How to fix this error with Neural Network Classifier?

Question

Sa rah 2015-12-28

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/261890-how-to-fix-this-error-with-neural-network-classifier

评论： Sa rah 2015-12-30

I used these code lines to built a Neural Network classifier in a face recognition project:

knowing that: the size of the images = 60*80, number of classes=15, 90 images for train set and 75 for test set are used.

net = patternnet(10);
[net,tr] = train(net,feaVectors,labels); % feaVectors=4800*90 and labels=15*90
testY = net(mat_test); % mat_test=4800*75
[c,cm] = confusion(labels_test,testY);

but I have this error:

Out of memory. Type HELP MEMORY for your options.
Error in
[net,tr] = train(net,feaVectors,labels);

Can someone help me to solve this please?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Walter Roberson 2015-12-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/261890-how-to-fix-this-error-with-neural-network-classifier#answer_204526

Install more RAM. Use a 64 bit operating system and 64 bit MATLAB.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 2

Greg Heath 2015-12-30

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/261890-how-to-fix-this-error-with-neural-network-classifier#answer_204632

You need to find an algorithm for face recognition feature extraction to drastically reduce the size of the 4800-dim inputs.

Hope this helps.

Thank you for formally accepting my answer

Greg

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Sa rah 2015-12-30

ok, thank you for the answer, I'll try to find a feature extraction algorithm. Yet, when I reduce the dimensions of the feature vectors by changing the image size, I don't get a satisfying result, the true recognition rate is around 50% or less, and that's too low. I don't get why because I think the implementation is correct !! In fact, I use the same inputs with SVM and I get very satisfying results. can you help me in this ?

请先登录，再进行评论。