Neural Network - net.divideFcn = 'divideind'

7 次查看（过去 30 天）

显示更早的评论

Anderson 2015-10-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/250442-neural-network-net-dividefcn-divideind

评论： Tea 2016-8-12

采纳的回答： Greg Heath

在 MATLAB Online 中打开

Hi,

I am trying to use "net.divideFcn = 'divideind'". In my case, I want to merge two different range of indices, e.g.,

net.divideParam.trainInd = 1:4, 10:20; (is it possible?) net.divideParam.valInd = 5:9; net.divideParam.testInd = 21:25;

Thank you!

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Greg Heath 2015-10-23

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/250442-neural-network-net-dividefcn-divideind#answer_197016

Yes.

However, use [ 1:4, 10:20]

Thank you for formally accepting my answer

Greg

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Tea 2016-8-12

Hi, could you please explain why if I input indices like that, trainInd in training records is given as column instead of row vector? However, trainMask is fine. Thank you

请先登录，再进行评论。

类别

AI, Data Science, and Statistics Deep Learning Toolbox Function Approximation, Clustering, and Control Function Approximation and Clustering Define Shallow Neural Network Architectures

在 Help Center 和 File Exchange 中查找有关 Define Shallow Neural Network Architectures 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by