Explicitly split the imagedataset into training and testing set
8 views (last 30 days)
Show older comments
I having dataset contains 1800 images in 10 subfolders. Each subfolder contain 180images.
I want to split my dataset into Train and Test. I want 10th,20th, 30th, ...., 180th images in each subfolder as test set. Remaining as training set.
After that i have to split my Train set into 3 part (XTrain1, XTrain2, XTrain3).
This is the code i have used:
imagefolder = 'C:\Users\manjurama\Desktop\study\PG\PROJECT\Finger vein database multiple copy\database_10';
imds = imageDatastore(imagefolder,'IncludeSubfolders',true,'LabelSource','foldernames');
numTrainingFiles = 162;
[Train, Test] = splitEachLabel(imds,numTrainingFiles);
[XTrain11, XTrain21, XTrain31] = splitEachLabel(imds, 0.333, 0.333, 0.333);
XTrain1 = augmentedImageDatastore([227 227],XTrain11);
XTrain2 = augmentedImageDatastore([227 227],XTrain21);
XTrain3 = augmentedImageDatastore([227 227],XTrain31);
But i wont work
Also i need to find the class information.
I used following code. But it wont work
classes = XTrain1.Labels; % retrieve the class information
numClasses = numel(classes);
Kindly help to do the above task. Thanks in advance.
0 Comments
Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!