NeuralNet::Layer Class Reference

Inheritance diagram for NeuralNet::Layer:

Public Member Functions
Eigen::MatrixXd	getOutputs () const
	This method get the layer's outputs.
int	getNumNeurons () const
	This method get the number of neurons actually in the layer.
virtual std::string	getSlug () const =0
	The slug of the layers (name + main parameter value)
void	printOutputs ()
	Method to print layer's outputs.
virtual Eigen::MatrixXd	feedInputs (std::vector< double > inputs, bool training=false)
	This method is used to feed the inputs to the layer.
virtual Eigen::MatrixXd	feedInputs (Eigen::MatrixXd inputs, bool training=false)=0
	This method is used to feed the inputs to the layer.
virtual void	feedInputs (std::vector< std::vector< std::vector< double > > > inputs, bool training=false)
	This method is used to feed the inputs to the layer.
const std::string	typeStr ()

Protected Member Functions
void	setOutputs (Eigen::MatrixXd outputs)
void	setOutputs (std::vector< double > outputs)
	This method is used to set the outputs of the layer.
virtual Eigen::MatrixXd	computeOutputs (Eigen::MatrixXd inputs, bool training=false)=0
	This method is used to feed the inputs to the layer.
virtual void	init (int args)
	Layer (std::tuple< int, int > inputShape)

Protected Attributes
int	nNeurons
Eigen::MatrixXd	outputs
LayerType	type = LayerType::DEFAULT
bool	trainingOnly = false

Friends
class	Network
class	cereal::access

Member Function Documentation

computeOutputs()

virtual Eigen::MatrixXd NeuralNet::Layer::computeOutputs ( Eigen::MatrixXd inputs, bool training = false )

protectedpure virtual

This method is used to feed the inputs to the layer.

Parameters

inputs

A vector of vectors of doubles representing the inputs (features)

Returns

an Eigen::MatrixXd representing the computed outputs based on the layer's parameters

Implemented in NeuralNet::Dropout.

feedInputs() [1/3]

virtual Eigen::MatrixXd NeuralNet::Layer::feedInputs ( Eigen::MatrixXd inputs, bool training = false )

pure virtual

This method is used to feed the inputs to the layer.

Parameters

inputs

An Eigen::MatrixXd representing the inputs (features)

Returns

an Eigen::MatrixXd representing the outputs of the layer

Implemented in NeuralNet::Dense, NeuralNet::Dropout, and NeuralNet::Flatten.

feedInputs() [2/3]

virtual Eigen::MatrixXd NeuralNet::Layer::feedInputs ( std::vector< double > inputs, bool training = false )

inlinevirtual

This method is used to feed the inputs to the layer.

Parameters

inputs

A vector of doubles representing the inputs (features)

Returns

an Eigen::MatrixXd representing the outputs of the layer

feedInputs() [3/3]

virtual void NeuralNet::Layer::feedInputs ( std::vector< std::vector< std::vector< double > > > inputs, bool training = false )

inlinevirtual

This method is used to feed the inputs to the layer.

Parameters

inputs

A vector of vectors of doubles representing the inputs (features)

Returns

void

Reimplemented in NeuralNet::Flatten.

getNumNeurons()

int NeuralNet::Layer::getNumNeurons ( ) const

inline

This method get the number of neurons actually in the layer.

Returns

The number of neurons in the layer

getOutputs()

Eigen::MatrixXd NeuralNet::Layer::getOutputs ( ) const

inline

This method get the layer's outputs.

Returns

an Eigen::Eigen::MatrixXd representing the layer's outputs

getSlug()

virtual std::string NeuralNet::Layer::getSlug ( ) const

pure virtual

The slug of the layers (name + main parameter value)

Returns

the slug

Implemented in NeuralNet::Dense, NeuralNet::Dropout, and NeuralNet::Flatten.

init()

virtual void NeuralNet::Layer::init ( int args )

inlineprotectedvirtual

This function will be used to properly initialize the Layer It's being done like this because of the number of neurons of the previous layer that's unkown prior

Reimplemented in NeuralNet::Dropout.

setOutputs() [1/2]

void NeuralNet::Layer::setOutputs ( Eigen::MatrixXd outputs )

inlineprotected

Parameters

outputs

the outputs to store

setOutputs() [2/2]

void NeuralNet::Layer::setOutputs ( std::vector< double > outputs )

inlineprotected

This method is used to set the outputs of the layer.

Parameters

outputs

A vector of doubles representing the outputs of the layer

Returns

void

Note

This method is used for the input layer (the first layer of the network)

typeStr()

const std::string NeuralNet::Layer::typeStr ( )

inline

Returns the layer type as string

Note

Returns "Base" for base class Layer and "Unknown" if no type specified.

---

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

• /github/workspace/src/NeuralNet/layers/Layer.hpp