How to split an image datastore for cross-validation?

Hello,

The method

splitEachLabel

of an

imageDatastore

object splits an image data store into proportions per category label. How can one split an image data store for training using cross-validation and using the

trainImageCategoryCalssifier

class?

I.e. it's easy to split it in N partitions, but then some sort of mergeEachLabel functionality is needed to be able to train a classifier using cross-validation. Or is there another way of achieving that?

Regards, Elena

[kowshik Thopalli]

I am looking for an answer to a similar problem. Did you solve it?

[Tripoli Settou]

I am also looking for an answer to a similar problem. Did you solve it?

Answer 1

[Hamza Mehboob]

[imd1 imd2 imd3 imd4 imd5 imd6 imd7 imd8 imd9 imd10] = splitEachLabel(imds,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,'randomize');

partStores{1} = imd1.Files ;
partStores{2} = imd2.Files ;
partStores{3} = imd3.Files ;
partStores{4} = imd4.Files ;
partStores{5} = imd5.Files ;

partStores{6} = imd6.Files ;
partStores{7} = imd7.Files ;
partStores{8} = imd8.Files ;
partStores{9} = imd9.Files ;
partStores{10} = imd10.Files; 

for i = 1 :k
    i
    test_idx = (idx == i);
    train_idx = ~test_idx;

      imdsTest = imageDatastore(partStores{test_idx}, 'IncludeSubfolders', true,'FileExtensions','.jpeg', 'LabelSource', 'foldernames');

      imdsTrain = imageDatastore(cat(1, partStores{train_idx}), 'IncludeSubfolders', true,'FileExtensions','.jpeg', 'LabelSource', 'foldernames');
  %%%%%%%%%%%%%%%%%%%%%%%%%
  %%%%%%%%%%%%%%%%%%%%%%%%%
  %%%%%%%%%%%%%%%%%%%%%%%%%
  %%%%%Write your classification task
  [e-mail] for any further help. 
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  }

[Sajja Tulasi Krishna]

what is idx and k here

[Hamza Mehboob]

k = 10

idx = crossvalind('Kfold', k, k);

[TRIPTI GOEL]

thank you for the code.

[Sajja Tulasi Krishna]

Thanq for clear doubt @Hamza Mehboob