How to deploy SVM on ARM Cortex-M processor
24 次查看（过去 30 天）
Micael Coutinho ，2019-1-1
评论： Walter Roberson ，2019-3-18
I have a project in which I have to deploy a SVM (support vector machine) model into an ARM Cortex-M processor. I have already successfully trained my SVM, but I don't know how to deploy it on my edge device (microcontroller). I know that there is a library for neural network (CMSIS NN), but it has little support, as far as I can see. Can anyone help?
Walter Roberson 2019-1-1
You do code generation on a https://www.mathworks.com/help/stats/classificationsvm.html ClassificationSVM object using https://www.mathworks.com/help/stats/classreg.learning.classif.compactclassificationsvm.predict.html predict().
In your interactive MATLAB session, you save() the classification model you trained. In the code for use on the deployed machine, you load() the model and predict() using it.
Micael Coutinho 2019-1-2
Walter Roberson 2019-3-18
I am not sure. You might have to alter that to use
yfit = predict(trainedClassifier, T2);
Signal Processing DSP System Toolbox Code Generation Code Generation for ARM Cortex-M and ARM Cortex-A Processors
Find more on Code Generation for ARM Cortex-M and ARM Cortex-A Processors in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!