MATLAB: Why inputs and targets have diffrent sampels

importing excel dataneural network

why do i get this error? iam trying to train a neural network.80%of my data is training data and the rest is test.

Error using network/train (line 340)

Inputs and targets have different numbers of samples.

Error in Untitled3 (line 20)

net= train(net,set',t');

this is my code.

clc
clear all
close all
filename='FIFA2.xlsx';
A =xlsread(filename);
[m,n]=size(A);
T=A(:,1);
data=A(:,(2:end));
[m,n]=size(A);
rows=int32(floor(0.8 * m));
set=A(1:rows,:);
testset=A(rows+1:end,2:n);
t=set(1:rows);
t_test=testset(rows:end);
net= newff(set',t');
y=sim(net,set');
% net.trainParam.epoch=20;
net= train(net,set',t');
y=sim(net,set');
hardlims(y);

Best Answer

For I-dimensional "I"nputs and O-dimensional "O"utput targets

After reading in inputs and targets

ALWAYS CHECK THE DIMENSIONS !!!

[ I Ni ] = size(input)

[ O Nt ] = size(target)

if Nt == Ni

N = Ni

else

error

end

Hope this helps

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: Can some one tell me what am i doing wrong

t=trainingset(1:rows80,1);

so t is one column

net= train(net,trainingset',t');

so you are constructing a neural network that has one output for each input.

y=sim(net,trainingset');

The result of simulation will be 1 output for each sample in trainingset.

 y1=hardlim(y');

The output of hardlim() has the same size as the input, so y1 will have one output for each sample in training set.

 find(trainingset' ==y1)

trainingset is a 2D array with multiple attributes per sample. You are trying to use == to compare all of those multiple attributes per sample to something that has one value per sample.

In R2016a and earlier, this is always a mistake. In R2016b and later, it will not cause an error if the dimensions match along one edge and the other edge has a singleton dimension.

I did not track through the various transposes to determine whether the edges can potentially match.

MATLAB: Neural Network keep best weight and how to use without training

You probably have to transpose weight. Type

 whos weight

and reread the help and doc documentation to make sure the dimensions are correct.

 help getwb
 doc getwb

and similarly for setwb.

Hope this helps.

THank you for formally accepting my answer