DataSet Class Reference

#include <DataSet.h>

Inheritance diagram for DataSet:

Public Member Functions
	DataSet (const char *filePath, size_t inputCount, size_t outputCount)
	DataSet (size_t inputCount, size_t outputCount)
virtual void	PrepareDirectory (const char *filePath)

Public Attributes
size_t	InputCount
	number input elements More...
size_t	OutputCount
	number output elements More...
Set	Training
	set for training More...
Set	Validation
	set for validation of training More...
Set	Test
	set to test after training More...
int	maxEpoch = 1000
	number of epochs while training More...
double	stopThreshold = 0.001
	threshold for loss to prevent over-fitting More...
double	eta = 0.0051
	learning rate More...
int	batchSize = 5
	number of elements per batch More...
bool	verbose = false
	use verbose output during fitting More...

Friends
class	ImageDataSet

Detailed Description

dataset representation

Constructor & Destructor Documentation

DataSet() [1/2]

DataSet::DataSet ( const char *  filePath, size_t  inputCount, size_t  outputCount  )

inline

regular constructor

Parameters

filePath	path with dataset data files
inputCount	number input elements
outputCount	number output elements

DataSet() [2/2]

DataSet::DataSet ( size_t  inputCount, size_t  outputCount  )

inline

initialization constructor, initializes required structures by given dimensions

Parameters

inputCount	number input elements
outputCount	number output elements

Member Function Documentation

PrepareDirectory()

virtual void DataSet::PrepareDirectory ( const char *  filePath )

inlinevirtual

interface definition, does nothing here

Parameters

filePath

Reimplemented in ImageDataSet.

Friends And Related Function Documentation

ImageDataSet

friend class ImageDataSet

friend

Member Data Documentation

batchSize

int DataSet::batchSize = 5

number of elements per batch

eta

double DataSet::eta = 0.0051

learning rate

InputCount

size_t DataSet::InputCount

number input elements

maxEpoch

int DataSet::maxEpoch = 1000

number of epochs while training

OutputCount

size_t DataSet::OutputCount

number output elements

stopThreshold

double DataSet::stopThreshold = 0.001

threshold for loss to prevent over-fitting

Test

Set DataSet::Test

set to test after training

Training

Set DataSet::Training

set for training

Validation

Set DataSet::Validation

set for validation of training

verbose

bool DataSet::verbose = false

use verbose output during fitting

---

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

• include/math/ds/DataSet.h