G'MIC - GREYC's Magic for Image Computing: A Full-Featured Open-Source Framework for Image Processing
Banner Institutions GREYC CNRS ENSICAEN UNICAEN

A Full-Featured Open-Source Framework for Image Processing



Latest stable version: 3.6.6        Current pre-release: 3.7.0 (2026/01/22)

Reference
Table of Contents  ▸  List of Commands  ▸  Neural Networks  ▸  nn_noise◀  nn_nl    |    nn_normalize  ▶

nn_noise

Arguments:

  • out,in,_amplitude,_noise_type,_training_only={ 0:No | 1:Yes }

Description:

Add a noise layer to the current network.

noise_type can be { 0:Gaussian | 1:Uniform | 2:Salt&pepper | 3:Poisson | 4:Rice }.
If training_only is set, the noise is applied on the input only during the network training phase.

Default values:

amplitude=0.1, noise_type=0 and training_only=1.

G'MIC - GREYC's Magic for Image Computing: A Full-Featured Open-Source Framework for Image Processing

G'MIC is an open-source software distributed under the CeCILL free software licenses (LGPL-like and/or
GPL-compatible). Copyrights (C) Since July 2008, David Tschumperlé - GREYC UMR CNRS 6072, Image Team.