| Table of Contents ▸ List of Commands ▸ Neural Networks ▸ nn_fc | ◀ nn_dropout | nn_init ▶ |
nn_fc
Arguments:
- out,in,nb_channels>0,_learning_mode,_weight_decay>=0,_initialization
Description:
Add a fc layer (fully connected layer) 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:
learning_mode=3, weight_decay=0 and initialization=3.


Home
Download
News
Mastodon
Bluesky
X
Summary - 17 Years
Summary - 16 Years
Summary - 15 Years
Summary - 13 Years
Summary - 11 Years
Summary - 10 Years
Resources
Technical Reference
Scripting Tutorial
Video Tutorials
Wiki Pages
Image Gallery
Color Presets
Using libgmic
G'MIC Online
Community
Discussion Forum (Pixls.us)
GimpChat
IRC
Report Issue