Starting R2016b MATLAB release:
You should be able to compile 'trainNetwork' and most command line functions (from both classical and deep learning networks) starting in R2016b.
Functions that cannot be compiled include the deep learning training "plot" function and all user interfaces.
Please refer the 'Neural Network Toolbox' product in this link for information on this:
Prior to R2016b release:
You can only compile a pre-trained network and use classify function to classify the test data.
So in order to compile the doc example below,
in releases prior to R2016b, please follow the steps below:
1. Run the example code in MATLAB
2. This will create the 'convnet' struct variable in your workspace. This is the pretrained network object. Save this to a mat file like below:
save 'model.mat' convnet
3. Also save the testImageData variable in the workspace to a mat file:
save 'testDigitData.mat' testDigitData
4. Then you can create a MATLAB function like below to be compiled into an executable that used the pretrained network to classify the test data.
function accuracy = runModelFromMATLAB()
load('model.mat');
load('testDigitData.mat')
YTest = classify(convnet,testDigitData);
TTest = testDigitData.Labels;
accuracy = sum(YTest == TTest)/numel(TTest)
end
5. Then create executable for this function with MATLAB compiler
