A class for performing 2D convolution operations as part of a machine learning function. More...

#include <functions.h>

Inheritance diagram for Convolute:

Public Member Functions
	Convolute (float weights, int dims_)
	Constructs a new Convolute object.

void	apply (const SelectivityVector &rows, std::vector< VectorPtr > &args, const TypePtr &type, exec::EvalCtx &context, VectorPtr &output) const override
	Applies the 2D convolution operation to the input data.

float *	getTensor () const override
	Returns the filter weights tensor.

std::string	getFuncName ()
	Returns the name of the function.

Public Member Functions inherited from MLFunction
virtual	~MLFunction ()=default
	Virtual destructor.

virtual std::vector< int >	getDims ()
	Returns the dimensions of the function.

virtual int	getNumDims ()
	Returns the number of dimensions of the function.

virtual CostEstimate	getCost (std::vector< int > inputDims)
	Estimates the computational cost of applying the function.

Static Public Member Functions
static std::vector< std::shared_ptr< exec::FunctionSignature > >	signatures ()
	Returns the function signatures for the convolution operation.

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 for performing 2D convolution operations as part of a machine learning function.

This class implements a 2D convolution operation using Eigen for matrix operations. It supports multi-channel inputs and filters, and produces multi-channel outputs.

Constructor & Destructor Documentation

◆ Convolute()

Convolute::Convolute	(	float *	weights,
		int *	dims_ )

inline

Constructs a new Convolute object.

Parameters

weights	A pointer to the filter weights.
dims_	An array of dimensions describing the filters and input: dims_[0]: Number of filters. dims_[1]: Filter height. dims_[2]: Filter width. dims_[3]: Number of input channels. dims_[4]: Input height. dims_[5]: Input width.

Member Function Documentation

◆ apply()

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

inlineoverride

Applies the 2D convolution operation to the input data.

Parameters

rows	A SelectivityVector indicating which rows to process.
args	A vector of input arguments (only the first argument is used).
type	The type of the output vector.
context	The evaluation context.
output	The output vector where the results will be stored.

◆ getFuncName()

std::string Convolute::getFuncName ( )

inlinevirtual

Returns the name of the function.

Returns: A string representing the function name.

Reimplemented from MLFunction.

◆ getName()

static std::string Convolute::getName ( )

inlinestatic

Returns the name of the function.

Returns: A string representing the function name.

◆ getTensor()

float * Convolute::getTensor ( ) const

inlineoverridevirtual

Returns the filter weights tensor.

Returns: A pointer to the filter weights.

Implements MLFunction.

◆ signatures()

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

inlinestatic

Returns the function signatures for the convolution operation.

Returns: A vector of shared pointers to FunctionSignature objects.

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

functions.h

Public Member Functions

Static Public Member Functions

Additional Inherited Members