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

38 ビュー (過去 30 日間)
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 件のコメント
Salma Hassan
Salma Hassan 2018 年 1 月 1 日
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
Javier Pinzón 2018 年 1 月 29 日
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

サインインしてコメントする。

回答 (3 件)

Ignacio Arganda-Carreras
Ignacio Arganda-Carreras 2018 年 10 月 17 日
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.

aybike pirol elmas
aybike pirol elmas 2020 年 6 月 23 日
Merhaba,
Ben de bu problemi yaşadım.
'ValidationFrequency' 1 olarak yazdığımda, ... sorun kayboldu. Artık NAN değeri yok.

mohammed mahmoud
mohammed mahmoud 2020 年 6 月 24 日
The main problem is the vanishing gradient. It can be solved with adjust suitable learning rate value

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by