GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider > Class Template Reference

Static implementation of a gated recurrent unit (GRU) layer with tanh activation and sigmoid recurrent activation. More...

Public Member Functions
	GRULayerT ()
std::string	getName () const noexcept
	Returns the name of this layer. More...
constexpr bool	isActivation () const noexcept
	Returns false since GRU is not an activation layer. More...
template<SampleRateCorrectionMode srCorr = sampleRateCorr>
std::enable_if_t< srCorr==SampleRateCorrectionMode::NoInterp, void >	prepare (int delaySamples)
	Prepares the GRU to process with a given delay length. More...
template<SampleRateCorrectionMode srCorr = sampleRateCorr>
std::enable_if_t< srCorr==SampleRateCorrectionMode::LinInterp, void >	prepare (T delaySamples)
	Prepares the GRU to process with a given delay length. More...
RTNEURAL_REALTIME void	reset ()
	Resets the state of the GRU. More...
template<int N = in_size>
RTNEURAL_REALTIME std::enable_if<(N > 1), void >::type	forward (const T(&ins)[in_size]) noexcept
	Performs forward propagation for this layer. More...
template<int N = in_size>
RTNEURAL_REALTIME std::enable_if< N==1, void >::type	forward (const T(&ins)[in_size]) noexcept
	Performs forward propagation for this layer. More...
RTNEURAL_REALTIME void	setWVals (const std::vector< std::vector< T >> &wVals)
	Sets the layer kernel weights. More...
RTNEURAL_REALTIME void	setUVals (const std::vector< std::vector< T >> &uVals)
	Sets the layer recurrent weights. More...
RTNEURAL_REALTIME void	setBVals (const std::vector< std::vector< T >> &bVals)
	Sets the layer bias. More...

Public Attributes
T	outs [out_size]

Static Public Attributes
static constexpr auto	in_size = in_sizet
static constexpr auto	out_size = out_sizet

Detailed Description

template<typename T, int in_sizet, int out_sizet, SampleRateCorrectionMode sampleRateCorr = SampleRateCorrectionMode::None, typename MathsProvider = DefaultMathsProvider>
class RTNEURAL_NAMESPACE::GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >

Static implementation of a gated recurrent unit (GRU) layer with tanh activation and sigmoid recurrent activation.

To ensure that the recurrent state is initialized to zero, please make sure to call reset() before your first call to the forward() method.

Compared to TensorFlow's GRU implementation, this layer will behave by default as if the parameter stateful=True. A "stateless" GRU can be achieved by calling the reset() function in between calls to forward().

Constructor & Destructor Documentation

GRULayerT()

GRULayerT

(

)

Member Function Documentation

getName()

std::string getName ( ) const

noexcept

Returns the name of this layer.

isActivation()

constexpr bool isActivation ( ) const

constexprnoexcept

Returns false since GRU is not an activation layer.

prepare() [1/2]

std::enable_if_t<srCorr == SampleRateCorrectionMode::NoInterp, void> prepare

(

int

delaySamples

)

Prepares the GRU to process with a given delay length.

prepare() [2/2]

std::enable_if_t<srCorr == SampleRateCorrectionMode::LinInterp, void> prepare

(

T

delaySamples

)

Prepares the GRU to process with a given delay length.

reset()

RTNEURAL_REALTIME void reset

(

)

Resets the state of the GRU.

forward() [1/2]

RTNEURAL_REALTIME std::enable_if<(N > 1), void>::type forward ( const T(&)  ins[in_size] )

noexcept

Performs forward propagation for this layer.

References GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >::out_size, and GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >::outs.

forward() [2/2]

RTNEURAL_REALTIME std::enable_if<N == 1, void>::type forward ( const T(&)  ins[in_size] )

noexcept

Performs forward propagation for this layer.

References GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >::out_size, and GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >::outs.

setWVals()

RTNEURAL_REALTIME void setWVals

(

const std::vector< std::vector< T >> &

wVals

)

Sets the layer kernel weights.

The weights vector must have size weights[in_size][3 * out_size]

setUVals()

RTNEURAL_REALTIME void setUVals

(

const std::vector< std::vector< T >> &

uVals

)

Sets the layer recurrent weights.

The weights vector must have size weights[out_size][3 * out_size]

setBVals()

RTNEURAL_REALTIME void setBVals

(

const std::vector< std::vector< T >> &

bVals

)

Sets the layer bias.

The bias vector must have size weights[2][3 * out_size]

Member Data Documentation

in_size

constexpr auto in_size = in_sizet

staticconstexpr

out_size

constexpr auto out_size = out_sizet

staticconstexpr

Referenced by GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >::forward().

outs

T outs[out_size]

Referenced by GRULayerT< T, in_sizet, out_sizet, sampleRateCorr, MathsProvider >::forward().

---

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

• gru.h