mlpack::ann::FFTConvolution< BorderMode, padLastDim > Class Template Reference

Computes the two-dimensional convolution through fft. More...

#include <fft_convolution.hpp>

Static Public Member Functions
template<typename eT , typename Border = BorderMode>
static std::enable_if< std::is_same< Border, ValidConvolution >::value, void >::type	Convolution (const arma::Mat< eT > &input, const arma::Mat< eT > &filter, arma::Mat< eT > &output)
template<typename eT , typename Border = BorderMode>
static std::enable_if< std::is_same< Border, FullConvolution >::value, void >::type	Convolution (const arma::Mat< eT > &input, const arma::Mat< eT > &filter, arma::Mat< eT > &output)
template<typename eT >
static void	Convolution (const arma::Cube< eT > &input, const arma::Cube< eT > &filter, arma::Cube< eT > &output)
template<typename eT >
static void	Convolution (const arma::Mat< eT > &input, const arma::Cube< eT > &filter, arma::Cube< eT > &output)
template<typename eT >
static void	Convolution (const arma::Cube< eT > &input, const arma::Mat< eT > &filter, arma::Cube< eT > &output)

Detailed Description

template<typename BorderMode = FullConvolution, const bool padLastDim = false>
class mlpack::ann::FFTConvolution< BorderMode, padLastDim >

Computes the two-dimensional convolution through fft.

This class allows specification of the type of the border type. The convolution can be computed with the valid border type or the full border type (default).

FullConvolution: returns the full two-dimensional convolution. ValidConvolution: returns only those parts of the convolution that are computed without the zero-padded edges.

Template Parameters

BorderMode	Type of the border mode (FullConvolution or ValidConvolution).
padLastDim	Pad the last dimension of the input to to turn it from odd to even.

---

The documentation for this class was generated from the following file:

• src/mlpack/methods/ann/convolution_rules/fft_convolution.hpp