Table of Contents  ▸  List of Commands  ▸  Neural Networks  ▸  nn_resconv3dnl

◀  nn_resconv2dnl    |    nn_resfcnl  ▶

nn_resconv3dnl

Arguments:

• out,_in,_kernel_size>0,_dilation>0,_boundary_conditions,_activation,_learning_mode,_regularization>=0

Description:

Add a resconv3dnl (residual 3D convolutional layer followed by a non-linearity) to the current network.

boundary_conditions can be { 0:Dirichlet | 1:Neumann | 2:Periodic | 3:Mirror }.
learning_mode can be { 0:No learning | 1:Weights only | 2:Biases only | 3:Weights+biases }.

Default values:

in=. (previous layer), kernel_size=3, dilation=1, boundary_conditions=1, activation='leakyrelu', learning_mode=3 and regularization=0.