incorrect matrix size while training data

Question

Arpan Parikh 2020-6-17

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/549780-incorrect-matrix-size-while-training-data

回答： Raynier Suresh 2021-2-17

I am training a neural network with input [25x1x1].

I am taking input using imageInputLayer([25 1]).

My training data is sotred in the variable images which is of size [25x1x1x80000].

But when I run the program to train the network I get an error:

I dont know what is causing this error. My input dimensions match with the dimensions of my training data and everything else in the network seems fine.

Please help.

5 个评论
显示 3更早的评论隐藏 3更早的评论

Arpan Parikh 2020-6-17

Now I am getting the error:

The training images are of size 1x25x1 but the input layer expects images of size 25x1x1.

or

The training images are of size 1x1x25 but the input layer expects images of size 25x1x1.

Arpan Parikh 2020-6-17

It seems that the dimensions are right but matlab is unable to extract training samples for some reason

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Raynier Suresh 2021-2-17

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/549780-incorrect-matrix-size-while-training-data#answer_625377

Hi, check whether you have defined the architecture of your network correctly, you can do this by using the command "analyzeNetwork(layers)". For input layer size [25 1] and the training data size [25 1 1 80000] the trainNetwork function should work fine for example you can refer the code below.

layers = [imageInputLayer([25 1])
    convolution2dLayer(1,32)
    reluLayer
    fullyConnectedLayer(4)
    softmaxLayer
    classificationLayer];
options = trainingOptions('sgdm', ...
    'MaxEpochs',1,...
    'InitialLearnRate',1e-4, ...
    'Verbose',false, ...
    'Plots','training-progress');
Xtrain = rand(25,1,1,80000);
Ytrain = categorical(randi(4,80000,1));
net = trainNetwork(Xtrain,Ytrain,layers,options);