2D-CNN matlab

2D-CNN是指二维卷积神经网络，可以用于图像分类、目标检测等任务。在Matlab中，可以使用Deep Learning Toolbox来构建和训练2D-CNN模型。具体步骤包括数据预处理、网络设计、训练和测试等。以下是一个简单的示例代码：

% 加载数据
imds = imageDatastore('path/to/images','IncludeSubfolders',true,'LabelSource','foldernames');
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.7,'randomized');

% 设计网络
layers = [
    imageInputLayer([32 32 3])
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,64,'Padding','same')
    batchNormalizationLayer
    reluLayer
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];

% 训练网络
options = trainingOptions('adam','MaxEpochs',20,'MiniBatchSize',128,'ValidationData',imdsValidation,'Plots','training-progress');
net = trainNetwork(imdsTrain,layers,options);

% 测试网络
YPred = classify(net,imdsValidation);
YValidation = imdsValidation.Labels;
accuracy = sum(YPred == YValidation)/numel(YValidation);
disp(['Accuracy: ' num2str(accuracy)]);