deep learning convnet with matlab

6 views (last 30 days)
Salma Hassan
Salma Hassan on 19 Dec 2017
Edited: Cedric on 31 Dec 2017
i want to divide the dataset into 3 parts ( training , validation , test ) with matlab
is this line true
[trainingimages,valDigitData,testimage]=splitEachLabel(allimages,0.7,0.2,0.1 ,'randomize');
and then into the training option i add the
trainingOptions('sgdm',....,'ValidationData',valDigitData,'ValidationFrequency',50)
is this ture

Answers (1)

Salma Hassan
Salma Hassan on 31 Dec 2017
ok i found the answer
Create three new datastores from the files in imds. The first datastore imds60 contains the first 60% of files with the demos label and the first 60% of files with the imagesci label. The second datastore imds10 contains the next 10% of files from each label. The third datastore imds30 contains the remaining 30% of files from each label. If the percentage applied to a label does not result in a whole number of files, splitEachLabel rounds down to the nearest whole number.
[imds60, imds10, imds30] = splitEachLabel(imds,0.6,0.1)

Community Treasure Hunt

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

Start Hunting!