If possible in neural networks turn off automatic data normalization?

回答 (1 件)

Greg Heath
Greg Heath 2015 年 6 月 9 日

0 投票

Or course. You can change any default that you want.
[ x,t] = simplefit_dataset;
Now, what do you see when you enter each of these commands, ONE AT A TIME, without an ending semicolon? Look CAREFULLY at EACH result.
net = fitnet
input = net.inputs{1}
processFcns = net.inputs{1}.processFcns
processFcns2 = net.inputs{1}.processFcns{2}
output = net.outputs{2}
etc
Hope this helps.
Thank you for formally accepting my answer
Greg

3 件のコメント

Greg Heath
Greg Heath 2015 年 6 月 9 日
編集済み: John Kelly 2017 年 2 月 3 日
I deleted your question that was inappropriately put into an Answer Box.
The answer is
net = fitnet;
net.inputs{1}.processFcns{2} = {'removeconstantrows'};
net.outputs{2}.processFcns{2} = {'removeconstantrows'};
Radek
Radek 2015 年 6 月 10 日
net.inputs{1}.processFcns = {'removeconstantrows'}; this was corrected! thanks
Greg Heath
Greg Heath 2015 年 6 月 10 日
Good!
I think I was trying to eliminate the 2nd component directly. However I couldn't find a way to do it.
I don't know how I came up with the answer I posted.

サインインしてコメントする。

カテゴリ

ヘルプ センター および File ExchangeDeep Learning Toolbox についてさらに検索

質問済み:

2015 年 6 月 9 日

編集済み:

2017 年 2 月 3 日

Community Treasure Hunt

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

Start Hunting!

Translated by