Training a neural netnork

1 view (last 30 days)
Lameck Amugongo
Lameck Amugongo on 14 Aug 2014
I have two files one imageReader that reads ans get the co-occurence matrix all images in the dataset and the neuralnet which does the training at the testing. It seems like the imageReader is only returning the co-occurence matrix of one image. I would like to use the co-ccurence matrix of the images to train. I would also like to label the images (as either cancerous or non cancerous).
ImageReader file
function dataset = imageReader(Folder,imgType)
Imgs = dir([Folder '/' imgType]); NumImgs = size(Imgs,1); image = double(imread([Folder '/' Imgs(1).name])); dataset = zeros([NumImgs size(image)]);
for i=1:NumImgs, image = double(imread([Folder '/' Imgs(i).name]));
[rows columns numberOfColorChannels] = size(Imgs);
%%Check if the im loaded is a grayscale image
if numberOfColorChannels > 1
%%Coverting to grayscale & get the co-occurrence matrix
F = graycomatrix(rgb2gray(imresize(image,[50 50])));
dataset = F;
else
F= graycomatrix(imresize(image,[50 50])); %get co-occurrence matrix
dataset = F;
end
end
end
neuralNet file
function neuralNet()
net = feedforwardnet(10);
%Loop to get the features for all images x = imageReader('TrainingSet','*.png');
for j=1:20
end
% Create a Self-Organizing Map som = selforgmap([10 10]); som = train(som,x); t = som(x); %Extract class data %t should 0 or 1
%t'=[0,0,0,0,0,1,1,1,1,1]
% Train the Network net = train(net,x,t); msgbox(sprintf('Training Successful'),'Success','success');
% Test the Network outputs = net(x); % now test it with a new x errors = gsubtract(t,outputs); performance = perform(net,t,outputs)
% View the Network view(net)
end
Any one that can help me with the neural Network please. Thank you.

Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!