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

Please help me out with this

Thanks in Advance

Below is the code

clc;
clear all;
imds = imageDatastore('/MATLAB Drive/HGG','IncludeSubfolders',true,'FileExtensions','.nii','LabelSource','foldernames');
imds.ReadFcn = @niftiread;
imds1 = transform(imds,@(x)imgaussfilt(x,2));
patchds = randomPatchExtractionDatastore(imds,imds1,[100 100]);
data = read(patchds);
layers = [
    image3dInputLayer([240 240 155 1],"Name","image3dinput")
    convolution3dLayer([3 3 3],32,"Name","conv3d_1","Padding","same")
    reluLayer("Name","relu1")
    batchNormalizationLayer("Name","batchnorm_1")
    maxPooling3dLayer([5 5 5],"Name","maxpool3d_1","Padding","same")
    convolution3dLayer([3 3 3],32,"Name","conv3d_2","Padding","same")
    reluLayer("Name","relu2")
    batchNormalizationLayer("Name","batchnorm_2")
    maxPooling3dLayer([5 5 5],"Name","maxpool3d_2","Padding","same")
    convolution3dLayer([3 3 3],32,"Name","conv3d_3","Padding","same")
    reluLayer("Name","relu3")
    convolution3dLayer([3 3 3],32,"Name","conv3d_4","Padding","same")
    reluLayer("Name","relu4")
    convolution3dLayer([3 3 3],32,"Name","conv3d_5","Padding","same")
    reluLayer("Name","relu5")
    maxPooling3dLayer([5 5 5],"Name","maxpool3d_3","Padding","same")
    fullyConnectedLayer(2,"Name","fc_2")
    reluLayer("Name","relu6")
    dropoutLayer(0.5,"Name","drop6")
    fullyConnectedLayer(10,"Name","fc_1")
    reluLayer("Name","relu7")
    dropoutLayer(0.5,"Name","drop7")
    fullyConnectedLayer(2,"Name","fc_3")
    softmaxLayer("Name","prob")
    classificationLayer("Name","classoutput")];

options = trainingOptions('sgdm','MiniBatchSize',2,'MaxEpochs',2,'InitialLearnRate',1e-4,'Shuffle','every-epoch','Verbose',false,'Plots','training-progress');
net = trainNetwork(patchds,layers,options);

Error is

Error using trainNetwork (line 184)

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

Error in Ex (line 36)

net = trainNetwork(patchds,layers,options);

Answer 1

[yanqi liu]

yes，sir，please use the follow code to test

imds1 = transform(imds,@(x)imgaussfilt(x,2));

%change to

imds1 = imageDatastore('MerchData','IncludeSubfolders',true,'LabelSource','foldernames','ReadFcn',@myreadfcn);

%and the function is

function J = myreadfcn(filename)
I = niftiread(filename);
J = imgaussfilt(I,2);
end

[Max Walliam]

Files must be a valid string scalar, character vector, cell array of character vectors, string array, or a

matlab.io.datastore.FileSet.

[Walter Roberson]

Please show your current imageDatastore() call