How to resolve this error-Invalid training data. For image, sequence-to-label, and feature classification tasks, responses must be categorical.

%% Totla RGB images=55, img4training size=35x60x3x55, YL=training Labels- 55x1
load traindata1.mat;

layers = [
    imageInputLayer([35 60 3])
    
    convolution2dLayer(3,8,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];

options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',4, ...
    'Shuffle','every-epoch', ...
    'Verbose',false, ...
    'Plots','training-progress');
YL=[ones(1,28) zeros(1,27)]';
net = trainNetwork(img4training,YL,layers,options);

Error using trainNetwork (line 184)

Invalid training data. For image, sequence-to-label, and feature classification tasks, responses must be categorical.

Error in IMP1 (line 37)

net = trainNetwork(img4training,YL,layers,options);

[zahoor m]

Invalid training data. For image, sequence-to-label, and feature classification tasks, responses must be categorical.

Answer 1

[Sindhu Karri]

Hii,

In the trainNetwork function the response input(YL) should be an categorical array, instead it is defined as an array.

Refer to below documentation links for more information on categorical array,trainNetwork.

categorical array

trainNetwork

[Shilpa Sonawane]

Yes mam,

I have done it as a categorical & it works.

Thank you so much

[Olawale]

Hello Shilpa, how did you fix it as categorical?

[Shilpa Sonawane]

Hello,

categorical command is available in Matlab. Use following link to check how to use it.

https://in.mathworks.com/help/matlab/ref/categorical.html