ebl::net_cscf< T, Tstate > Class Template Reference

#include <ebl_machines.h>

Inheritance diagram for ebl::net_cscf< T, Tstate >:

List of all members.

Public Member Functions
	net_cscf ()
	net_cscf (parameter< T, Tstate > &prm, intg ini, intg inj, intg ki0, intg kj0, idx< intg > &tbl0, intg si0, intg sj0, intg ki1, intg kj1, idx< intg > &tbl1, intg outthick, bool norm=false, bool mirror=false, bool tanh=false, bool shrink=false, bool diag=false, bool lut_features=false, idx< T > *lut=NULL)
void	init (parameter< T, Tstate > &prm, intg ini, intg inj, intg ki0, intg kj0, idx< intg > &tbl0, intg si0, intg sj0, intg ki1, intg kj1, idx< intg > &tbl1, intg outthick, bool norm=false, bool mirror=false, bool tanh=false, bool shrink=false, bool diag=false, bool lut_features=false, idx< T > *lut=NULL)

---

Detailed Description

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

Standard LeNet5-type architecture without the final e-dist RBF layer.

---

Constructor & Destructor Documentation

template<typename T , class Tstate >

ebl::net_cscf< T, Tstate >::net_cscf

(

)

Empty constructor, awaiting for initialization by the user via the init() function.

template<typename T , class Tstate >

ebl::net_cscf< T, Tstate >::net_cscf	(	parameter< T, Tstate > &	prm,
		intg	ini,
		intg	inj,
		intg	ki0,
		intg	kj0,
		idx< intg > &	tbl0,
		intg	si0,
		intg	sj0,
		intg	ki1,
		intg	kj1,
		idx< intg > &	tbl1,
		intg	outthick,
		bool	norm = false,
		bool	mirror = false,
		bool	tanh = false,
		bool	shrink = false,
		bool	diag = false,
		bool	lut_features = false,
		idx< T > *	lut = NULL
	)

Complete constructor, calls the init() function. See the init() description for complete arguments description.

---

Member Function Documentation

template<typename T , class Tstate >

void ebl::net_cscf< T, Tstate >::init	(	parameter< T, Tstate > &	prm,
		intg	ini,
		intg	inj,
		intg	ki0,
		intg	kj0,
		idx< intg > &	tbl0,
		intg	si0,
		intg	sj0,
		intg	ki1,
		intg	kj1,
		idx< intg > &	tbl1,
		intg	outthick,
		bool	norm = false,
		bool	mirror = false,
		bool	tanh = false,
		bool	shrink = false,
		bool	diag = false,
		bool	lut_features = false,
		idx< T > *	lut = NULL
	)

The init function creates the machine by stacking the modules in this order (c-s-c-s-c-f): convolution_layer, subsampling_layer, convolution_layer, subsampling_layer, convolution_layer, full_layer. <ini> <inj>: expected max size of input for preallocation of internal states <ki0> <kj0>: kernel size for first convolutional layer <tbl0>: table of connections between input anf feature maps for first layer <si0> <sj0>: subsampling for first layer <ki1> <kj1> <tbl1> <si1> <sj1>: same for next 2 layers <ki2> <kj2> <tbl2>: same for last convolution layer <outthick>: number of outputs. <prm> an idx1-ddparam in which the parameters will be allocated.

---

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

• /home/rex/ebltrunk/core/libeblearn/include/ebl_machines.h
• /home/rex/ebltrunk/core/libeblearn/include/ebl_machines.hpp