Matlab深度学习—

Matlab&深度学习

0.重要的事情

之前我没有注意到Matlab版本的问题，给一些小伙伴造成了困扰，抱歉，以后我会详细说明的
最近很忙，大概率到明年才更新Matlab&深度学习(二),加油

1.为什么使用Matlab？

如今Python语言占据了深度学习，然而Matlab也是可以做的。

好奇心，尝鲜，学习
Matlab的优点：
- 使用应用程序和可视化工具创建、修改和分析深度学习架构
- 使用应用程序预处理数据，并自动对图像、视频和音频数据进行真值标注
- 在 NVIDIA® GPU、云和数据中心资源上加速算法，而无需专门编程
- 与基于 TensorFlow、PyTorch 和 MxNet 等框架的使用者开展协作
- 使用强化学习仿真和训练动态系统行为
- 从物理系统的 MATLAB 和 Simulink® 模型生成基于仿真的训练和测试数据

2.入门——手写数字识别

2.0环境介绍

【重要】Matlab 2019b版本以上包括Matlab 2019b，我不知道Matlab 2019a版本怎么样，小伙伴们知道的话请评论一下我会及时更新的
RTX 2060，其实其他显卡也可以，只要支持GPU计算即可
GPU支持

2.1手写数字图片集

MNIST是手写数字图片数据集，包含60000张训练样本和10000张测试样本。MNIST数据集来自美国国家标准与技术研究所，National Institute of Standards and Technology(NIST)，M是Modified的缩写。训练集是由来自250个不同人手写的数字构成，其中50%是高中学生，50%来自人口普查局的工作人员。测试集也是同样比例的手写数字数据。每张图片有28x28个像素点构成，每个像素点用一个灰度值表示，这里是将28*28的像素展开为一个一维的行向量(每行784个值)。图片标签为one-hot编码：0-9

重要：需要下载Mnist数据集

Mnist数据集下载链接

2.2Matlab读取Mnist数据集获取图像和标签

datapath = "./Mnist/";filenameImagesTrain = strcat(datapath, "train-images-idx3-ubyte");
filenameLabelsTrain = strcat(datapath, "train-labels-idx1-ubyte");
filenameImagesTest = strcat(datapath, "t10k-images-idx3-ubyte");
filenameLabelsTest = strcat(datapath, "t10k-labels-idx1-ubyte");XTrain = processMNISTimages(filenameImagesTrain);
YTrain = processMNISTlabels(filenameLabelsTrain);
XTest = processMNISTimages(filenameImagesTest);
YTest = processMNISTlabels(filenameLabelsTest);
% 处理Mnist数据集图像
function X = processMNISTimages(filename)[fileID,errmsg] = fopen(filename,'r','b');if fileID < 0error(errmsg);endmagicNum = fread(fileID,1,'int32',0,'b');if magicNum == 2051fprintf('\nRead MNIST image data...\n')endnumImages = fread(fileID,1,'int32',0,'b');fprintf('Number of images in the dataset: %6d ...\n',numImages);numRows = fread(fileID,1,'int32',0,'b');numCols = fread(fileID,1,'int32',0,'b');X = fread(fileID,inf,'unsigned char');X = reshape(X,numCols,numRows,numImages);X = permute(X,[2 1 3]);X = X./255;X = reshape(X, [28,28,1,size(X,3)]);X = dlarray(X, 'SSCB');fclose(fileID);
end
% 处理Mnist数据集标签
function Y = processMNISTlabels(filename)[fileID,errmsg] = fopen(filename,'r','b');if fileID < 0error(errmsg);endmagicNum = fread(fileID,1,'int32',0,'b');if magicNum == 2049fprintf('\nRead MNIST label data...\n')endnumItems = fread(fileID,1,'int32',0,'b');fprintf('Number of labels in the dataset: %6d ...\n',numItems);Y = fread(fileID,inf,'unsigned char');Y = categorical(Y);fclose(fileID);
end

运行结果：

Read MNIST image data...
Number of images in the dataset:  60000 ...Read MNIST label data...
Number of labels in the dataset:  60000 ...Read MNIST image data...
Number of images in the dataset:  10000 ...Read MNIST label data...
Number of labels in the dataset:  10000 ...

