matlab解决svmtrain转化为fitcsvm函数的过程

源程序为：

TrainLabel = [zeros(length(TrainData_background),1); ...
        ones(length(TrainData_foreground),1)];

TrainData = [TrainData_background;TrainData_foreground];

model = svmtrain(TrainLabel, TrainData,'-t 1 -d 1');     
%svm调用出现问题 原函数为svmtrain '-t 1 -d 1'
preTrainLabel = svmpredict(TrainLabel, TrainData, model);
[m,n,k] = size(pic);
TestData = double(reshape(pic,m*n,k));
% whos TestData;
TestLabal = svmpredict(zeros(length(TestData),1), TestData, model);
ind = reshape([TestLabal,TestLabal,TestLabal],m,n,k);
ind = logical(ind);

因为近期重新装了系统，并且重新安装了matlab2018b出现提示svmtrain函数调用过期，需要更改为fitcsvm的提示，也跟着网上其他博客安装libsvm包，mex -setup，make,但还是没有解决我的问题

我就开始看fitcsvm的介绍网址，进行这两者的转换

TrainLabel = [zeros(length(TrainData_background),1); ...
        ones(length(TrainData_foreground),1)];

TrainData = [TrainData_background;TrainData_foreground];

SVMModel = fitcsvm( TrainData,TrainLabel,'KernelScale','auto','Standardize',true,...
    'OutlierFraction',0.05);     %设置5%的观察值是离群点
   
svInd = SVMModel.IsSupportVector;
    
[m,n,k] = size(pic);
TestData = double(reshape(pic,m*n,k));
% whos TestData;
TestLabal = predict(SVMModel,TestData );
ind = reshape([TestLabal,TestLabal,TestLabal],m,n,k);
ind = logical(ind);

 关键点在于：

1、输入的数据类型是不变的，但是位置需要调换。生成model

svmtrain:

model = svmtrain(TrainLabel, TrainData,'-t 1 -d 1');

fitcsvm:

SVMModel = fitcsvm( TrainData,TrainLabel,'KernelScale','auto','Standardize',true,...
    'OutlierFraction',0.05);     %设置5%的观察值是离群点

svInd = SVMModel.IsSupportVector;

2、调用模型

svmtrain:

TestLabal = svmpredict(zeros(length(TestData),1), TestData, model);

fitcsvm:

TestLabal = predict(SVMModel,TestData );