Setting Neural network training dataset

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

 采纳的回答

yanqi liu
yanqi liu 2022-1-17
yes,sir,may be set net.divideFcn、divideblock to get trainInd,valInd,testInd

更多回答(0 个)

类别

帮助中心File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

版本

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by