BatchNorm1D Class Reference

A class that implements 1D batch normalization, inheriting from MLFunction. More...

#include <BatchNorm.h>

Inheritance diagram for BatchNorm1D:

Public Member Functions
	BatchNorm1D (float *weights, float *bias, int numDims, float eps=1e-05)
	Constructor that initializes the batch normalization operation with weights, biases, and dimensions.
void	apply (const SelectivityVector &rows, std::vector< VectorPtr > &args, const TypePtr &type, exec::EvalCtx &context, VectorPtr &output) const override
	Applies 1D batch normalization to the input array.
float *	getTensor () const override
	Returns the tensor associated with this function.
float *	getWeight ()
	Returns the weights of the batch normalization.
float *	getBias ()
	Returns the biases of the batch normalization.
std::string	getWeightsFile ()
	Returns the path to the weights file.
void	setWeights (float *weights)
	Sets the weights for the batch normalization.
CostEstimate	getCost (std::vector< int > inputDims)
	Estimates the computational cost of applying batch normalization.
Public Member Functions inherited from MLFunction
virtual	~MLFunction ()=default
	Virtual destructor.
virtual std::vector< int >	getDims ()
	Returns the dimensions of the function.
virtual std::string	getFuncName ()
	Returns the name of the function.
virtual int	getNumDims ()
	Returns the number of dimensions of the function.

Static Public Member Functions
static std::vector< std::shared_ptr< exec::FunctionSignature > >	signatures ()
	Returns the function signatures supported by this class.
static std::string	getName ()
	Returns the name of the function.

Additional Inherited Members
Protected Member Functions inherited from MLFunction
double	getWeightedCost (std::string name, float cost)
	Calculates the weighted cost of the function.
std::vector< double >	getCoefficientVector (std::string name)
	Retrieves the cost coefficients for the function.
Protected Attributes inherited from MLFunction
std::vector< int >	dims
	Dimensions of the function.

Detailed Description

A class that implements 1D batch normalization, inheriting from MLFunction.

This class provides functionality to apply 1D batch normalization to an input array. Batch normalization normalizes the input by subtracting the mean and dividing by the standard deviation, then scales and shifts the result using learned weights and biases.

Constructor & Destructor Documentation

BatchNorm1D()

BatchNorm1D::BatchNorm1D ( float * weights, float * bias, int numDims, float eps = 1e-05 )

inline

Constructor that initializes the batch normalization operation with weights, biases, and dimensions.

Parameters

weights	A pointer to the weight matrix for scaling.
bias	A pointer to the bias vector for shifting.
numDims	The number of dimensions (features) in the input.
eps	A small value added to the variance to avoid division by zero (default: 1e-05).

Member Function Documentation

apply()

void BatchNorm1D::apply ( const SelectivityVector & rows, std::vector< VectorPtr > & args, const TypePtr & type, exec::EvalCtx & context, VectorPtr & output ) const

inlineoverride

Applies 1D batch normalization to the input array.

This method processes the input array, applies batch normalization, and stores the result in the output vector.

Parameters

rows	A SelectivityVector specifying the rows to process.
args	A vector of input arguments (e.g., the input array).
type	The type of the output vector.
context	The execution context.
output	The output vector where the result will be stored.

getBias()

float * BatchNorm1D::getBias ( )

inline

Returns the biases of the batch normalization.

Returns

A pointer to the bias vector.

getCost()

CostEstimate BatchNorm1D::getCost ( std::vector< int > inputDims )

inlinevirtual

Estimates the computational cost of applying batch normalization.

Parameters

inputDims

A vector containing the dimensions of the input.

Returns

A CostEstimate object representing the estimated cost.

Reimplemented from MLFunction.

getName()

static std::string BatchNorm1D::getName ( )

inlinestatic

Returns the name of the function.

Returns

The name of the function as a string.

getTensor()

float * BatchNorm1D::getTensor ( ) const

inlineoverridevirtual

Returns the tensor associated with this function.

Returns

A pointer to the weight matrix.

Implements MLFunction.

getWeight()

float * BatchNorm1D::getWeight ( )

inline

Returns the weights of the batch normalization.

Returns

A pointer to the weight matrix.

getWeightsFile()

std::string BatchNorm1D::getWeightsFile ( )

inline

Returns the path to the weights file.

Returns

The path to the weights file as a string.

setWeights()

void BatchNorm1D::setWeights ( float * weights )

inline

Sets the weights for the batch normalization.

Parameters

weights

A pointer to the new weight matrix.

signatures()

static std::vector< std::shared_ptr< exec::FunctionSignature > > BatchNorm1D::signatures ( )

inlinestatic

Returns the function signatures supported by this class.

Returns

A vector of shared pointers to FunctionSignature objects.

---

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

• BatchNorm.h