How to find the sensitivity and specificity from the confusion matrix?

2 次查看（过去 30 天）
Win Sheng Liew
Win Sheng Liew 2018-9-28
评论： Win Sheng Liew 2018-9-28
  2 个评论
Win Sheng Liew
Win Sheng Liew 2018-9-28
global net imageSize featureLayer classifier
f = waitbar(0,'Please wait...');
rootFolder = fullfile('c:\', 'Users', 'Ws Liew', 'Documents', 'MATLAB', 'Dataset'); categories = {'normal', 'abnormal'}; imds = imageDatastore(fullfile(rootFolder, categories), 'LabelSource','foldernames');
tb1 = countEachLabel(imds)
minSetCount = 0.6;
imds = splitEachLabel(imds, minSetCount, 'randomize');
normal = find(imds.Labels == 'normal', 1); abnormal = find(imds.Labels == 'abnormal', 1);
str = {'Select a CNN Architectures: '}; list = {'GoogLeNet','AlexNet','ResNet','VGG-16','VGG-19'}; [indx,tf] = listdlg('PromptString', str, 'ListSize', [200 130], 'SelectionMode', 'single', 'ListString', list);
waitbar(.25,f,'Loading Pre-trained Network');
if indx == 1 net = googlenet(); featureLayer = 'loss3-classifier';
elseif indx == 2 net = alexnet(); featureLayer = 'fc8';
elseif indx == 3 net = resnet50(); featureLayer = 'fc1000';
elseif indx == 4 net = vgg16(); featureLayer = 'fc8';
else indx == 5 net = vgg19(); featureLayer = 'fc8';
end
net.Layers
net.Layers(1)
net.Layers(end)
numel(net.Layers(end).ClassNames)
waitbar(.4,f,'Training and Testing Image Datasets');
[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); w1 = imresize(w1,5);
trainingFeatures = activations(net, augmentedTrainingSet, featureLayer, 'MiniBatchSize', 32, 'OutputAs', 'columns');
trainingLabels = trainingSet.Labels;
waitbar(.65,f,'SVM Classifier Training');
classifier = fitcecoc(trainingFeatures, trainingLabels, 'Learners', 'Linear', 'Coding', 'onevsall', 'ObservationsIn', 'columns');
testFeatures = activations(net, augmentedTestSet, featureLayer, 'MiniBatchSize', 32, 'OutputAs', 'columns');
predictedLabels = predict(classifier, testFeatures, 'ObservationsIn', 'columns');
testLabels = testSet.Labels;
confMat = confusionmat(testLabels, predictedLabels);
confMat = bsxfun(@rdivide,confMat,sum(confMat,2))

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Classification 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by