Fitnet: Can we forbid the normalization pre processing ?

4 views (last 30 days)
Hello,
I would like to know if there is a possibility to avoid the pre processing included inside fitnet, rescaling the data between -1 and 1.
I want to feed it with my own scales/normalization method, is it possible ?

Accepted Answer

Steven Lord
Steven Lord on 2 Jun 2021
net = fitnet(10);
net.inputs{1}
ans =
Neural Network Input name: 'Input' feedbackOutput: [] processFcns: {'removeconstantrows', 'mapminmax'} processParams: {1x2 cell array of 2 params} processSettings: {1x2 cell array of 2 settings} processedRange: [] processedSize: 0 range: [] size: 0 userdata: (your custom info)
You want to modify the processFcns property of the net.inputs{1} object. See this documentation page for more information about the properties of that Neural Network Input object.

More Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!