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: 4.0.7 (2026/10/28)

Reference
Table of Contents  ▸  List of Commands  ▸  Neural Networks  ▸  nn_dropout◀  nn_div    |    nn_fc  ▶

nn_dropout

Arguments:

  • out,in,0<=dropout_rate<1,_axes

Description:

Add a dropout layer to the current network.

axes is a combination of { x | y | z | c } (e.g. xyz, c, xzc), or 0, and gives the axes along which the same dropout decision is shared: 0:One decision per element | xyz:Per channel (default) | xyzc:Whole layer (drop path).
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.