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

#include <ebl_basic.h>

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

List of all members.

Public Member Functions

 mirrorpad_module (int nr, int nc)
 mirrorpad_module (idxdim &kernel_size)
virtual ~mirrorpad_module ()
 destructor
virtual void fprop (Tstate &in, Tstate &out)
 forward propagation from in to out
virtual void fprop (Tstate &in, idx< T > &out)
 forward propagation from in to out
virtual mirrorpad_module< T,
Tstate > * 
copy (parameter< T, Tstate > *p=NULL)

Detailed Description

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

A simple mirror padding module that is mostly usefull for doing same size output convolutions.


Constructor & Destructor Documentation

template<typename T , class Tstate >
ebl::mirrorpad_module< T, Tstate >::mirrorpad_module ( int  nr,
int  nc 
)

<nrow> is the number of rows in zero added border <ncol> is the number of cols in zero added border the output size is enlarged by 2*nrow in rows and 2*ncols in cols for each feature map.

template<typename T , class Tstate >
ebl::mirrorpad_module< T, Tstate >::mirrorpad_module ( idxdim &  kernel_size)

Constructor adding zero borders with same size on each size if the kernel had odd size, otherwise adding 1 pixel less on the right and bottom borders.

Parameters:
kernel_sizeThe sizes of the kernel for which to pad.

Member Function Documentation

template<typename T , class Tstate >
mirrorpad_module< T, Tstate > * ebl::mirrorpad_module< T, Tstate >::copy ( parameter< T, Tstate > *  p = NULL) [virtual]

Returns a deep copy of this module.

Parameters:
pIf NULL, reuse current parameter space, otherwise allocate new weights on parameter 'p'.

Reimplemented from ebl::zpad_module< T, Tstate >.


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