How can i combine 3 datastore? and how can i improve accuracy

I have 64 image in datastores (imds), I wish augmet data by using imageDataAugmenter and denoisingImageDatastore and improve the validation accuracy.

Error using trainNetwork (line 165)

All tables in the bracketed expression must have the same number of rows.

Error in combindata (line 130)

net2 = trainNetwork(imdsCombined,layers,options);

Caused by:

Error using matlab.io.datastore.CombinedDatastore/read (line 109)

All tables in the bracketed expression must have the same number of rows.

imds = imageDatastore(fullfile(rootFolder, categories), 'LabelSource', 'foldernames');
inputSize = [64 64];
imds.ReadFcn = @(loc)imresize(imread(loc),inputSize);
imshow(preview(imds));
labelCount = countEachLabel(imds);
numClasses = height(labelCount);
%% Create training and validation sets
[imdsTrainingSet, imdsValidationSet] = splitEachLabel(imds, 0.7, 'randomize');
%% Build a simple CNN 
imageSize = [64 64 3];
% Specify the convolutional neural network architecture.
layers = [
    imageInputLayer(imageSize)
    
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
     reluLayer   
    
    convolution2dLayer(3,5,'Padding','same')
    batchNormalizationLayer
     reluLayer 

    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer

    fullyConnectedLayer(2)
    softmaxLayer
    classificationLayer]
%% Specify training options %   
options = trainingOptions('sgdm', ...
'MiniBatchSize',300, ...
    'MaxEpochs',500, ...
    'InitialLearnRate',1e-2, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsValidationSet, ...
    'ValidationFrequency',3, ...
    'Verbose',false, ...
    'L2Regularization',0.0001,...
    'Plots','training-progress');
%%%%%%************Augmented data**************************
%% Create augmented image data store
% Specify data augmentation options and values/ranges
 imageAugmenter = imageDataAugmenter( ...
    'RandRotation',[-20,20], ...
    'RandXTranslation',[-3 3], ...
    'RandYTranslation',[-3 3]);
% Apply transformations (using randomly picked values) and build augmented
% data store
augImds = augmentedImageDatastore(imageSize,imdsTrainingSet, ...
    'DataAugmentation',imageAugmenter);
dnimds = denoisingImageDatastore(imdsTrainingSet,...
    'PatchesPerImage',512,...
    'PatchSize',64,...
    'GaussianNoiseLevel',[0.01 0.1],...
    'ChannelFormat','rgb')


imdsCombined = combine(imds,augImds,dnimds)

% % (OPTIONAL) Preview augmentation results 
% batchedData = preview(augImds);
% figure, imshow(imtile(batchedData.input))
%     
% %% Train the network. 
net2 = trainNetwork(imdsCombined,layers,options);
%% Report accuracy of baseline classifier with image data augmentation
YPred = classify(net2,imdsValidationSet);
YValidation = imdsValidationSet.Labels;
augImdsAccuracy = sum(YPred == YValidation)/numel(YValidation);
%% Plot confusion matrix
figure, plotconfusion(YValidation,YPred)