Table of Contents  ▸  List of Commands  ▸  Neural Networks  ▸  nn_conv3d

◀  nn_conv2dnnl    |    nn_conv3dnl  ▶

nn_conv3d

Arguments:

• out,in,nb_channels>0,_kernel_size>0,_stride>0,_dilation,_shrink>=0,_boundary_conditions,0<=_learning_mode<=3,_regularization>=0

Description:

Add a conv3d layer (3D convolutional layer) 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:

kernel_size=3, stride=1, dilation=1, shrink=0, boundary_conditions=1, learning_mode=3 and regularization=0.