No appropriate method, property, or field 'Lables' for class 'matlab.io.datastore.ImageDatastore'.
6 views (last 30 days)
Show older comments
I am trying to classify two class of images with resnet-50 in deep learning and getting an error 'No appropriate method, property, or field 'Lables' for class 'matlab.io.datastore.ImageDatastore'..
Can anyone help. This is my code
clc
%%Image Folder%%
outputFolder = fullfile('input folder');
rootFolder = fullfile(outputFolder, 'CNN_Class');
categories = {'a','b'};
%%Datastore for storing the images%%
imds = imageDatastore(fullfile(rootFolder, categories),'LabelSource', 'foldernames');
tbl=countEachLabel(imds);
minSetcount=min(tbl{:,2});
imds=splitEachLabel(imds,minSetcount,'randomize');
countEachLabel(imds);
net=resnet50();
set(gca,'YLim',[150 170]);
net.Layers(1);
net.Layers(end);
numel(net.Layers(end).ClassNames);
%%Split into Training and Testing set%%
[trainingSet,testSet] = splitEachLabel(imds,0.8,'randomized');
imageSize=(net.Layers(1).InputSize);
augmentedTrainingset=augmentedImageDatastore(imageSize,trainingSet);
augmentedTestset=augmentedImageDatastore(imageSize,testSet);
w1=net.Layers(2).Weights;
w1=mat2gray(w1);
% figure
%montage(w1)
title('First Convolution Layer Weight')
featureLayer='fc1000';
trainingFeatures=activations(net,augmentedTrainingset,...
featureLayer,'MiniBatchSize',32,'OutputAs','Columns');
trainingLabels=trainingSet.Labels;
Classifier=fitcecoc(trainingFeatures,trainingLabels,...
'Learner','Linear','Coding','onevsall','ObservationsIn','Columns');
testFeatures=activations(net,augmentedTestset,...
featureLayer,'MiniBatchSize',32,'OutputAs','Columns');
predictLabels=predict(Classifier,testFeatures,'ObservationsIn','Columns');
testLables=testSet.Lables;
confMat=confusionmat(testLables,predictLables);
confMat=bsxfun(@rdivide,confMat,sum(confMat,2));
mean(diag(confMat))
0 Comments
Accepted Answer
dpb
on 22 Dec 2019
It's spelled "labels", not "lables"
testLabeles=testSet.Lables;
should be
testLabels=testSet.Labels;
Of course, let the auto-correct feature fix the other places it can and manually correct the other places as well. Judicious use of the text substitution can help typing here.
1 Comment
More Answers (0)
See Also
Categories
Find more on Image Data Workflows 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!