How I can add more hidden layers on the nftool code that I exported from the nnstart GUI?
15 views (last 30 days)
Show older comments
Caio Custódio
on 14 Sep 2017
Edited: sally abdulaziz
on 24 Sep 2023
Since I don't know much about how to implement a network using command line, I tried using the GUI from NNSTART and exported the code so I could try to figure out how to make the changes I need. the problems is that I don't how to add more layers/neurons, even more ephocs.
Here is the code I got from my first attempt:
% Solve an Input-Output Fitting problem with a Neural Network
% Script generated by Neural Fitting app
% Created 13-Sep-2017 20:47:36
%
% This script assumes these variables are defined:
%
% Input_train - input data.
% Target_train - target data.
x = Input_train;
t = Target_train;
% Choose a Training Function
% For a list of all training functions type: help nntrain
% 'trainlm' is usually fastest.
% 'trainbr' takes longer but may be better for challenging problems.
% 'trainscg' uses less memory. Suitable in low memory situations.
trainFcn = 'trainlm'; % Levenberg-Marquardt backpropagation.
% Create a Fitting Network
hiddenLayerSize = 23;
net = fitnet(hiddenLayerSize,trainFcn);
% Choose Input and Output Pre/Post-Processing Functions
% For a list of all processing functions type: help nnprocess
net.input.processFcns = {'removeconstantrows','mapminmax'};
net.output.processFcns = {'removeconstantrows','mapminmax'};
% Setup Division of Data for Training, Validation, Testing
% For a list of all data division functions type: help nndivide
net.divideFcn = 'dividerand'; % Divide data randomly
net.divideMode = 'sample'; % Divide up every sample
net.divideParam.trainRatio = 80/100;
net.divideParam.valRatio = 10/100;
net.divideParam.testRatio = 10/100;
% Choose a Performance Function
% For a list of all performance functions type: help nnperformance
net.performFcn = 'mse'; % Mean Squared Error
% Choose Plot Functions
% For a list of all plot functions type: help nnplot
net.plotFcns = {'plotperform','plottrainstate','ploterrhist', ...
'plotregression', 'plotfit'};
% Train the Network
[net,tr] = train(net,x,t);
% Test the Network
y = net(x);
e = gsubtract(t,y);
performance = perform(net,t,y)
% Recalculate Training, Validation and Test Performance
trainTargets = t .* tr.trainMask{1};
valTargets = t .* tr.valMask{1};
testTargets = t .* tr.testMask{1};
trainPerformance = perform(net,trainTargets,y)
valPerformance = perform(net,valTargets,y)
testPerformance = perform(net,testTargets,y)
% View the Network
view(net)
% Plots
% Uncomment these lines to enable various plots.
%figure, plotperform(tr)
%figure, plottrainstate(tr)
%figure, ploterrhist(e)
%figure, plotregression(t,y)
%figure, plotfit(net,x,t)
end
0 Comments
Accepted Answer
JESUS DAVID ARIZA ROYETH
on 21 Sep 2017
you can use :
trainFcn = 'trainlm';
hiddenLayerSize = 23;
numberhiddenlayers=2;%more hidden layers
net = fitnet([hiddenLayerSize numberhiddenlayers],trainFcn);
net.trainParam.epochs=2000;% more epochs
view(net)
with your code:
% Solve an Input-Output Fitting problem with a Neural Network
% Script generated by Neural Fitting app
% Created 13-Sep-2017 20:47:36
%
% This script assumes these variables are defined:
%
% Input_train - input data.
% Target_train - target data.
x = Input_train;
t = Target_train;
% Choose a Training Function
% For a list of all training functions type: help nntrain
% 'trainlm' is usually fastest.
% 'trainbr' takes longer but may be better for challenging problems.
% 'trainscg' uses less memory. Suitable in low memory situations.
trainFcn = 'trainlm'; % Levenberg-Marquardt backpropagation.
% Create a Fitting Network
hiddenLayerSize = 23;
numberhiddenlayers=2; %more hidden layers
net = fitnet([hiddenLayerSize numberhiddenlayers],trainFcn);
net.trainParam.epochs=2000; %more epochs
% Choose Input and Output Pre/Post-Processing Functions
% For a list of all processing functions type: help nnprocess
net.input.processFcns = {'removeconstantrows','mapminmax'};
net.output.processFcns = {'removeconstantrows','mapminmax'};
% Setup Division of Data for Training, Validation, Testing
% For a list of all data division functions type: help nndivide
net.divideFcn = 'dividerand'; % Divide data randomly
net.divideMode = 'sample'; % Divide up every sample
net.divideParam.trainRatio = 80/100;
net.divideParam.valRatio = 10/100;
net.divideParam.testRatio = 10/100;
% Choose a Performance Function
% For a list of all performance functions type: help nnperformance
net.performFcn = 'mse'; % Mean Squared Error
% Choose Plot Functions
% For a list of all plot functions type: help nnplot
net.plotFcns = {'plotperform','plottrainstate','ploterrhist', ...
'plotregression', 'plotfit'};
% Train the Network
[net,tr] = train(net,x,t);
% Test the Network
y = net(x);
e = gsubtract(t,y);
performance = perform(net,t,y)
% Recalculate Training, Validation and Test Performance
trainTargets = t .* tr.trainMask{1};
valTargets = t .* tr.valMask{1};
testTargets = t .* tr.testMask{1};
trainPerformance = perform(net,trainTargets,y)
valPerformance = perform(net,valTargets,y)
testPerformance = perform(net,testTargets,y)
% View the Network
view(net)
% Plots
% Uncomment these lines to enable various plots.
%figure, plotperform(tr)
%figure, plottrainstate(tr)
%figure, ploterrhist(e)
%figure, plotregression(t,y)
%figure, plotfit(net,x,t)
end
2 Comments
sally abdulaziz
on 24 Sep 2023
Edited: sally abdulaziz
on 24 Sep 2023
how can I export this trained network to simulink
More Answers (1)
Rawana Joha
on 1 Jun 2022
Where i must add the syntax of number hidden layer inside the ANN training code
0 Comments
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!