How to classify a folder of images after training network

Question

Nathnael Esayas Bulti 2022-4-11

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1693430-how-to-classify-a-folder-of-images-after-training-network

回答： Walter Roberson 2022-4-11

I am trying to classify a whole folder of images into 2 classes (eg. cats and dogs) and then I want to save the images classified in one class (eg. dogs).

So, in the last bit of the code I was able to classify 1 image at a time but would like to do it for multiple images and then save the images of one class.

outputFolder = fullfile('DataToClean');
rootFolder = fullfile(outputFolder, 'categories');
categories = {'Cars', 'NotCars'};
imds = imageDatastore(fullfile(rootFolder, categories),'LabelSource','foldernames');
tbl = countEachLabel(imds);
cars = find(imds.Labels == 'Cars',1);
notcars = find(imds.Labels == 'NotCars',1);
% figure
% subplot(2,2,1);
% imshow(readimage(imds,cars));
% subplot(2,2,2);
% imshow(readimage(imds,notcars));
net = resnet50();
% figure
% plot(net)
% title('Architecture Of ResNet-50')
% set(gca,'YLim',[150 170]);
net.Layers(1);
net.Layers(end);
numel(net.Layers(end).ClassNames);
[trainingSet, testSet] = splitEachLabel(imds, 0.3, 'randomize');
imageSize = net.Layers(1).InputSize;
augmentedTrainingSet = augmentedImageDatastore(imageSize,...
    trainingSet, 'colorPreprocessing', 'gray2rgb');
augmentedTestSet = augmentedImageDatastore(imageSize,...
    testSet, 'colorPreprocessing', 'gray2rgb');
w1 = net.Layers(2).Weights;
w1 = mat2gray(w1);
featureLayer = 'fc1000';
trainingFeatures = activations(net, augmentedTrainingSet,...
    featureLayer, 'MiniBatchSize', 32, 'Outputas', 'columns');
trainingLabels = trainingSet.Labels;
classifier = fitcecoc(trainingFeatures, trainingLabels,...
    'Learner', 'Linear', 'ObservationsIn', 'columns');
testFeatures = activations(net, augmentedTestSet,...
    featureLayer, 'MiniBatchSize', 32, 'Outputas', 'columns');
predictLabels = predict(classifier, testFeatures, 'ObservationsIn', 'columns');
testLabels = testSet.Labels;
confMat = confusionmat(testLabels, predictLabels);
confMat = bsxfun(@rdivide, confMat, sum(confMat,2));
mean(diag(confMat));
newImage = imread(fullfile('test101.jpg'));
ds = augmentedImageDatastore(imageSize,...
    newImage, 'colorPreprocessing', 'gray2rgb');
imageFeatures = activations(net, ds,...
    featureLayer, 'MiniBatchSize', 32, 'Outputas', 'columns');
imLabels = predict(classifier, imageFeatures, 'ObservationsIn', 'columns');