Table of Contents  ▸  List of Commands  ▸  Neural Networks  ▸  nn_fcnnl

◀  nn_fcnl    |    nn_init  ▶

nn_fcnnl

Arguments:

• out,in,nb_channels>0,_activation,_learning_mode,_regularization>=0,_initialization

Description:

Add a fcnnl layer (fully connected layer followed by a normalization layer, then a non-linearity) to the current network.

learning_mode can be { 0:No learning | 1:Weights only | 2:Biases only | 3:Weights+biases }.
initialization can be { 0:Zero | 1:Identity | 2:Lecun-initialization | 3:He-initialization }.

Default values:

activation=leakyrelu, learning_mode=3, regularization=0 and initialization=2.

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.