space at the beginning of value or number.sorry it is not clear enough

Javier Pinzón 2018-1-29

Hello As Has,

Sorry for the late response, but, with the info provide is very difficult to find what is the root of the problem, may you provide us the next information?:

- Definition of the layers declared

- Network Options declared

At the moment that information. In that way, we can find what causes the problem.

Best Regards

Javier

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Ignacio Arganda-Carreras 2018-10-17

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/375090-what-is-causes-nan-values-in-the-validation-accuracy-and-loss-from-traning-convolutional-neural-n#answer_341831

Hello As Has,

I found the answer in the documentation of trainingInfo : "Each field is a numeric vector with one element per training iteration. Values that have not been calculated at a specific iteration are represented by NaN." So you need to check the iterations multiple of your validation frequency, those should have a value different from NaN.