Translating linear SVM classification algorithm to C using MATLAB Coder

Question

I've trained a linear SVM classifier using the Classification Learner app, and exported the model to a .mat file. I'm attempting to translate this algorithm to C using MATLAB Coder, but am getting an error.

I'm not sure if I'm approaching the problem correctly, but my current approach is to load the .mat file as I would do in MATLAB, and then call the classification prediction function using values that are passed in (this assumes that using load() would normally work in MATLAB Coder, of which I'm not sure). When running the "Check for issues" step in MATLAB Coder, the following error is triggered:

Found unsupported class for variable using function 'load'. MATLAB class 'ClassificationSVM' found at 'classifier.trainedClassifier.ClassificationSVM' is unsupported.

Use the command 'whos -file classifierOptimal.mat' to view the variables in the MAT file.

It would appear that the MATLAB class used for classification is unsupported in MATLAB Coder.

How do I translate this classification algorithm for use outside of MATLAB?

carlosdc · Accepted Answer · 2016-04-05 20:08:57Z

0

There are two things here. It seems to me that you're trying to generate an executable with:

Loading an external mat file
External library that needs to be compiled in to your executable

I would read this article about finding mat files for the first issue: http://blogs.mathworks.com/loren/2008/08/11/path-management-in-deployed-applications/

I would carefully try to avoid dynamic (i.e. loaded at run time language constructs) while I grasp how the compiler works. Loading an instance from a MAT file asking for trouble.

You're trying to do too many things at the same time, simplify your approach and see what happens.

answered Apr 5, 2016 at 20:08

carlosdc

12.1k4 gold badges48 silver badges64 bronze badges

Sign up to request clarification or add additional context in comments.

3 Comments

Paul Van Wieren Over a year ago

Loading the .mat file seems to work; the issue is that the types defined in the .mat file aren't supported by Coder. Do you have any suggestions on a method that doesn't rely on using the .mat file?

carlosdc Over a year ago

Hard to say without knowing where: classifierOptimal.mat came from, who created it, and who wrote predictFcn, and can it be changed into a standard Matlab function or a mex file?

Paul Van Wieren Over a year ago

The .mat file was generated using the Classification Learner app.

Paul Van Wieren · Accepted Answer · 2016-04-05 20:20:54Z

0

Unfortunately, it appears that code generation for SVM routines is not supported:

MATLAB Answers

MATLAB Documentation

answered Apr 5, 2016 at 20:20

Paul Van Wieren

9851 gold badge7 silver badges11 bronze badges

Collectives™ on Stack Overflow

Translating linear SVM classification algorithm to C using MATLAB Coder

2 Answers 2

3 Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

3 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related