MATLAB Coder class not supported

I have the following code for an image classification function:

function out = NNet_Predict(in) %#codegen
persistent NNet;
    if isempty(NNet)
        NNet = coder.loadDeepLearningNetwork('C:\Users\iacev\Desktop\ImgClass\NNet.mat');
    end
out = classify(NNet,in);
end

and the corresponding test file that calls on the function:

clc;

newImage = imread(fullfile('C:\Users\iacev\Desktop\ImgClass\Prueba\106.jpg'));
imageSize = [256 256 3];
in = augmentedImageDatastore(imageSize, newImage, 'ColorPreprocessing','gray2rgb');

y = NNet_Predict(in);

disp(y)
sprintf('The subjects mask is %s', y)
figure
imshow(newImage)

When using MATLAB Coder, i get the following error:

what could I do to fix this?

[Walter Roberson]

It is true, that kind of data store is not supported for code generation.

https://www.mathworks.com/help/deeplearning/ref/augmentedimagedatastore.html

The limitations are discussed in https://www.mathworks.com/help/deeplearning/ref/seriesnetwork.classify.html#mw_9fc06d87-a72f-4e03-b313-c82a3b4c1a92

C++ code generation supports the following syntaxes:

• [YPred,scores] = classify(net,X)
• [YPred,scores] = classify(net,sequences)

That is, do not create an augmented store: do the imresize() yourself and pass the resized image in as image data directly.