imds = imageDatastore('s3://cifar10cloud/cifar10/train',...'IncludeSubfolders',true,...'LabelSource','foldernames'); imdsTest = imageDatastore('s3://cifar10cloud/cifar10/test',...'IncludeSubfolders',true,...'LabelSource','foldernames'); [imdsTrain,imdsValidation] = splitEachLabel(imds,0.9);

imageSize = [32 32 3]; pixelRange = [-4 4]; imageAugmenter = imageDataAugmenter(...'RandXReflection',true,...'RandXTranslation',pixelRange,...'RandYTranslation',pixelRange); augmentedImdsTrain = augmentedImageDatastore(imageSize,imdsTrain,...'DataAugmentation',imageAugmenter,...'OutputSizeMode','randcrop');

imageSize = [32 32 3]; netDepth = 2;% netDepth controls the depth of a convolutional blocknetWidth = 16;% netWidth controls the number of filters in a convolutional blocklayers = [ imageInputLayer(imageSize) convolutionalBlock(netWidth,netDepth) maxPooling2dLayer(2,'Stride',2) convolutionalBlock(2*netWidth,netDepth) maxPooling2dLayer(2,'Stride',2) convolutionalBlock(4*netWidth,netDepth) averagePooling2dLayer(8) fullyConnectedLayer(10) softmaxLayer classificationLayer ];

miniBatchSizes = [64 128 256 512]; numMiniBatchSizes = numel(miniBatchSizes); trainedNetworks = cell(numMiniBatchSizes,1); accuracies = zeros(numMiniBatchSizes,1);

parforidx = 1:numMiniBatchSizes miniBatchSize = miniBatchSizes(idx); initialLearnRate = 1e-1 * miniBatchSize/256;% Scale the learning rate according to the mini-batch size.%定义培训选项。Set the mini-batch size.options = trainingOptions('sgdm',...'MiniBatchSize',miniBatchSize,...% Set the corresponding MiniBatchSize in the sweep.'Verbose',false,...% Do not send command line output.'InitialLearnRate',initialLearnRate,...% Set the scaled learning rate.'L2Regularization',1e-10,...“MaxEpochs”,30,...'Shuffle','every-epoch',...'ValidationData',imdsValidation,...'LearnRateSchedule','piecewise',...'LearnRateDropFactor',0.1,...'LearnRateDropPeriod',25);% Train the network in a worker in the cluster.net = trainNetwork(augmentedImdsTrain,layers,options);% To obtain the accuracy of this network, use the trained network to% classify the validation images on the worker and compare the predicted labels to the% actual labels.YPredicted = classify(net,imdsValidation); accuracies(idx) = sum(YPredicted == imdsValidation.Labels)/numel(imdsValidation.Labels);% Send the trained network back to the client.trainedNetworks{idx} = net;end

trainedNetworks

accuracies

[~, I] = max(accuracies); bestNetwork = trainedNetworks{I(1)}; YPredicted = classify(bestNetwork,imdsTest); accuracy = sum(YPredicted == imdsTest.Labels)/numel(imdsTest.Labels)

f = figure; f.Visible = true;fori=1:4 subplot(2,2,i) xlabel('Iteration'); ylabel('Training accuracy'); lines(i) = animatedline;end

D = parallel.pool.DataQueue; afterEach(D, @(opts) updatePlot(lines, opts{:}));

parforidx = 1:numel(miniBatchSizes) miniBatchSize = miniBatchSizes(idx); initialLearnRate = 1e-1 * miniBatchSize/256;% Scale the learning rate according to the miniBatchSize.%定义培训选项。设置一个输出功能ion to send data back% to the client each iteration.options = trainingOptions('sgdm',...'MiniBatchSize',miniBatchSize,...% Set the corresponding MiniBatchSize in the sweep.'Verbose',false,...% Do not send command line output.'InitialLearnRate',initialLearnRate,...% Set the scaled learning rate.'OutputFcn',@(state) sendTrainingProgress(D,idx,state),...% Set an output function to send intermediate results to the client.'L2Regularization',1e-10,...“MaxEpochs”,30,...'Shuffle','every-epoch',...'ValidationData',imdsValidation,...'LearnRateSchedule','piecewise',...'LearnRateDropFactor',0.1,...'LearnRateDropPeriod',25);% Train the network in a worker in the cluster. The workers send% training progress information during training to the client.net = trainNetwork(augmentedImdsTrain,layers,options);% To obtain the accuracy of this network, use the trained network to% classify the validation images on the worker and compare the predicted labels to the% actual labels.YPredicted = classify(net,imdsValidation); accuracies(idx) = sum(YPredicted == imdsValidation.Labels)/numel(imdsValidation.Labels);% Send the trained network back to the client.trainedNetworks{idx} = net;end

trainedNetworks

accuracies

[~, I] = max(accuracies); bestNetwork = trainedNetworks{I(1)}; YPredicted = classify(bestNetwork,imdsTest); accuracy = sum(YPredicted == imdsTest.Labels)/numel(imdsTest.Labels)

functionlayers = convolutionalBlock(numFilters,numConvLayers) layers = [ convolution2dLayer(3,numFilters,'Padding','same') batchNormalizationLayer reluLayer ]; layers = repmat(layers,numConvLayers,1);end

functionsendTrainingProgress(D,idx,info)ifinfo.State =="iteration"send(D,{idx,info.Iteration,info.TrainingAccuracy});endend

functionupdatePlot(lines,idx,iter,acc) addpoints(lines(idx),iter,acc); drawnowlimitratenocallbacksend