Settings for classificationused to distinguish between different function signatures.

contains additional settings if the DNN problem is classification

Definition at line 894 of file NeuralNet.h.

Public Member Functions
	ClassificationSettings (TString name, size_t _convergenceSteps=15, size_t _batchSize=10, size_t _testRepetitions=7, double _factorWeightDecay=1e-5, EnumRegularization _regularization=EnumRegularization::NONE, size_t _scaleToNumEvents=0, MinimizerType _eMinimizerType=MinimizerType::fSteepest, double _learningRate=1e-5, double _momentum=0.3, int _repetitions=3, bool _useMultithreading=true)
	c'tor

virtual	~ClassificationSettings ()
	d'tor

virtual void	endTestCycle ()
	action to be done when the training cycle is ended (e.g.

void	endTrainCycle (double)
	action to be done when the training cycle is ended (e.g.

void	setResultComputation (std::string _fileNameNetConfig, std::string _fileNameResult, std::vector< Pattern > *_resultPatternContainer)
	preparation for monitoring output

void	setWeightSums (double sumOfSigWeights, double sumOfBkgWeights)
	set the weight sums to be scaled to (preparations for monitoring output)

virtual void	startTestCycle ()
	action to be done when the test cycle is started (e.g.

void	startTrainCycle ()
	action to be done when the training cycle is started (e.g.

void	testIteration ()
	callback for monitoring and loggging

void	testSample (double error, double output, double target, double weight)
	action to be done after the computation of a test sample (e.g.

Public Member Functions inherited from TMVA::DNN::Settings
	Settings (TString name, size_t _convergenceSteps=15, size_t _batchSize=10, size_t _testRepetitions=7, double _factorWeightDecay=1e-5, TMVA::DNN::EnumRegularization _regularization=TMVA::DNN::EnumRegularization::NONE, MinimizerType _eMinimizerType=MinimizerType::fSteepest, double _learningRate=1e-5, double _momentum=0.3, int _repetitions=3, bool _multithreading=true)
	c'tor

virtual	~Settings ()
	d'tor

void	addPoint (std::string histoName, double x)
	for monitoring

void	addPoint (std::string histoName, double x, double y)
	for monitoring

size_t	batchSize () const
	mini-batch size

void	clear (std::string histoName)
	for monitoring

virtual void	computeResult (const Net &, std::vector< double > &)
	callback for monitoring and logging

size_t	convergenceCount () const
	returns the current convergence count

size_t	convergenceSteps () const
	how many steps until training is deemed to have converged

void	create (std::string histoName, int bins, double min, double max)
	for monitoring

void	create (std::string histoName, int bins, double min, double max, int bins2, double min2, double max2)
	for monitoring

virtual void	cycle (double progress, TString text)

virtual void	drawSample (const std::vector< double > &, const std::vector< double > &, const std::vector< double > &, double)
	callback for monitoring and logging

const std::vector< double > &	dropFractions () const

size_t	dropRepetitions () const

bool	exists (std::string histoName)
	for monitoring

double	factorWeightDecay () const
	get the weight-decay factor

virtual bool	hasConverged (double testError)
	has this training converged already?

double	learningRate () const
	get the learning rate

size_t	maxConvergenceCount () const
	returns the max convergence count so far

size_t	minError () const
	returns the smallest error so far

MinimizerType	minimizerType () const
	which minimizer shall be used (e.g. SGD)

double	momentum () const
	get the momentum (e.g. for SGD)

void	pads (int numPads)
	preparation for monitoring

void	plot (std::string histoName, std::string options, int pad, EColor color)
	for monitoring

EnumRegularization	regularization () const
	some regularization of the DNN is turned on?

int	repetitions () const
	how many steps have to be gone until the batch is changed

template<typename Iterator >
void	setDropOut (Iterator begin, Iterator end, size_t _dropRepetitions)
	set the drop-out configuration (layer-wise)

void	setMonitoring (std::shared_ptr< Monitoring > ptrMonitoring)
	prepared for monitoring

virtual void	setProgressLimits (double minProgress=0, double maxProgress=100)

virtual void	startTraining ()

size_t	testRepetitions () const
	how often is the test data tested

bool	useMultithreading () const
	is multithreading turned on?

