how to interpret from output matrix of neural network that what is result
조회 수: 3 (최근 30일)
이전 댓글 표시
Hi i had to classify images as normal and pathological, in order to do that i use neural network.
to put images data into neural network i extracted features from images and converted them into column vector using (:)
D = 'Data';
Train_Feature=[];
Train_Label=[];
S = dir(fullfile(D,'*'));
N = setdiff({S([S.isdir]).name},{'.','..'}); % list of subfolders of D.
for ii = 1:numel(N)
T = dir(fullfile(D,N{ii},'*')); % improve by specifying the file extension.
C = {T(~[T.isdir]).name}; % files in subfolder.
for jj = 1:numel(C)
F = fullfile(D,N{ii},C{jj})
I=imread(F);
a=imresize(I,[256 256]);
G=rgb2gray(a);
F=extractHOGFeatures(G);
[b,c]=size(F);
X=zeros(b,c);
Y=zeros(b,c);
X(1,:)=1;
Y(1,:)=0;
Train_Feature=[Train_Feature,F(:)];
if(N{ii}=='1')
Train_Label=[Train_Label,X(:)];
else
Train_Label=[Train_Label,Y(:)];
end
end
end
save('Train_Feature','Train_Feature')
save('Train_Label','Train_Label')
and made two variables Train_Feature(input data) and Train_Label(target data).
the values that are stored in these variables are
for Train_Feature
and for Train_Label
So i put these variables(Train_Feature and Train_Label) as input data and target data to train neural network...
this is code for neural network...
inputs = Train_Feature;
targets = Train_Label;
% Create a Pattern Recognition Network
hiddenLayerSize = 10;
net = patternnet(hiddenLayerSize);
% Set up 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,inputs,targets);
% Test the Network
outputs = net(inputs)
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs)
% View the Network
view(net)
save('Mynetwork','net')
so in order to classify image i wrote this code
load Mynetwork
[fname, path]=uigetfile('.png','Open an Image as input for training');
fname=strcat(path, fname);
I=imread(fname);
a=imresize(I,[256 256]);
G=rgb2gray(a);
F=extractHOGFeatures(G);
answer=net(F(:))
here the answer that i get is in column matrix form...
so how do i know what was the output (that is how to know that the image belonged to which class) ???
댓글 수: 0
답변 (0개)
참고 항목
카테고리
Help Center 및 File Exchange에서 Get Started with 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!