2.3网络设计——LeNet5

LeNet-5的网络模型如下图所示

网络模型具体参数如下表所示

网络层	卷积核尺寸	步长	填充	输出大小
输入层				32 * 32 * 1
卷积层1	5	1	0	28 * 28 * 6
最大池化层1	2	2	0	14 * 14 * 6
卷积层2	5	1	0	10 * 10 * 6
最大池化层2	2	2	0	5 * 5 * 16
全连接层1				1 * 1 * 120
全连接层2				1 * 1 * 84
全连接层3				1 * 1 * 10
Softmax层				1 * 1 * 10
分类层				1 * 1 * 10

2.4Matlab——LeNet5设计

在Matlab 2019b中的App中有一个App，名为Deep Network Designer，即深度网络设计师，打开它，就可以通过拖动神经网络的组件来设计深度网络了

下表给出Matlab网络设计师中常见组件的相关信息

组件	翻译
imageInputLayer	图像输入层
sequenceInputLayer	序列输入层
convolution2dLayer	卷积层
fullyConnectLayer	全连接层
reluLayer	relu层
leakyReluLayer	leakyRelu层
tanhLayer	tanhLayer层
eluLayer	eLu层
batchNormalizationLayer	BN层
dropoutLayer	dropout层
crossChannelNormalizationLayer	CCN层
averagePooling2dLayer	平均池化层
globalAveragePooling2dLayer	全局平均池化层
maxPooling2dLayer	最大池化层
additionLayer	加法层
depthConcatenationLayer	深度连接层
concatenationLayer	连接层
softmaxLayer	softmax层
classificationLayer	分类层
regressionLayer	回归层

LeNet5设计图

设计完网络后用分析工具进行分析

分析结果无误后，导出LeNet5网络代码

layers = [imageInputLayer([28 28 1],"Name","imageinput")convolution2dLayer([5 5],6,"Name","conv1","Padding","same")tanhLayer("Name","tanh1")maxPooling2dLayer([2 2],"Name","maxpool1","Stride",[2 2])convolution2dLayer([5 5],16,"Name","conv2")tanhLayer("Name","tanh2")maxPooling2dLayer([2 2],"Name","maxpool","Stride",[2 2])fullyConnectedLayer(120,"Name","fc1")fullyConnectedLayer(84,"Name","fc2")fullyConnectedLayer(10,"Name","fc")softmaxLayer("Name","softmax")classificationLayer("Name","classoutput")];

至此，LeNet5网络Matlab设计已完成

2.5训练LeNet5网络

在Matlab训练网络，可以使用以下代码来设置训练，详见注释。训练时如果可以使用GPU来加速，训练会很快完成

options = trainingOptions('sgdm', ... %优化器'LearnRateSchedule','piecewise', ... %学习率'LearnRateDropFactor',0.2, ... % 'LearnRateDropPeriod',5, ...'MaxEpochs',20, ... %最大学习整个数据集的次数'MiniBatchSize',128, ... %每次学习样本数'Plots','training-progress'); %画出整个训练过程doTraining = true; %是否训练
if doTrainingtrainNet = trainNetwork(XTrain, YTrain,layers,options);% 训练网络，XTrain训练的图片，YTrain训练的标签，layers要训练的网% 络，options训练时的参数
end
save Minist_LeNet5 trainNet %训练完后保存模型
yTest = classify(trainNet, XTest); % 测试训练后的模型
accuracy = sum(yTest == YTest)/numel(YTest); %模型在测试集的准确率

2.6训练结果与测试

训练结果

测试模型
首先，给出测试示例图片

测试代码，详见注释

test_image = imread('5.jpg');
shape = size(test_image);
dimension=numel(shape);
if dimension > 2test_image = rgb2gray(test_image); %灰度化
end
test_image = imresize(test_image, [28,28]); %保证输入为28*28
test_iamge = imbinarize(test_image,0.5); %二值化
test_image = imcomplement(test_image); %反转，使得输入网络时一定要保证图片
% 背景是黑色，数字部分是白色
imshow(test_image);load('Minist_LeNet5');
% test_result = Recognition(trainNet, test_image);
result = classify(trainNet, test_image);
disp(test_result);

