How to give new input to trained network and getting output using neural network toolbox

Question

ABHAY SONI 2013-8-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/85348-how-to-give-new-input-to-trained-network-and-getting-output-using-neural-network-toolbox

回答： Greg Heath 2017-11-13

Hello Friends,

I am using neural network toolbox. I have trained the net using input matrix of 5 X 48 and output matrix of 2 X 48. The network is saved by name Abhay. Now I want to use this network using a 5 X 1 input matrix and the corresponding output should be a 2 X 1 matrix as it is trained. I used, y = sim(Abhay,r) % r is the 5 X 1 input matrix. The result of this command should be a 2 X 1 but I am getting error regarding the size of input. so please if anyone can explain the problem and remedy.

3 个评论
显示 1更早的评论隐藏 1更早的评论

ABHAY SONI 2013-8-23

function net = Abhay(inputs,targets) %CREATE_FIT_NET Creates and trains a fitting neural network. % % NET = CREATE_FIT_NET(INPUTS,TARGETS) takes these arguments: % INPUTS - RxQ matrix of Q R-element input samples % TARGETS - SxQ matrix of Q S-element associated target samples % arranged as columns, and returns these results: % NET - The trained neural network % % For example, to solve the Simple Fit dataset problem with this function: % % load simplefit_dataset % net = create_fit_net(simplefitInputs,simplefitTargets); % simplefitOutputs = sim(net,simplefitInputs); % % To reproduce the results you obtained in NFTOOL: % % net = create_fit_net(data',data');

% Create Network numHiddenNeurons = 40; % Adjust as desired net = newfit(inputs,targets,numHiddenNeurons); net.divideParam.trainRatio = 70/100; % Adjust as desired net.divideParam.valRatio = 15/100; % Adjust as desired net.divideParam.testRatio = 15/100; % Adjust as desired

% Train and Apply Network [net,tr] = train(net,inputs,targets); outputs = sim(net,inputs);

% Plot plotperf(tr) plotfit(net,inputs,targets) plotregression(targets,outputs)

The error

>> Abhay ??? Input argument "inputs" is undefined.

Error in ==> Abhay at 22 net = newfit(inputs,targets,numHiddenNeurons);