10 fold validation using bag of features

I was wondering how I can implement a Bag of Features Algorithm on Matlab but using 10-fold Cross Validation on the training and testing sets and finding the average accuracy from this. Below is the code I have attempted to implement.

    % code
ims = imageDatastore(fullfile(setDir,categories),'LabelSource',...
 'foldernames');
 tbl = countEachLabel(ims);
 minimumSetCount = min(tbl{:,2}); %find the smallest amount of images in the categories
 ims = splitEachLabel(ims,minimumSetCount, 'randomize');
[trainingSet, testSet] = splitEachLabel(ims, 0.5, 'randomize'); %train only 30% of images

 p=10;
cv = crossvalind('Kfold', ims, p);
 for i=1:p
   testSet = (cv == i);
   trainingSet = ~testSet;    

   SURFFcn = @exampleBagOfFeaturesExtractor;
   bag = bagOfFeatures(trainingSet, 'CustomExtractor', SURFFcn,  'VocabularySize', 500, 'StrongestFeatures', 0.5);
   categoryClassifier = trainImageCategoryClassifier(trainingSet,bag);
   confMatrix = evaluate(categoryClassifier, testSet);
 end

However, I receive this error when trying to implementing this. It says:

Array formation and parentheses-style indexing with objects of class 'matlab.io.datastore.ImageDatastore' is not allowed. Use objects of class 'matlab.io.datastore.ImageDatastore' only as scalars or use a cell array.

Can anyone help me to find a solution to this problem? Thanks