用两层长短时记忆神经网络（LSTM）对指定文件夹内的具有四个标签的图片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/image/folder', 'IncludeSubfolders', true, 'LabelSource', 'foldernames');
labels = imds.Labels;

% Split data into training and testing sets
[imdsTrain,imdsTest] = splitEachLabel(imds,0.7,'randomized');

% Define CNN architecture
inputSize = [224 224 3];
numClasses = 4;
layers = [
    imageInputLayer(inputSize)
    convolution2dLayer(3,64,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,128,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,256,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,512,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,512,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    fullyConnectedLayer(4096)
    reluLayer
    dropoutLayer(0.5)
    fullyConnectedLayer(4096)
    reluLayer
    dropoutLayer(0.5)
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];

% Define training options
options = trainingOptions('sgdm',...
    'MiniBatchSize',32,...
    'MaxEpochs',20,...
    'InitialLearnRate',1e-4,...
    'LearnRateSchedule','piecewise',...
    'LearnRateDropFactor',0.1,...
    'LearnRateDropPeriod',10,...
    'Shuffle','every-epoch',...
    'ValidationData',imdsTest,...
    'ValidationFrequency',10,...
    'Verbose',false,...
    'Plots','training-progress');

% Train CNN
net = trainNetwork(imdsTrain,layers,options);

% Test CNN on testing set
predictedLabels = classify(net,imdsTest);
confMat = confusionmat(labels(imdsTest.Files),predictedLabels);
confMatNorm = bsxfun(@rdivide,confMat,sum(confMat,2));

% Visualize confusion matrix
figure
imagesc(confMatNorm)
title('Normalized Confusion Matrix')
xlabel('Predicted Labels')
xticks(1:numClasses)
xticklabels(categories(imdsTest.Labels))
ylabel('True Labels')
yticks(1:numClasses)
yticklabels(categories(imdsTest.Labels))
colorbar

Note: This is an example code for training and testing a CNN on image data using MATLAB Deep Learning Toolbox. It is not specific for LSTM or text data.