Inheritance diagram for NeuralNet::Network:

Public Member Functions
void	setup (const std::shared_ptr< Optimizer > &optimizer, LOSS loss=LOSS::QUADRATIC)
	Method that sets up the model's hyperparameter.

void	addLayer (std::shared_ptr< Layer > &layer)
	Method to add a layer to the network.

void	setLoss (LOSS loss)
	This method will set the network's loss function.

std::shared_ptr< Layer >	getLayer (int index) const
	This method will return the Layer residing at the specified index.

std::shared_ptr< Layer >	getOutputLayer () const
	This method will return the output layer (the last layer of the network)

size_t	getNumLayers () const
	This method will get you the number of layers currently in the Network.

std::string	getSlug () const
	Get the slug of the network based on it's architecture.

double	train (std::vector< std::vector< double > > X, std::vector< double > y, int epochs=1, const std::vector< std::shared_ptr< Callback > > callbacks={}, bool progBar=true)
	This method will Train the model with the given inputs and labels.

double	train (std::vector< std::vector< std::vector< double > > > X, std::vector< double > y, int epochs=1, const std::vector< std::shared_ptr< Callback > > callbacks={}, bool progBar=true)
	This method will Train the model with the given inputs and labels.

double	train (TrainingData< std::vector< std::vector< double > >, std::vector< double > > trainingData, int epochs=1, const std::vector< std::shared_ptr< Callback > > callbacks={}, bool progBar=true)
	This method will train the model with the given TrainingData.

double	train (TrainingData< std::vector< std::vector< std::vector< double > > >, std::vector< double > > trainingData, int epochs=1, const std::vector< std::shared_ptr< Callback > > callbacks={}, bool progBar=true)
	This method will train the model with the given TrainingData.

Eigen::MatrixXd	predict (std::vector< std::vector< double > > inputs)
	This model will try to make predictions based off the inputs passed.

Eigen::MatrixXd	predict (std::vector< std::vector< std::vector< double > > > inputs)
	This model will try to make predictions based off the inputs passed.

void	to_file (const std::string &filename) override
	Save the current model to a binary file.

void	from_file (const std::string &filename) override
	Load a model's params from a file.

Friends
class	cereal::access

Additional Inherited Members
Static Public Member Functions inherited from NeuralNet::Model
template<typename T, typename = typename std::enable_if< std::is_base_of<Model, T>::value>::type>
static void	save_to_file (const std::string &filename, T model)
	This method will save (by serializing) the model passed as argument to a .bin file.

template<typename T, typename = typename std::enable_if< std::is_base_of<Model, T>::value>::type>
static void	load_from_file (const std::string &filename, T &model)
	This static method loads a Model from a file and assigns it to the supposedly "empty" model passed as argument.

Protected Member Functions inherited from NeuralNet::Model
void	registerSignals () const

Protected Attributes inherited from NeuralNet::Model
int	cEpoch = 0

double	loss = 0

double	accuracy = 0

double	testLoss = 0

double	testAccuracy = 0

Member Function Documentation

◆ addLayer()

void Network::addLayer ( std::shared_ptr< Layer > & layer )

Method to add a layer to the network.

Parameters

layer the layer to add to the model it should be of type Layer

◆ from_file()

void NeuralNet::Network::from_file ( const std::string & filename )

inlineoverridevirtual

Load a model's params from a file.

Parameters

filename the name of the from which to load the model params

Implements NeuralNet::Model.

◆ getLayer()

std::shared_ptr< Layer > Network::getLayer ( int index ) const

This method will return the Layer residing at the specified index.

Parameters

index The index from which to fetch the layer

Returns: Layer at specified index

◆ getNumLayers()

size_t Network::getNumLayers ( ) const

This method will get you the number of layers currently in the Network.

Returns: A size_t representing the number of layers in the Network

◆ getOutputLayer()

std::shared_ptr< Layer > Network::getOutputLayer ( ) const

This method will return the output layer (the last layer of the network)

Returns: The output Layer

◆ getSlug()

std::string Network::getSlug ( ) const

Get the slug of the network based on it's architecture.