Public Attributes
std::vector< double >	m_ams

double	m_cutValue

std::string	m_fileNameNetConfig

std::string	m_fileNameResult

std::vector< double >	m_input

std::vector< double >	m_output

std::vector< Pattern > *	m_pResultPatternContainer

size_t	m_scaleToNumEvents

std::vector< double >	m_significances

double	m_sumOfBkgWeights

double	m_sumOfSigWeights

std::vector< double >	m_targets

std::vector< double >	m_weights

Public Attributes inherited from TMVA::DNN::Settings
size_t	count_dE

size_t	count_E

size_t	count_mb_dE

size_t	count_mb_E

double	fLearningRate

MinimizerType	fMinimizerType

double	fMomentum

int	fRepetitions

size_t	m_batchSize
	mini-batch size

size_t	m_convergenceCount

size_t	m_convergenceSteps
	number of steps without improvement to consider the DNN to have converged

std::vector< double >	m_dropOut

double	m_dropRepetitions

double	m_factorWeightDecay

size_t	m_maxConvergenceCount

double	m_maxProgress
	current limits for the progress bar

double	m_minError

double	m_minProgress
	current limits for the progress bar

EnumRegularization	m_regularization

size_t	m_testRepetitions

Timer	m_timer
	timer for monitoring

Additional Inherited Members
Protected Attributes inherited from TMVA::DNN::Settings
std::shared_ptr< Monitoring >	fMonitoring

bool	m_useMultithreading

#include <TMVA/NeuralNet.h>

Inheritance diagram for TMVA::DNN::ClassificationSettings:

[legend]

Constructor & Destructor Documentation

◆ ClassificationSettings()

TMVA::DNN::ClassificationSettings::ClassificationSettings	(	TString	name,
		size_t	_convergenceSteps = 15,
		size_t	_batchSize = 10,
		size_t	_testRepetitions = 7,
		double	_factorWeightDecay = 1e-5,
		EnumRegularization	_regularization = EnumRegularization::NONE,
		size_t	_scaleToNumEvents = 0,
		MinimizerType	_eMinimizerType = MinimizerType::fSteepest,
		double	_learningRate = 1e-5,
		double	_momentum = 0.3,
		int	_repetitions = 3,
		bool	_useMultithreading = true )

inline

c'tor

Definition at line 901 of file NeuralNet.h.

◆ ~ClassificationSettings()

virtual TMVA::DNN::ClassificationSettings::~ClassificationSettings ( )

inlinevirtual

d'tor

Definition at line 924 of file NeuralNet.h.

Member Function Documentation

◆ endTestCycle()

void TMVA::DNN::ClassificationSettings::endTestCycle ( )

virtual

action to be done when the training cycle is ended (e.g.

update some monitoring output)

Reimplemented from TMVA::DNN::Settings.

Definition at line 326 of file NeuralNet.cxx.

◆ endTrainCycle()

void TMVA::DNN::ClassificationSettings::endTrainCycle ( double )

virtual

action to be done when the training cycle is ended (e.g.

update some monitoring output)

Reimplemented from TMVA::DNN::Settings.

Definition at line 296 of file NeuralNet.cxx.

◆ setResultComputation()

void TMVA::DNN::ClassificationSettings::setResultComputation	(	std::string	_fileNameNetConfig,
		std::string	_fileNameResult,
		std::vector< Pattern > *	_resultPatternContainer )

preparation for monitoring output

Definition at line 520 of file NeuralNet.cxx.

◆ setWeightSums()

void TMVA::DNN::ClassificationSettings::setWeightSums	(	double	sumOfSigWeights,
		double	sumOfBkgWeights )

set the weight sums to be scaled to (preparations for monitoring output)

Definition at line 512 of file NeuralNet.cxx.

◆ startTestCycle()

void TMVA::DNN::ClassificationSettings::startTestCycle ( )

virtual

action to be done when the test cycle is started (e.g.

update some monitoring output)

Reimplemented from TMVA::DNN::Settings.

