NeuralNet::EarlyStopping Class Reference

Inheritance diagram for NeuralNet::EarlyStopping:

Public Member Functions
	EarlyStopping (const std::string &metric="LOSS", double minDelta=0, int patience=0)
	EarlyStopping is a Callback that stops training when a monitored metric has stopped improving.
void	onEpochBegin (Model &model) override
void	onEpochEnd (Model &model) override
	This method will be called at the end of each epoch.
void	onTrainBegin (Model &model) override
void	onTrainEnd (Model &model) override
void	onBatchBegin (Model &model) override
void	onBatchEnd (Model &model) override

Additional Inherited Members
Static Public Member Functions inherited from NeuralNet::Callback
template<typename T >
static void	callMethod (std::shared_ptr< T > callback, const std::string &methodName, Model &model)
	Calls the method of the callback with the given logs.
Static Protected Member Functions inherited from NeuralNet::Callback
static void	checkMetric (const std::string &metric, const std::vector< std::string > &metrics)
static std::unordered_map< std::string, Logs >	getLogs (Model &model)

Constructor & Destructor Documentation

EarlyStopping()

NeuralNet::EarlyStopping::EarlyStopping ( const std::string & metric = "LOSS", double minDelta = 0, int patience = 0 )

inline

EarlyStopping is a Callback that stops training when a monitored metric has stopped improving.

Parameters

metric	The metric to monitor (default: LOSS)
minDelta	Minimum change in the monitored quantity to qualify as an improvement, i.e. an absolute change of less than minDelta, will count as no improvement. (default: 0)
patience	Number of epochs with no improvement after which training will be stopped. (default: 0)

Member Function Documentation

onBatchBegin()

void NeuralNet::EarlyStopping::onBatchBegin ( Model & model )

inlineoverridevirtual

Implements NeuralNet::Callback.

onBatchEnd()

void NeuralNet::EarlyStopping::onBatchEnd ( Model & model )

inlineoverridevirtual

Implements NeuralNet::Callback.

onEpochBegin()

void NeuralNet::EarlyStopping::onEpochBegin ( Model & model )

inlineoverridevirtual

Implements NeuralNet::Callback.

onEpochEnd()

void NeuralNet::EarlyStopping::onEpochEnd ( Model & model )

inlineoverridevirtual

This method will be called at the end of each epoch.

Parameters

epoch	The current epoch
logs	The logs of the current epoch

Returns

Returns true if the training should continue otherwise returns false

Warning

The order of the logs should be the same as the order of the metrics.

Implements NeuralNet::Callback.

onTrainBegin()

void NeuralNet::EarlyStopping::onTrainBegin ( Model & model )

inlineoverridevirtual

Implements NeuralNet::Callback.

onTrainEnd()

void NeuralNet::EarlyStopping::onTrainEnd ( Model & model )

inlineoverridevirtual

Implements NeuralNet::Callback.

---

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

• /github/workspace/src/NeuralNet/callbacks/EarlyStopping.hpp