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

◀  nn_fc    |    nn_init  ▶

nn_fft

Arguments:

• out,in,io_mode,_is_inverse={ 0:No | 1:Yes },_axes.

Description:

Add a fft layer (Fourier Transform) to the current network.

Argument io_mode tells about the meaning of input/output data. It can be { 0:real → real | 1:(real,imag) → real | 2:real → (real,imag) | 3:(real,imag) → (real,imag) }
When dealing with (real,imag) data, the real and imaginary parts of the data (N channels each) are concatenated into a 2N-channels image.
Argument axes can be { 0 (all) | x | y | z | xy | xz | yz | xyz }.

Default values:

is_inverse=0, axes=0 (all).

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.