I am trying to use a different data for my Validation and it is saying that: Training and validation responses must have the same categories. To view the categories of the res

6 views (last 30 days)
myfolder = 'C:\Users\Myname\Downloads\fall dataset\rgb';
dataDir = fullfile(myfolder);
imdir = fullfile(dataDir);
myfolder2 = 'C:\Users\Myname\Downloads\Validation';
dataDir2 = fullfile(myfolder2);
imdir2 = fullfile(dataDir2);
imds = imageDatastore(imdir, "IncludeSubfolders",true ,"LabelSource","foldernames");
imds2 = imageDatastore(imdir2,"IncludeSubfolders",true,"LabelSource","foldernames");
numTrainfiles =5172;
numValidfiles = 6598;
[imdsTrain] = splitEachLabel(imds,numTrainfiles,'randomized');
[imdsValidation] = splitEachLabel(imds2,numValidfiles,'randomized');
inputSize = [ 240 320 3];
numClasses = numel(categories(imdsTrain.Labels));
numClasses2 = numel(categories(imdsValidation.Labels));
layers = [
options = trainingOptions('sgdm', ...
'MaxEpochs',4, ...
'ValidationData',imdsValidation, ...
'ValidationFrequency',30, ...
'Verbose',false, ...
net = trainNetwork(imdsTrain,layers,options);
YPred = classify(net,imdsValidation);
yvalidation = imdsValidation.Labels;
accuracy = mean(Ypred == yvalidation);

Accepted Answer

Philip Brown
Philip Brown on 25 Nov 2021
It's likely that your training and validation folders contain different folder names, and those are being used as the class labels. For example, your training set has labels A, B, and C, but your validation set has labels A, B and D. This means your network never learns to classify into class D during training.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!