libeblearn
ebl::lenet7< T, Tstate > Class Template Reference

#include <ebl_machines.h>

Inheritance diagram for ebl::lenet7< T, Tstate >:
ebl::net_cscscf< T, Tstate > ebl::layers< T, Tstate > ebl::module_1_1< T, Tstate, Tstate > ebl::module

List of all members.

Public Member Functions

 lenet7 (parameter< T, Tstate > &prm, intg image_height, intg image_width, intg output_size, bool norm=false, bool mirror=false, bool tanh=false, bool shrink=false, bool diag=false)

Detailed Description

template<typename T, class Tstate = bbstate_idx<T>>
class ebl::lenet7< T, Tstate >

Lenet7, similar to lenet5 with different neural connections. This network takes a 1-layer image as input.


Constructor & Destructor Documentation

template<typename T , class Tstate >
ebl::lenet7< T, Tstate >::lenet7 ( parameter< T, Tstate > &  prm,
intg  image_height,
intg  image_width,
intg  output_size,
bool  norm = false,
bool  mirror = false,
bool  tanh = false,
bool  shrink = false,
bool  diag = false 
)
Parameters:
output_sizethe number of ouputs. For a 5 class classifier like NORB, this would be 5.

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