Definition at line 316 of file NeuralNet.cxx.

◆ startTrainCycle()

void TMVA::DNN::ClassificationSettings::startTrainCycle ( )

virtual

action to be done when the training cycle is started (e.g.

update some monitoring output)

Reimplemented from TMVA::DNN::Settings.

Definition at line 281 of file NeuralNet.cxx.

◆ testIteration()

void TMVA::DNN::ClassificationSettings::testIteration ( )

inlinevirtual

callback for monitoring and loggging

Reimplemented from TMVA::DNN::Settings.

Definition at line 930 of file NeuralNet.h.

◆ testSample()

void TMVA::DNN::ClassificationSettings::testSample	(	double	error,
		double	output,
		double	target,
		double	weight )

virtual

action to be done after the computation of a test sample (e.g.

update some monitoring output)

Reimplemented from TMVA::DNN::Settings.

Definition at line 304 of file NeuralNet.cxx.

Member Data Documentation

◆ m_ams

std::vector<double> TMVA::DNN::ClassificationSettings::m_ams

Definition at line 1000 of file NeuralNet.h.

◆ m_cutValue

double TMVA::DNN::ClassificationSettings::m_cutValue

Definition at line 1008 of file NeuralNet.h.

◆ m_fileNameNetConfig

std::string TMVA::DNN::ClassificationSettings::m_fileNameNetConfig

Definition at line 1011 of file NeuralNet.h.

◆ m_fileNameResult

std::string TMVA::DNN::ClassificationSettings::m_fileNameResult

Definition at line 1010 of file NeuralNet.h.

◆ m_input

std::vector<double> TMVA::DNN::ClassificationSettings::m_input

Definition at line 995 of file NeuralNet.h.

◆ m_output

std::vector<double> TMVA::DNN::ClassificationSettings::m_output

Definition at line 996 of file NeuralNet.h.

◆ m_pResultPatternContainer

std::vector<Pattern>* TMVA::DNN::ClassificationSettings::m_pResultPatternContainer

Definition at line 1009 of file NeuralNet.h.

◆ m_scaleToNumEvents

size_t TMVA::DNN::ClassificationSettings::m_scaleToNumEvents

Definition at line 1006 of file NeuralNet.h.

◆ m_significances

std::vector<double> TMVA::DNN::ClassificationSettings::m_significances

Definition at line 1001 of file NeuralNet.h.

◆ m_sumOfBkgWeights

double TMVA::DNN::ClassificationSettings::m_sumOfBkgWeights

Definition at line 1005 of file NeuralNet.h.

◆ m_sumOfSigWeights

double TMVA::DNN::ClassificationSettings::m_sumOfSigWeights

Definition at line 1004 of file NeuralNet.h.

◆ m_targets

std::vector<double> TMVA::DNN::ClassificationSettings::m_targets

Definition at line 997 of file NeuralNet.h.

◆ m_weights

std::vector<double> TMVA::DNN::ClassificationSettings::m_weights

Definition at line 998 of file NeuralNet.h.

Libraries for TMVA::DNN::ClassificationSettings:

[legend]

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

tmva/tmva/inc/TMVA/NeuralNet.h
tmva/tmva/src/NeuralNet.cxx

Public Member Functions

Public Attributes

Additional Inherited Members

Constructor & Destructor Documentation

◆ ClassificationSettings()

◆ ~ClassificationSettings()

Member Function Documentation

◆ endTestCycle()

◆ endTrainCycle()

◆ setResultComputation()

◆ setWeightSums()

◆ startTestCycle()

◆ startTrainCycle()

◆ testIteration()

◆ testSample()

Member Data Documentation

◆ m_ams

◆ m_cutValue

◆ m_fileNameNetConfig

◆ m_fileNameResult

◆ m_input

◆ m_output

◆ m_pResultPatternContainer

◆ m_scaleToNumEvents

◆ m_significances

◆ m_sumOfBkgWeights

◆ m_sumOfSigWeights

◆ m_targets

◆ m_weights