Structure representing the parameters of the GRU. More...

#include <Gru.hpp>

Public Attributes
poplar::Type	dataType

std::size_t	batchSize
	The batch size. More...

std::size_t	timeSteps
	The number of time steps in the sequence of the GRU. More...

std::vector< std::size_t >	layerSizes
	The number of neurons for the input and output layer. More...

bool	outputFullSequence = true
	If true the GRU function returns the entire sequence of outputs, otherwise it returns just the final output.

bool	calcInputGradients = true
	If this parameter is set to false then the GRU will skip the calculation of the gradients of the inputs.

std::vector< BasicGruCellUnit >	cellOrder = getDefaultBasicGruCellOrder()
	The weights and biases for all of the layers being processed are concatenated in the outermost dimension of the weights and biases tensors. More...

bool	resetAfter = false
	Controls whether the reset gate is applied before or after the candidate weights and biases.

NonLinearityType	activation = NonLinearityType::TANH
	Activation function.

NonLinearityType	recurrentActivation = NonLinearityType::SIGMOID
	Recurrent activation function.

Detailed Description

Structure representing the parameters of the GRU.

Member Data Documentation

◆ batchSize

std::size_t popnn::gru::GruParams::batchSize

The batch size.

Deprecated:: Use rnn::RnnParams.batchSize instead.

◆ cellOrder

std::vector<BasicGruCellUnit> popnn::gru::GruParams::cellOrder = getDefaultBasicGruCellOrder()

The weights and biases for all of the layers being processed are concatenated in the outermost dimension of the weights and biases tensors.

This option allows you to specify the order of the gates in that outermost dimension. The default order can be obtained with getDefaultBasicGruCellOrder().

◆ dataType

poplar::Type popnn::gru::GruParams::dataType

Deprecated:: Use rnn::RnnParams.dataType instead.

◆ layerSizes

std::vector<std::size_t> popnn::gru::GruParams::layerSizes

The number of neurons for the input and output layer.

Deprecated:: Use rnn::RnnParams.layerSizes instead.

◆ timeSteps

std::size_t popnn::gru::GruParams::timeSteps

The number of time steps in the sequence of the GRU.

Deprecated:: Use rnn::RnnParams.maxTimeSteps instead.

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

include/popnn/Gru.hpp