DO i need to process the unit8 data when i use "trainautoencoder" function?

2016 10 9
1 个回答
回答已采纳
更新时间：2016 10 10
2 次查看（30 天）

0 个投票

I want to use the SAE net to processing my image data. But my data is unit8 format,and should I use "mapminmax" funtion to make the data betwen[-1,1]? Thanks all.

请先登录，再回答此问题。

 采纳的回答

Massimo Zanetti
Massimo Zanetti 2016-10-9
编辑：Massimo Zanetti 2016-10-9

3 个投票

The trainAutoencoder accepts inputs of type single, double (and cell).
So, just cast your data as double
A=double(A);
and then run the function.

5 个评论
显示 3更早的评论 隐藏 3更早的评论

Liang Seacom
Liang Seacom 2016-10-10
编辑：Liang Seacom 2016-10-10
Thanks,and should I use "mapminmax" funtion to make the data betwen[-1,1] like the normal neural networks?
Walter Roberson
Walter Roberson 2016-10-10
SAE does not require that, and defaults to not doing that, according to the documentation.
That said... you would have been much further along by now if you had just gone ahead and tried both with and without the mapminmax .
Liang Seacom
Liang Seacom 2016-10-10
I have tried the both ways,but the result is very different when i use the the SAE networks to predict the test data.So I have the question:need to process the data between[-1,1]?
Walter Roberson
Walter Roberson 2016-10-10
Which way gives you better results for your purpose?
Liang Seacom
Liang Seacom 2016-10-10
funny result,the data*10 is the best. DATA*10 > DATA > mapminmax(DATA);

请先登录，再进行评论。

更多回答（0 个）

类别

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

产品

标签

Community Treasure Hunt

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

Start Hunting!

Translated by