how i save this code please tell me?? with .mat
2 ビュー (過去 30 日間)
古いコメントを表示
% Solve a Pattern Recognition Problem with a Neural Network
% Script generated by Neural Pattern Recognition app
% Created 28-Jun-2021 19:24:51
%
% This script assumes these variables are defined:
%
% inputs - input data.
% targetsd - target data.
x = inputs;
t = targetsd;
net = alexnet;
% 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 = 20;
net = patternnet(hiddenLayerSize, trainFcn);
% 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)
0 件のコメント
回答 (1 件)
Cris LaPierre
2021 年 6 月 28 日
You don't save code as a .mat file. Save it as .m or .mlx.
You can save variables in your workspace to a mat file. To do that, see the Save documentation page.
4 件のコメント
Cris LaPierre
2021 年 6 月 29 日
編集済み: Cris LaPierre
2021 年 6 月 29 日
"i save the variable x and t but i got error
variable x was not found"
How did you try to save variable x? What code or command produced this error?
As for how you would do it, see this example on saving variables named p and q to a matfile named pqfile.mat.
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!