结果输出为：5，成功

5.完整的目录结构

3.完整的训练代码

%% 需要数据集 %%
datapath = "./Mnist/";filenameImagesTrain = strcat(datapath, "train-images-idx3-ubyte");
filenameLabelsTrain = strcat(datapath, "train-labels-idx1-ubyte");
filenameImagesTest = strcat(datapath, "t10k-images-idx3-ubyte");
filenameLabelsTest = strcat(datapath, "t10k-labels-idx1-ubyte");XTrain = processMNISTimages(filenameImagesTrain);
YTrain = processMNISTlabels(filenameLabelsTrain);
XTest = processMNISTimages(filenameImagesTest);
YTest = processMNISTlabels(filenameLabelsTest);%% LeNet网络 %%
LeNet = [imageInputLayer([28 28 1],"Name","imageinput")convolution2dLayer([5 5],6,"Name","conv1","Padding","same")tanhLayer("Name","tanh1")maxPooling2dLayer([2 2],"Name","maxpool1","Stride",[2 2])convolution2dLayer([5 5],16,"Name","conv2")tanhLayer("Name","tanh2")maxPooling2dLayer([2 2],"Name","maxpool","Stride",[2 2])fullyConnectedLayer(120,"Name","fc1")fullyConnectedLayer(84,"Name","fc2")fullyConnectedLayer(10,"Name","fc")softmaxLayer("Name","softmax")classificationLayer("Name","classoutput")];%% 训练LeNet %%
options = trainingOptions('sgdm', ... %优化器'LearnRateSchedule','piecewise', ... %学习率'LearnRateDropFactor',0.2, ... % 'LearnRateDropPeriod',5, ...'MaxEpochs',20, ... %最大学习整个数据集的次数'MiniBatchSize',128, ... %每次学习样本数'Plots','training-progress'); %画出整个训练过程doTraining = true; %是否训练
if doTrainingtrainLeNet = trainNetwork(XTrain, YTrain,LeNet,options);% 训练网络，XTrain训练的图片，YTrain训练的标签，layers要训练的网% 络，options训练时的参数
end
save Minist_LeNet5 trainLeNet %训练完后保存模型
yTest = classify(trainLeNet, XTest); % 测试训练后的模型
accuracy = sum(yTest == YTest)/numel(YTest); %模型在测试集的准确率%% 函数 %%
%% 处理Mnist数据集图像 %%
function X = processMNISTimages(filename)[fileID,errmsg] = fopen(filename,'r','b');if fileID < 0error(errmsg);endmagicNum = fread(fileID,1,'int32',0,'b');if magicNum == 2051fprintf('\nRead MNIST image data...\n')endnumImages = fread(fileID,1,'int32',0,'b');fprintf('Number of images in the dataset: %6d ...\n',numImages);numRows = fread(fileID,1,'int32',0,'b');numCols = fread(fileID,1,'int32',0,'b');X = fread(fileID,inf,'unsigned char');X = reshape(X,numCols,numRows,numImages);X = permute(X,[2 1 3]);X = X./255;X = reshape(X, [28,28,1,size(X,3)]);X = dlarray(X, 'SSCB');fclose(fileID);
end
%% 处理Mnist数据集标签 %%
function Y = processMNISTlabels(filename)[fileID,errmsg] = fopen(filename,'r','b');if fileID < 0error(errmsg);endmagicNum = fread(fileID,1,'int32',0,'b');if magicNum == 2049fprintf('\nRead MNIST label data...\n')endnumItems = fread(fileID,1,'int32',0,'b');fprintf('Number of labels in the dataset: %6d ...\n',numItems);Y = fread(fileID,inf,'unsigned char');Y = categorical(Y);fclose(fileID);
end

4.完整的测试代码以及测试结果

test_image = imread('5.jpg');
shape = size(test_image);
dimension = numel(shape);
if dimension > 2test_image = rgb2gray(test_image); %灰度化
end
test_image = imresize(test_image, [28,28]); %保证输入为28*28
test_iamge = imbinarize(test_image,0.5); %二值化
test_image = imcomplement(test_image); %反转，使得输入网络时一定要保证图片、
% 背景是黑色，数字部分是白色
imshow(test_image);load('Minist_LeNet5');
% test_result = Recognition(trainNet, test_image);
test_result = classify(trainLeNet, test_image);
disp(test_result);

结束语

这个文章会适时更新的，欢迎大家学习，参考，评论，遇到问题在可以评论里Q我，当然关于“我的训练为啥不能用GPU这种玄学问题”，我能试着给予解答，但不保证能解决你的问题，或许可以用CPU来训练网络，不过我没试。可以看到Matlab在设计一些网络时还是很方便的——通过拖拖拽拽，哈哈，希望Matlab能引入更多的网络层组件，来使我们可以更好更方便地设计深度网络