Returns: A string representing the combined slug of the different components in the Network

◆ predict() [1/2]

Eigen::MatrixXd Network::predict ( std::vector< std::vector< double > > inputs )

This model will try to make predictions based off the inputs passed.

Parameters

inputs The inputs that will be passed through the network

Returns: This method will return the outputs of the neural network

◆ predict() [2/2]

Eigen::MatrixXd Network::predict ( std::vector< std::vector< std::vector< double > > > inputs )

This model will try to make predictions based off the inputs passed.

Parameters

inputs The inputs that will be passed through the network

Returns: This method will return the outputs of the neural network

◆ setLoss()

void Network::setLoss ( LOSS loss )

This method will set the network's loss function.

Parameters

loss	The loss function (choose from the list of LOSS enums)

◆ setup()

void Network::setup	(	const std::shared_ptr< Optimizer > &	optimizer,
		LOSS	loss = LOSS::QUADRATIC )

Method that sets up the model's hyperparameter.

Parameters

optimizer	An Optimizer's child class
epochs	The number of epochs
loss	The loss function

◆ to_file()

void NeuralNet::Network::to_file ( const std::string & filename )

inlineoverridevirtual

Save the current model to a binary file.

Parameters

filename the name of the file in which to save the model params

Implements NeuralNet::Model.

◆ train() [1/4]

double Network::train	(	std::vector< std::vector< double > >	X,
		std::vector< double >	y,
		int	epochs = 1,
		const std::vector< std::shared_ptr< Callback > >	callbacks = {},
		bool	progBar = true )

This method will Train the model with the given inputs and labels.

Parameters

X	The inputs that will be passed to the model
y	The labels that represent the expected outputs of the model
epochs
callbacks	A vector of `Callback` that will be called during training stages
progBar	Ouput a progress bar for the training process . Default: `true`

Returns: The last training's loss

◆ train() [2/4]

double Network::train	(	std::vector< std::vector< std::vector< double > > >	X,
		std::vector< double >	y,
		int	epochs = 1,
		const std::vector< std::shared_ptr< Callback > >	callbacks = {},
		bool	progBar = true )

This method will Train the model with the given inputs and labels.

Parameters

inputs	The inputs that will be passed to the model
labels	The labels that represent the expected outputs of the model
epochs
callbacks	A vector of `Callback` that will be called during training stages
progBar	Whether to output a progress bar for the training process. Default: `true`

Returns: The last training's loss

◆ train() [3/4]

double Network::train	(	TrainingData< std::vector< std::vector< double > >, std::vector< double > >	trainingData,
		int	epochs = 1,
		const std::vector< std::shared_ptr< Callback > >	callbacks = {},
		bool	progBar = true )

This method will train the model with the given TrainingData.

Parameters

trainingData	the data passed through the TrainingData class
epochs
callbacks	A vector of `Callback` that will be called during training stages
progBar	Whether to output a progress bar for the training process. Default: `true`

Returns: The last training's loss

◆ train() [4/4]

double Network::train	(	TrainingData< std::vector< std::vector< std::vector< double > > >, std::vector< double > >	trainingData,
		int	epochs = 1,
		const std::vector< std::shared_ptr< Callback > >	callbacks = {},
		bool	progBar = true )

This method will train the model with the given TrainingData.

Parameters

trainingData	the data passed through the TrainingData class
epochs
callbacks	A vector of `Callback` that will be called during training stages
progBar	Whether to output a progress bar for the training process. Default: `true`

Returns: The last training's loss

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

/github/workspace/src/NeuralNet/Network.hpp
/github/workspace/src/NeuralNet/Network.cpp

Public Member Functions

Friends

Additional Inherited Members

Member Function Documentation

◆ addLayer()

◆ from_file()

◆ getLayer()

◆ getNumLayers()

◆ getOutputLayer()

◆ getSlug()

◆ predict() [1/2]

◆ predict() [2/2]

◆ setLoss()

◆ setup()

◆ to_file()

◆ train() [1/4]

◆ train() [2/4]

◆ train() [3/4]

◆ train() [4/4]