Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
改良コード
imds = imageDatastore('/Users/mizuno/Documents/MATLAB/deeplearning/SimpleDeepLearning/trainingSet/','IncludeSubfolders',true,'LabelSource','foldernames');
labelCount = countEachLabel(imds)
perm = randperm(40000,20);
montage(imds, 'Indices', perm);
img = readimage(imds,1);
size(img)
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.8);
layers = [imageInputLayer([28 28 1])
convolution2dLayer(3,8,'Padding','same')
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer
fullyConnectedLayer(10)
softmaxLayer
classificationLayer];
options = trainingOptions('sgdm', ...
'InitialLearnRate',0.001, ...
'MaxEpochs',4, ...
'Shuffle','every-epoch', ...
'ValidationData',imdsValidation, ...
'ValidationFrequency',30, ...
'Verbose',false, ...
'Plots','training-progress');
net = trainNetwork(imdsTrain,layers,options);
YPred = classify(net,imdsValidation);
YValidation = imdsValidation.Labels;
accuracy = sum(YPred == YValidation)/numel(YValidation)
[numberconf, numbernames] = confusionmat(YValidation, YPred);
heatmap(numbernames, numbernames, numberconf);
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.