I am aware that we can use the lines of code bellow to set the percentages of the dataset to be used for training, testing and validating, however I am planning to oversmaple my training dataset and save it in array 'A', and then have array 'B' and 'C' to be testing and validating datapoints. is there a way to use array A,B and C as my training, testing and validating datasets because I only want A to be oversampled
net.divideParam.trainRatio=0.7
net.divideParam.testRatio=0.15
net.divideParam.valRation-0.15

 Akzeptierte Antwort

yanqi liu
yanqi liu am 17 Jan. 2022

0 Stimmen

yes,sir,may be set net.divideFcn、divideblock to get trainInd,valInd,testInd

Weitere Antworten (0)

Kategorien

Mehr zu Deep Learning Toolbox finden Sie in Hilfe-Center und File Exchange

Produkte

Version

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by