MATLAB: Is it possible to compile MATLAB files that call Neural Network Toolbox functions into stand-alone applications

ccodecompilerDeep Learning Toolboxexportgenerationjavaneuralnnnnetstandalone

I would like to generate a stand-alone application from MATLAB code that uses the Neural Network Toolbox.

Best Answer

The ability to deploy Neural Network Toolbox functions (including *training *functions such as train) to compiled applications was added in MATLAB Compiler Version 6.3 (R2016b). However, there are a few limitations regarding which Neural Network toolbox functions can be compiled in a stand-alone application. These limitations are listed here:

http://www.mathworks.com/products/compiler/compiler_support.html

It is possible to deploy only *pre-trained* network command line functions from the Neural Network toolbox in Compiler releases 4.0 (R14) through 6.2 (R2016a). For previous releases of MATLAB (R13 and earlier), please refer the following link:

http://www.mathworks.com/matlabcentral/answers/323265-how-do-i-compile-matlab-files-that-call-neural-network-toolbox-functions-into-stand-alone-applicatio

Related Solutions

MATLAB: How to compile a pre-trained neural network into a standalone application using the MATLAB Compiler 4.10 (R2009a)

The following script sets up the creation of a pre-trained network and stores it in a MAT-file ('pre_trained_net.mat').

clc
clear all
close all
P = [1 2 3 4 5];
T = [1 2 3 4 3];
net = newff(P,T,5);
net.trainParam.epochs = 50;
net = train(net,P,T);
save pre_trained_net net

The following function utilizing the pre-trained network can be compiled into a stand-alone application:

function compiled_network(input)
% Include Neural Network Toolbox dependencies.
% web([docroot '/toolbox/compiler/function.html'])
%#function network
% Load data.
load pre_trained_net
if ischar(input)
      input=str2num(input);
end
output = sim(net,input)
plot(input,output,'o')

The following command may be used to compile the above function into a stand-alone application:

mcc -m compiled_network

The compiled application may be called from the system command line as follows to generate output for new input:

compiled_network([1,2,3,4,5])

For your convenience, find attached 'pre_trained_net.mat' and 'compiled_network.exe'. The executable was compiled using MATLAB Compiler 4.10 (R2009a) on Windows XP. These files can always be created as described earlier.

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: How to compile a pre-trained neural network into a standalone application using the MATLAB Compiler 4.10 (R2009a)

MATLAB: How to train a feedfordward neural network with error weights

Related Question