필터 지우기
필터 지우기

training in neural network

조회 수: 1 (최근 30일)
Narges Sedre
Narges Sedre 2018년 11월 26일
댓글: Greg Heath 2018년 11월 26일
can some one tell me why my ytrain and ytest is zero?
my labels are 100, 200 and 300
iam trying to find training error and test error but it gives me zeros
clc
clear all
close all
filename='FIFA2.xlsx';
A =xlsread(filename);
[m,n]=size(A);
T=A(:,1);
data=A(:,(2:end));
rows80=int32(floor(0.8 * m));
trainingset=A(1:rows80,2:n);
testset=A(rows80+1:end,2:n);
t=trainingset(1:rows80,1);
t_test=A(rows80+1:end,1);
net= newff(trainingset',t');
y=sim(net,trainingset');
%net.trainParam.epoch=20;
net= train(net,trainingset',t');
y=sim(net,trainingset')
y_test=sim(net,testset')
p=0;
y1=hardlim(y');
% hardlims(y_test);
for(i=1:size(t,1))
if(t(i,:)==y1(i,:))
p=p+1;
end
end
ytrain =100*p/size(trainingset,1);
q=0;
y2=hardlim(y_test');
for(j=1:size(t_test,1))
if(t_test(j,:)==y2(j,:))
q=q+1;
end
end
ytest=100*q/size(t_test,1);
  댓글 수: 1
Greg Heath
Greg Heath 2018년 11월 26일
Need sample data for evaluation.
Greg

댓글을 달려면 로그인하십시오.

답변 (0개)

카테고리

Help CenterFile Exchange에서 Deep Learning Toolbox에 대해 자세히 알아보기

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by