Neural Network Function does not work in Stand-Alone Application

3 views (last 30 days)
Hi, dear all. Recently, I’m working on develop a GUI user interface and to compile the code into the PC standalone application.
In the model, I incorporated an ensemble of artificial neural network. The network has been trained and save in a mat file. Every time, I just use function 'predictFcn' to run neural network with my input data.
function startupFcn(app)
global appnet;
appnet = load('myModel1.mat');
end
function PredictMLFFRButtonPushed(app, event)
T = Inputdata;
ypred = appnet.trainedModel.predictFcn(T)
end
All the codes work well in Matlab environment, but when we compile them into standalone application; it seems that the neural network toolbox cannot be complied into the standalone application.
I have no idea how to make my executive application works, really need someone who experience this help me out. Hope hears you soon. Thanks!!!!!

Accepted Answer

Steven Lord
Steven Lord on 27 Dec 2019
Edited: Steven Lord on 27 Dec 2019
There's no indication to the dependency analysis MATLAB Compiler performs to determine what needs to be included in your application that it needs to include the Neural Network Toolbox functionality. You need to tell it to include that functionality using one of the techniques shown in the "Fixing Callback Problems: Missing Functions" section on this documentation page.
  1 Comment
Umair Yousaf
Umair Yousaf on 27 Dec 2019
Thank you so much Sir 'Steven Lord' for pointing out this. I was just stuck.Thanks again for your kind help

Sign in to comment.

More Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Products


Release

R2019b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!