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

#include <ebl_machines.h>

Inheritance diagram for ebl::lenet_cscsc< T, Tstate >:
ebl::net_cscsc< T, Tstate > ebl::layers< T, Tstate > ebl::module_1_1< T, Tstate, Tstate > ebl::module

List of all members.

Public Member Functions

 lenet_cscsc (parameter< T, Tstate > &prm, intg image_height, intg image_width, intg ki0, intg kj0, intg si0, intg sj0, intg ki1, intg kj1, intg si1, intg sj1, intg output_size, bool norm=false, bool color=false, bool mirror=false, bool tanh=false, bool shrink=false, bool diag=false, bool norm_pos=false, idx< intg > *table0_=NULL, idx< intg > *table1_=NULL, idx< intg > *table2_=NULL)

Detailed Description

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

lenet type of architecture without last full layer. absolution rectification + contrast normalization can be turned on with the norm boolean. color can be turned on with the color boolean, in which case a 3-layer input is assumed and bigger tables are used.


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