How can i do if i want to test the network created with new input ?

Question

afef 2017-5-29

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/342373-how-can-i-do-if-i-want-to-test-the-network-created-with-new-input

评论： afef 2017-5-30

Hi , i used the neural Network start (nnstart) for pattern recognition and i got this script

% Solve a Pattern Recognition Problem with a Neural Network
% Script generated by Neural Pattern Recognition app
% Created 29-May-2017 14:25:55
%
% This script assumes these variables are defined:
%
%   inputepilepsie - input data.
%   targetepilepsie - target data.
 x = inputepilepsie;
 t = targetepilepsie;
 % 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 = 'trainscg';  % Scaled conjugate gradient backpropagation.
 % Create a Pattern Recognition Network
hiddenLayerSize = 10;
 net = patternnet(hiddenLayerSize);
 % Setup Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;
 % Train the Network
[net,tr] = train(net,x,t);
 % Test the Network
y = net(x);
e = gsubtract(t,y);
performance = perform(net,t,y)
tind = vec2ind(t);
yind = vec2ind(y);
percentErrors = sum(tind ~= yind)/numel(tind);
 % View the Network
view(net)
 % Plots
% Uncomment these lines to enable various plots.
%figure, plotperform(tr)
 %figure, plottrainstate(tr)
 %figure, ploterrhist(e)
 %figure, plotconfusion(t,y)
 %figure, plotroc(t,y)

I want to know how can i do if i want to test the network with new input ?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Greg Heath 2017-5-30

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/342373-how-can-i-do-if-i-want-to-test-the-network-created-with-new-input#answer_268888

在 MATLAB Online 中打开

 % Test the Network with new data
ynew             = net(xnew);
enew             = gsubtract(tnew,ynew);
performancenew   = perform(net,tnew,ynew)
tindnew          = vec2ind(tnew);
yindnew          = vec2ind(ynew);
percentErrorsnew = sum(tindnew ~= yindnew)/numel(tindnew);

Hope this helps.

Thank you for formally accepting my answer

Greg

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

afef 2017-5-30

Actually i want to evalute the network created and see how it will classify the new data and also please how could i save this network as .mat file then i can directly open the network in matlab software.

请先登录，再进行评论。