Index exceeds the number of array elements (1511).

Index exceeds the number of array elements (1511).

Error in kod (line 17)

imshow(imds.Files{perm(i)});

what should i do?

clc
clear all
close all

% verilerin okunması

digitDatasetPath = fullfile(matlabroot,'toolbox','nnet','nndemos', ...
    'nndatasets','testverileri');
imds = imageDatastore(digitDatasetPath, ...
    'IncludeSubfolders',true,'LabelSource','foldernames');

%verilerin gösterimi
figure;
perm = randperm(10000,20);
for i = 1:20
    subplot(4,5,i);
    imshow(imds.Files{perm(i)});
end

labelCount = countEachLabel(imds)

% verilerin ayrımı

[imdsTrain, imdsTest] = splitEachLabel(imds,0.75,'randomize');


%CNN tasarımı
layers = [
    imageInputLayer([450   600     3])
    
    convolution2dLayer(3,8,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];

%eÄŸitim parametreleri
options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',4, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsTest, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress');

%EÄŸitim iÅŸlemi
net = trainNetwork(imdsTrain,layers,options);
% test iÅŸlemi
YPred = classify(net,imdsTest);
YTest = imdsTest.Labels;

accuracy = sum(YPred == YTest)/numel(YTest)

Answer 1

[Burhan Burak AKMAN]

May you use this method. .

 img = readimage(imds,perm(i));
 imshow(img);

Answer 2

[Image Analyst]

Find out the value of i, and if it's more than 1511, figure out why you're trying to access element of perm that is more than 1511.

Or else find out the value of perm(i) and figure out why it's more than 1511 when the length of imds.Files is only 1511.

Before the error, put these two lines with no semicolons

i
perm(i)

If you want to display images in random order, then the code should look like

numFiles = length(imds.Files)
numImagesToDisplay = numFiles; % Or some number less than numfiles if you want only a subset of them.
randomIndexes = randperm(numFiles, numImagesToDisplay);
plotRows = ceil(sqrt(numImagesToDisplay))
for k = 1:numImagesToDisplay
    subplot(plotRows, plotRows, k);
    thisFileName = imds.Files{randomIndexes(k)};
    rgbImage = imread(thisFileName);
    imshow(rgbImage);
end

Answer 3

[yanqi liu]

clc
clear all
close all

% verilerin okunması

digitDatasetPath = fullfile(matlabroot,'toolbox','nnet','nndemos', ...
    'nndatasets','testverileri');
imds = imageDatastore(digitDatasetPath, ...
    'IncludeSubfolders',true,'LabelSource','foldernames');

%verilerin gösterimi
figure;
perm = randperm(length(imds.Labels),20);
for i = 1:20
    subplot(4,5,i);
    imshow(imds.Files{perm(i)});
end

labelCount = countEachLabel(imds)

% verilerin ayrımı

[imdsTrain, imdsTest] = splitEachLabel(imds,0.75,'randomize');


%CNN tasarımı
layers = [
    imageInputLayer([450   600     3])
    
    convolution2dLayer(3,8,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,16,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    
    convolution2dLayer(3,32,'Padding','same')
    batchNormalizationLayer
    reluLayer
    
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer];

%eÄŸitim parametreleri
options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',4, ...
    'Shuffle','every-epoch', ...
    'ValidationData',imdsTest, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress');

inputSize = layers(1).InputSize;
augimdsTrain = augmentedImageDatastore(inputSize(1:2),imdsTrain,'ColorPreprocessing','gray2rgb');
augimdsTest = augmentedImageDatastore(inputSize(1:2),imdsTest,'ColorPreprocessing','gray2rgb');

%EÄŸitim iÅŸlemi
net = trainNetwork(augimdsTrain,layers,options);
% test iÅŸlemi
YPred = classify(net,augimdsTest);
YTest = imdsTest.Labels;

accuracy = sum(YPred == YTest)/numel(YTest)