Matlab Help Needed Please

3 次查看（过去 30 天）

Anas Bilal 2020-4-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/518828-matlab-help-needed-please

评论： Anas Bilal 2020-4-18

hello everyne i'm runing this code for testing and training but receiving errors can any please help me to correct this code i shall be very thank full to you for this kindness.

clc
clear all
close all
image=uigetfile(['*.jpg'],'D:\Diabetic retnopathery\DR code');
copyfile('D:\Diabetic retnopathery\DR code','D:\Diabetic retnopathery\DR code\New Folder');
%inp=input('ENTER IMAGE :');
imgg=imread(image);
aa=imgg;
[m n c]=size(aa);
if c==3
b=rgb2gray(aa);
else
b=aa;
end
im =b;
figure,
imshow(aa)
title('input ')
matlabroot='D:\Diabetic retnopathery\DR code'
DatasetPath = fullfile(matlabroot,'fundusdeeplearning','Dataset1');
Data = imageDatastore(DatasetPath, ...
        'IncludeSubfolders',true,'LabelSource','foldernames');
     
CountLabel = Data.countEachLabel;
trainData=Data;
%% Define the Network Layers
% Define the convolutional neural network architecture. 
layers = [imageInputLayer([336 448 3])
          convolution2dLayer(5,20)
          reluLayer
          maxPooling2dLayer(2,'Stride',2)
          convolution2dLayer(5,20)
          reluLayer
          maxPooling2dLayer(2,'Stride',2)
          fullyConnectedLayer(2)
          softmaxLayer
          classificationLayer()];
options = trainingOptions('sgdm','MaxEpochs',15, ...
	'InitialLearnRate',0.0001);  
convnet = trainNetwork(trainData,layers,options);
%% Classify the Images in the Test Data and Compute Accuracy
% Run the trained network on the test set that was not used to train the
% network and predict the image labels (digits).
img =imgg;
img=imresize(img,[336 448]);
size(img)
outt = classify(convnet,img);
 tf1=[]
for  ii=1:2
    st=int2str(ii)
tf = ismember(outt,st);
tf1=[tf1 tf];
end
out=find(tf1==1);
ss=sprintf('THE CLASS IS  : %2f ',round((out)));
if out==1
    msgbox('NORMAL')
    elseif out==2
    msgbox('AB NORMAL') 
end
    

9 个评论
显示 7更早的评论隐藏 7更早的评论

Walter Roberson 2020-4-18

If I am correct about the cause of the problem, then the only way to fix your code would be to put in some tests to detect the situation and give a appropriate message without trying to do the training.

That is, if I am right about the error, then then problem is your data and not the code.

Anas Bilal 2020-4-18