三隐层深度信念网络对指定文件夹内的具有四个标签的图像进行分类并可视化混淆矩阵具体matlab

代码如下：

% Load image data and labels
imds = imageDatastore('path/to/folder', 'IncludeSubfolders', true, 'LabelSource', 'foldernames');
[imdsTrain, imdsTest] = splitEachLabel(imds, 0.7, 'randomize');
numClasses = numel(categories(imdsTrain.Labels));

% Define the deep belief network architecture
layers = [ ...
    imageInputLayer([28 28 3])
    convolution2dLayer(5, 20)
    reluLayer()
    maxPooling2dLayer(2, 'Stride', 2)
    convolution2dLayer(5, 50)
    reluLayer()
    maxPooling2dLayer(2, 'Stride', 2)
    fullyConnectedLayer(500)
    reluLayer()
    fullyConnectedLayer(numClasses)
    softmaxLayer()
    classificationLayer()];

% Train the deep belief network
options = trainingOptions('sgdm', ...
    'MaxEpochs', 20, ...
    'InitialLearnRate', 0.001, ...
    'MiniBatchSize', 128, ...
    'Plots', 'training-progress');
net = trainNetwork(imdsTrain, layers, options);

% Evaluate the trained network on the test set
YPred = classify(net, imdsTest);
YTest = imdsTest.Labels;
accuracy = sum(YPred == YTest) / numel(YTest);
fprintf('Test Set Accuracy: %.2f%%\n', accuracy * 100);

% Visualize the confusion matrix
figure;
plotconfusion(YTest, YPred);