Belle II Software development
Public Attributes | List of all members
GRLNeuro::Parameters Struct Reference

Struct to keep neurotrigger parameters. More...

#include <GRLNeuro.h>

Public Attributes

unsigned nMLP
 Number of networks.
 
std::vector< std::vector< float > > nHidden
 Number of nodes in each hidden layer for all networks or factor to multiply with number of inputs.
 
bool targetresult = true
 train result as output
 
bool multiplyHidden = false
 If true, multiply nHidden with number of input nodes.
 
std::vector< std::vector< float > > outputScale = {{ -1., 1.}}
 Output scale for all networks.
 
unsigned n_cdc_sector
 Number of CDC sectors.
 
std::vector< float > i_cdc_sector
 
unsigned n_ecl_sector
 Number of ECL sectors.
 
std::vector< float > i_ecl_sector
 
std::vector< std::vector< int > > total_bit_bias
 bit width etc.
 
std::vector< std::vector< int > > int_bit_bias
 
std::vector< std::vector< bool > > is_signed_bias
 
std::vector< std::vector< int > > rounding_bias
 
std::vector< std::vector< int > > saturation_bias
 
std::vector< std::vector< int > > total_bit_accum
 
std::vector< std::vector< int > > int_bit_accum
 
std::vector< std::vector< bool > > is_signed_accum
 
std::vector< std::vector< int > > rounding_accum
 
std::vector< std::vector< int > > saturation_accum
 
std::vector< std::vector< int > > total_bit_weight
 
std::vector< std::vector< int > > int_bit_weight
 
std::vector< std::vector< bool > > is_signed_weight
 
std::vector< std::vector< int > > rounding_weight
 
std::vector< std::vector< int > > saturation_weight
 
std::vector< std::vector< int > > total_bit_relu
 
std::vector< std::vector< int > > int_bit_relu
 
std::vector< std::vector< bool > > is_signed_relu
 
std::vector< std::vector< int > > rounding_relu
 
std::vector< std::vector< int > > saturation_relu
 
std::vector< std::vector< int > > total_bit
 
std::vector< std::vector< int > > int_bit
 
std::vector< std::vector< bool > > is_signed
 
std::vector< std::vector< int > > rounding
 
std::vector< std::vector< int > > saturation
 
std::vector< std::vector< std::vector< int > > > W_input
 
std::vector< std::vector< std::vector< int > > > I_input
 

Detailed Description

Struct to keep neurotrigger parameters.

Contains all information that is needed to initialize several expert MLPs (not including values determined during training).

Definition at line 40 of file GRLNeuro.h.

Member Data Documentation

◆ i_cdc_sector

std::vector<float> i_cdc_sector

Definition at line 62 of file GRLNeuro.h.

◆ i_ecl_sector

std::vector<float> i_ecl_sector

Definition at line 65 of file GRLNeuro.h.

◆ I_input

std::vector<std::vector<std::vector<int> > > I_input

Definition at line 94 of file GRLNeuro.h.

◆ int_bit

std::vector<std::vector<int> > int_bit

Definition at line 89 of file GRLNeuro.h.

◆ int_bit_accum

std::vector<std::vector<int> > int_bit_accum

Definition at line 74 of file GRLNeuro.h.

◆ int_bit_bias

std::vector<std::vector<int> > int_bit_bias

Definition at line 69 of file GRLNeuro.h.

◆ int_bit_relu

std::vector<std::vector<int> > int_bit_relu

Definition at line 84 of file GRLNeuro.h.

◆ int_bit_weight

std::vector<std::vector<int> > int_bit_weight

Definition at line 79 of file GRLNeuro.h.

◆ is_signed

std::vector<std::vector<bool> > is_signed

Definition at line 90 of file GRLNeuro.h.

◆ is_signed_accum

std::vector<std::vector<bool> > is_signed_accum

Definition at line 75 of file GRLNeuro.h.

◆ is_signed_bias

std::vector<std::vector<bool> > is_signed_bias

Definition at line 70 of file GRLNeuro.h.

◆ is_signed_relu

std::vector<std::vector<bool> > is_signed_relu

Definition at line 85 of file GRLNeuro.h.

◆ is_signed_weight

std::vector<std::vector<bool> > is_signed_weight

Definition at line 80 of file GRLNeuro.h.

◆ multiplyHidden

bool multiplyHidden = false

If true, multiply nHidden with number of input nodes.

Definition at line 55 of file GRLNeuro.h.

◆ n_cdc_sector

unsigned n_cdc_sector

Number of CDC sectors.

Definition at line 61 of file GRLNeuro.h.

◆ n_ecl_sector

unsigned n_ecl_sector

Number of ECL sectors.

Definition at line 64 of file GRLNeuro.h.

◆ nHidden

std::vector<std::vector<float> > nHidden

Number of nodes in each hidden layer for all networks or factor to multiply with number of inputs.

The number of layers is derived from the shape.

Definition at line 51 of file GRLNeuro.h.

◆ nMLP

unsigned nMLP

Number of networks.

For network specific parameters you can give either a list with values for each network, or a single value that will be used for all. The ranges are also valid if nPhi * nPt * nTheta * nPattern = nMLPs

Definition at line 46 of file GRLNeuro.h.

◆ outputScale

std::vector<std::vector<float> > outputScale = {{ -1., 1.}}

Output scale for all networks.

Definition at line 57 of file GRLNeuro.h.

57{{ -1., 1.}};

◆ rounding

std::vector<std::vector<int> > rounding

Definition at line 91 of file GRLNeuro.h.

◆ rounding_accum

std::vector<std::vector<int> > rounding_accum

Definition at line 76 of file GRLNeuro.h.

◆ rounding_bias

std::vector<std::vector<int> > rounding_bias

Definition at line 71 of file GRLNeuro.h.

◆ rounding_relu

std::vector<std::vector<int> > rounding_relu

Definition at line 86 of file GRLNeuro.h.

◆ rounding_weight

std::vector<std::vector<int> > rounding_weight

Definition at line 81 of file GRLNeuro.h.

◆ saturation

std::vector<std::vector<int> > saturation

Definition at line 92 of file GRLNeuro.h.

◆ saturation_accum

std::vector<std::vector<int> > saturation_accum

Definition at line 77 of file GRLNeuro.h.

◆ saturation_bias

std::vector<std::vector<int> > saturation_bias

Definition at line 72 of file GRLNeuro.h.

◆ saturation_relu

std::vector<std::vector<int> > saturation_relu

Definition at line 87 of file GRLNeuro.h.

◆ saturation_weight

std::vector<std::vector<int> > saturation_weight

Definition at line 82 of file GRLNeuro.h.

◆ targetresult

bool targetresult = true

train result as output

Definition at line 53 of file GRLNeuro.h.

◆ total_bit

std::vector<std::vector<int> > total_bit

Definition at line 88 of file GRLNeuro.h.

◆ total_bit_accum

std::vector<std::vector<int> > total_bit_accum

Definition at line 73 of file GRLNeuro.h.

◆ total_bit_bias

std::vector<std::vector<int> > total_bit_bias

bit width etc.

constant in each node

Definition at line 68 of file GRLNeuro.h.

◆ total_bit_relu

std::vector<std::vector<int> > total_bit_relu

Definition at line 83 of file GRLNeuro.h.

◆ total_bit_weight

std::vector<std::vector<int> > total_bit_weight

Definition at line 78 of file GRLNeuro.h.

◆ W_input

std::vector<std::vector<std::vector<int> > > W_input

Definition at line 93 of file GRLNeuro.h.

The documentation for this struct was generated from the following file: