Why does data prediction with cascade forward net not work ?

Question

Mara 2017-2-15

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/325208-why-does-data-prediction-with-cascade-forward-net-not-work

回答： Nachiket Katakkar 2017-2-23

I have a problem with making new predictions with my cascade forward net. i created a cascade forward net with 10 Neurons and trained it. Then I tried to make predictions with new data by using sim(net,Xnew) which always gives the same error saying:

Error using network/sim (line 266)
Input data sizes do not match net.inputs{1}.size.
Error in CASCADEnet (line 12)
predCASCADE=sim(netCASCADE,Xnew');

Xnew vector and X vector (with which I trained the net) have the same size. This is my Code so far with X as input and Y as Target vector:

netCASCADE=cascadeforwardnet(10,'trainlm');
netCASCADE.divideParam.trainRatio=0.7;
netCASCADE.divideParam.valRatio=0.15;
netCASCADE.divideParam.testRatio=0.15;
netCASCADE=train(netCASCADE, X',Y');
predCASCADE=sim(netCASCADE,Xnew');

Thanks in advance for help !

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

Nachiket Katakkar 2017-2-23

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/325208-why-does-data-prediction-with-cascade-forward-net-not-work#answer_256096

在 MATLAB Online 中打开

This error message is observed if the number of columns (input size) in the Test data (Xnew) does not match the number of columns in the Train data (X). I would recommend ensuring that the number of columns in Xnew and X are exactly the same:

>> isequal(size(Xnew,2),size(X,2))

Here is an example with a data-set containing 2 columns and using your code:

load carsmall
X = [Weight,Acceleration];
Y = MPG;
Xnew = X;
netCASCADE=cascadeforwardnet(10,'trainlm');
netCASCADE.divideParam.trainRatio=0.7;
netCASCADE.divideParam.valRatio=0.15;
netCASCADE.divideParam.testRatio=0.15;
netCASCADE=train(netCASCADE, X',Y');
predCASCADE=sim(netCASCADE,Xnew')