libeblearn
ebl::laplacian_module< T, Tstate > Class Template Reference

#include <ebl_normalization.h>

Inheritance diagram for ebl::laplacian_module< T, Tstate >:
ebl::module_1_1< T, Tstate > ebl::module

List of all members.

Public Member Functions

 laplacian_module (int nf, bool mirror=false, bool global_norm=false, const char *name="laplacian_module")
virtual ~laplacian_module ()
 destructor
virtual void fprop (Tstate &in, Tstate &out)
 forward propagation from in to out
virtual laplacian_module< T,
Tstate > * 
copy ()
 Returns a deep copy of this module.
virtual std::string describe ()
 Returns a string describing this module and its parameters.

Detailed Description

template<typename T, class Tstate = bbstate_idx<T>>
class ebl::laplacian_module< T, Tstate >

Laplacian pyramid normalization: input is filtered with a 5x5 kernel and the result is subtracted to the input, resulting in a high-pass filtered output.


Constructor & Destructor Documentation

template<typename T , class Tstate >
ebl::laplacian_module< T, Tstate >::laplacian_module ( int  nf,
bool  mirror = false,
bool  global_norm = false,
const char *  name = "laplacian_module< T, Tstate >" 
)
Parameters:
nfThe number of feature maps input to this module.
mirrorUse mirroring of the input to pad border if true, or use zero-padding otherwise (default).
global_normIf true, apply global normalization first.

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