Borrar filtros
Borrar filtros

image resize deep learning

1 visualización (últimos 30 días)
amjad hammad
amjad hammad el 30 de Oct. de 2022
Comentada: amjad hammad el 6 de Nov. de 2022
i have problem in image size in matlab
Error using trainNetwork (line 183)
Unexpected image size: All images must have the same size.
Error in neuralkadoplnenienulami (line 58)
net = trainNetwork(imgsTrain,layers,options);
%Trenovacie data pre siet
trainingDataPath = fullfile('C:\Users\amjad\Desktop\COVID-19-master\doplnenie nulami (1)\Triedenie');
trainingImages = imageDatastore(trainingDataPath,'IncludeSubfolders',true,'LabelSource','foldernames');
% Zobrazenie nahodnych trenovacich dat
figure;
perm = randperm(169,16);
for i = 1:16
subplot(4,4,i);
imshow(trainingImages.Files{perm(i)});
end
% Pocet fotografii v jednotlivych triedach
labelCount = countEachLabel(trainingImages);
% Velkost trenovacich fotiek
img = readimage(trainingImages,1);
[sizeR, SizeC] = size(img);
%specifikovanie poctu trenovacich a validacnych dat
numTrainData = 75;
[imgsTrain,imgsValidation] = splitEachLabel(trainingImages,numTrainData,'randomize');
%Definovanie architektury siete
layers = [
imageInputLayer([sizeR SizeC 1])
convolution2dLayer(3,8,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(1,'Stride',2)
convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer
fullyConnectedLayer(2)
softmaxLayer
classificationLayer];
options = trainingOptions('sgdm', ...
'InitialLearnRate',0.01, ...
'MaxEpochs',20, ...
'Shuffle','every-epoch', ...
'ValidationData',imgsValidation, ...
'Verbose',false, ...
'Plots','training-progress');
net = trainNetwork(imgsTrain,layers,options);
%Klasifikacia dat s vyhodnotenim
clasifydataPath = fullfile('C:\Users\amjad\Desktop\COVID-19-master\doplnenie nulami (1)\Klasifikacia');
clasifyingImages = imageDatastore(clasifydataPath,'IncludeSubfolders',true,'LabelSource','foldernames');
YPred = classify(net,clasifyingImages);
YValidation = clasifyingImages.Labels;
accuracy = sum(YPred == YValidation)/numel(YValidation);
missclassifaction = find(YPred ~= YValidation);
missclassifaction = transpose(missclassifaction);
FP = sum(missclassifaction (:)>8);
FN = sum(missclassifaction (:)<9);
TN = 8-FP;
TP = 8-FN;
  2 comentarios
KALYAN ACHARJYA
KALYAN ACHARJYA el 30 de Oct. de 2022
Dear Amjad, before train the model, why do not perfoem just 2 line code to make all images in same size.
amjad hammad
amjad hammad el 6 de Nov. de 2022
i have chabged all images to same sizes using resize program
Please if you have code to resize images can you provide me

Iniciar sesión para comentar.

Respuestas (1)

Walter Roberson
Walter Roberson el 30 de Oct. de 2022
https://www.mathworks.com/help/deeplearning/ref/augmentedimagedatastore.html
You use an augmented image data store. That allows you to specify an output size. It also allows you to set rgb or grayscale and will automatically convert images as needed.

Categorías

Más información sobre Image Data Workflows en Help Center y File Exchange.

Etiquetas

Community Treasure Hunt

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

Start Hunting!

Translated by