MATLAB构建神经网络识别FashionMnist数据集（附代码）

Lee9085

已于 2024-03-13 16:01:19 修改

阅读量499

点赞数 5

文章标签：神经网络人工智能深度学习

于 2024-03-13 15:56:46 首次发布

本文链接：https://blog.csdn.net/m0_61053547/article/details/135230907

版权

数据集介绍：

FashionMNIST 是一个替代 MNIST 手写数字集 的图像数据集。它是由 Zalando（一家德国的时尚科技公司）旗下的研究部门提供。其涵盖了来自 10 种类别不同商品的正面图片。数据集链接：https://pan.quark.cn/s/c1e1f62059c5，部分图片如下所示：

使用多层感知机构建模型：

代码：

clear
clc
matlabroot = './FashionMnist';
digitDatasetPath = fullfile(matlabroot);
imds = imageDatastore(digitDatasetPath,'IncludeSubfolders',true,'LabelSource','foldernames');

numTrainFiles = 5000;
[imdsTrain,imdsValidation] = splitEachLabel(imds,numTrainFiles,'randomize');

layers = [
    imageInputLayer([28 28 1],"Name","imageinput")
    fullyConnectedLayer(256,"Name","fc")
    batchNormalizationLayer("Name","batchnorm")
    reluLayer("Name","relu")
    fullyConnectedLayer(128,"Name","fc_1")
    batchNormalizationLayer("Name","batchnorm_1")
    reluLayer("Name","relu_1")
    fullyConnectedLayer(64,"Name","fc_2")
    batchNormalizationLayer("Name","batchnorm_2")
    reluLayer("Name","relu_2")
    fullyConnectedLayer(10,"Name","fc_3")
    softmaxLayer("Name","softmax")
    classificationLayer("Name","classoutput")];

  options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',4, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsValidation, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress'); 

   net = trainNetwork(imdsTrain,layers,options); 
   YPred = classify(net,imdsValidation);
   YValidation = imdsValidation.Labels;
   accuracy = sum(YPred == YValidation)/numel(YValidation);
   disp(accuracy);

模型结构：

运行结果：

使用卷积神经网络构造模型：

代码：

clear
clc
matlabroot = './FashionMnist';
digitDatasetPath = fullfile(matlabroot);
imds = imageDatastore(digitDatasetPath,'IncludeSubfolders',true,'LabelSource','foldernames');

numTrainFiles = 5000;
[imdsTrain,imdsValidation] = splitEachLabel(imds,numTrainFiles,'randomize');

layers = [
    imageInputLayer([28 28 1],"Name","imageinput")
    convolution2dLayer([3 3],8,"Name","conv","Padding","same")
    batchNormalizationLayer("Name","batchnorm")
    reluLayer("Name","relu")
    maxPooling2dLayer([5 5],"Name","maxpool","Padding","same")
    convolution2dLayer([3 3],16,"Name","conv_1","Padding","same")
    batchNormalizationLayer("Name","batchnorm_1")
    reluLayer("Name","relu_1")
    fullyConnectedLayer(10,"Name","fc_3")
    softmaxLayer("Name","softmax")
    classificationLayer("Name","classoutput")];

  options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',4, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsValidation, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress'); 

   net = trainNetwork(imdsTrain,layers,options); 
   YPred = classify(net,imdsValidation);
   YValidation = imdsValidation.Labels;
   accuracy = sum(YPred == YValidation)/numel(YValidation);
   disp(accuracy);