Embedding Class Reference

Implements an embedding layer for machine learning, where embeddings are stored as a 2-D array. More...

#include <Embedding.h>

Inheritance diagram for Embedding:

Public Member Functions
	Embedding (float *weights, int numEmbeddings, int embeddingDims)
	Constructor for Embedding.
	Embedding (std::string weightsFile, int numEmbeddings, int embeddingDims)
	Constructor for Embedding.
void	apply (const SelectivityVector &rows, std::vector< VectorPtr > &args, const TypePtr &type, exec::EvalCtx &context, VectorPtr &output) const override
	Applies the embedding function to the input data.
float *	getTensor () const override
	Returns the tensor associated with the function.
std::string	getWeightsFile ()
	Returns the path to the weights file.
void	setWeights (float *weights)
	Sets the embedding weights.
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.
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.
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

Implements an embedding layer for machine learning, where embeddings are stored as a 2-D array.

Constructor & Destructor Documentation

Embedding() [1/2]

Embedding::Embedding ( float * weights, int numEmbeddings, int embeddingDims )

inline

Constructor for Embedding.

Parameters

weights	Pointer to the embedding weights.
numEmbeddings	Number of embeddings.
embeddingDims	Dimensionality of each embedding.

Embedding() [2/2]

Embedding::Embedding ( std::string weightsFile, int numEmbeddings, int embeddingDims )

inline

Constructor for Embedding.

Parameters

weightsFile	Path to the file containing the embedding weights.
numEmbeddings	Number of embeddings.
embeddingDims	Dimensionality of each embedding.

Member Function Documentation

apply()

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

inlineoverride

Applies the embedding function to the input data.

Parameters

rows	Selectivity vector indicating which rows to process.
args	Vector of input arguments.
type	Type of the output vector.
context	Evaluation context.
output	Output vector to store the results.

getName()

static std::string Embedding::getName ( )

inlinestatic

Returns the name of the function.

Returns

Function name.

getTensor()

float * Embedding::getTensor ( ) const

inlineoverridevirtual

Returns the tensor associated with the function.

Returns

Pointer to the tensor.

Implements MLFunction.

getWeightsFile()

std::string Embedding::getWeightsFile ( )

inline

Returns the path to the weights file.

Returns

Path to the weights file.

setWeights()

void Embedding::setWeights ( float * weights )

inline

Sets the embedding weights.

Parameters

weights

Pointer to the embedding weights.

signatures()

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

inlinestatic

Returns the function signatures.

Returns

Vector of function signatures.

---

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

• Embedding.h