i was getting an error as unrecognised method,property or field 'Labels' for class 'augmented​ImageDatas​tore' for image classification can anybody help me with this error

clear all;

imds = imageDatastore('TRAINING',...

'IncludeSubfolders',true, ...

'LabelSource','foldernames');

imdsTest = imageDatastore('TESTING',...

'IncludeSubfolders',true, ...

'LabelSource','foldernames');

clear labels;

labelCount = countEachLabel(imds)

img = readimage(imds,1);

size(img)

[imdsTrain,imdsTesting] = splitEachLabel(imds,600,'randomize');

inputSize = [256 256 1];

imdsTrain = augmentedImageDatastore(inputSize, imdsTrain,'ColorPreprocessing','rgb2gray');

imdsTesting = augmentedImageDatastore(inputSize, imdsTesting,'ColorPreprocessing','rgb2gray');

numClasses = 2;

layers = [

imageInputLayer(inputSize)

convolution2dLayer(5,20)

batchNormalizationLayer

reluLayer

fullyConnectedLayer(numClasses)

softmaxLayer

classificationLayer];

options = trainingOptions('sgdm', ...

'InitialLearnRate',0.05,...

'MaxEpochs',15, ...

'ValidationData',imdsTesting, ...

'ValidationFrequency',30, ...

'Verbose',false, ...

'Plots','training-progress');

net = trainNetwork(imdsTrain,layers,options);

YPred = classify(net,imdsTesting);

YTested = imdsTesting.Labels;

accuracy = mean(YPred == YTested);

Answer 1

[T.Nikhil kumar]

Hey Hanisha!

I understand that you’re facing an error while finding the accuracy of the network you trained.

In this line,

 accuracy = mean(YPred == YTested);

You have compared the labels of the ground truth test data and predicted data.

Here, I would like to point that the augmentedImageDatastore() does not record the labels of the input data store.

You currently have

 imdsTesting = augmentedImageDatastore(inputSize, imdsTesting,'ColorPreprocessing','rgb2gray');

which takes imdsTesting(an image data store that has labels) as input, and you assign the augmented data store to the same variable.You need to know but augmentedImageDatastore does not carry the labels.So, you cannot access any lables when you write ,

 imdsTesting.Labels

If you store the augmented datastore in a different variable like

 imdsTestingAug = augmentedImageDatastore(inputSize, imdsTesting,'ColorPreprocessing','rgb2gray');

then when you run

 accuracy = mean(YPred == imdsValidation.Labels)

you will refer to the unaugmented data store that still contains the labels.