FullyConnectWithBatchNormAndRelu Class Reference

A class that implements a fully connected layer with batch normalization and ReLU activation, inheriting from MLFunction. More...

Inheritance diagram for FullyConnectWithBatchNormAndRelu:

Public Member Functions
	FullyConnectWithBatchNormAndRelu (float *NNWeights, float *NNBias, float *NormWeights, float *NormBias, float eps, int numInput, int numOutput)
	Constructor that initializes the fully connected layer 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 the fully connected layer, batch normalization, and ReLU activation to the input array.
float *	getTensor () const override
	Returns the tensor associated with this function.
std::string	getWeightsFile ()
	Returns the path to the weights file.
void	setWeights (float *weights)
	Sets the weights for the fully connected layer.
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 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 a fully connected layer with batch normalization and ReLU activation, inheriting from MLFunction.

This class provides functionality to apply a fully connected layer, followed by batch normalization and ReLU activation, to an input array.

Constructor & Destructor Documentation

FullyConnectWithBatchNormAndRelu()

FullyConnectWithBatchNormAndRelu::FullyConnectWithBatchNormAndRelu ( float * NNWeights, float * NNBias, float * NormWeights, float * NormBias, float eps, int numInput, int numOutput )

inline

Constructor that initializes the fully connected layer with weights, biases, and dimensions.

Parameters

NNWeights	A pointer to the weight matrix for the fully connected layer.
NNBias	A pointer to the bias vector for the fully connected layer.
NormWeights	A pointer to the weight matrix for batch normalization.
NormBias	A pointer to the bias vector for batch normalization.
eps	A small value added to the variance to avoid division by zero.
numInput	The number of input features.
numOutput	The number of output features.

Member Function Documentation

apply()

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

inlineoverride

Applies the fully connected layer, batch normalization, and ReLU activation to the input array.

This method processes the input array, applies the fully connected layer, batch normalization, and ReLU activation, 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.

getName()

static std::string FullyConnectWithBatchNormAndRelu::getName ( )

inlinestatic

Returns the name of the function.

Returns

The name of the function as a string ("fully_layer_with_batch_norm").

getTensor()

float * FullyConnectWithBatchNormAndRelu::getTensor ( ) const

inlineoverridevirtual

Returns the tensor associated with this function.

Returns

A pointer to the weight matrix for the fully connected layer.

Implements MLFunction.

getWeightsFile()

std::string FullyConnectWithBatchNormAndRelu::getWeightsFile ( )

inline

Returns the path to the weights file.

Returns

The path to the weights file as a string.

setWeights()

void FullyConnectWithBatchNormAndRelu::setWeights ( float * weights )

inline

Sets the weights for the fully connected layer.

Parameters

weights

A pointer to the new weight matrix.

signatures()

static std::vector< std::shared_ptr< exec::FunctionSignature > > FullyConnectWithBatchNormAndRelu::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:

• ComplexLayer.cpp