train the CNN for image classification by image in mat format

close all, clear all, clc;
output_folder=fullfile('datasets','New folder') ;  %creat file path
categories={'pituitary','meningioma','glioma'};
 imds=imageDatastore((fullfile(output_folder,categories)),'FileExtensions', '.mat','ReadFcn',@load,'LabelSource','foldernames');
  [trainingset, testset]=splitEachLabel(imds, 0.8,0.2);
layers = [
    ...];
  imageSize=layers(1).InputSize;
augmentedrainingset=augmentedImageDatastore (imageSize,...
     trainingset,'colorPreprocessing','gray2rgb');
 augmentedtestset=augmentedImageDatastore (imageSize,...
     testset,'colorPreprocessing','gray2rgb');
options = trainingOptions('sgdm', ...
     'InitialLearnRate',0.01, ...
 'MaxEpochs',10, ...
     'Shuffle','every-epoch', ...
    'ValidationData',testset, ...
    'ValidationFrequency',3, ...
    'MiniBatchSize',32,...
    'Verbose',false, ...
    'Plots','training-progress');
 net = trainNetwork(trainingset,layers,options);

Hi every one,

I try to trainng my CNN by image in mat format, but there is an error during that, which is

Error using trainNetwork (line 150)
Conversion to single from struct is not possible.
Error in classificationlayers (line 55)
 net = trainNetwork(trainingset,layers,options);
Caused by:
    Error using cast
    Conversion to single from struct is not possible.
    

What can i do to solve this problem please??