Static implementation of a fully-connected (dense) layer, with no activation. More...

Public Member Functions
	DenseT ()

std::string	getName () const noexcept
	Returns the name of this layer. More...

constexpr bool	isActivation () const noexcept
	Returns false since dense is not an activation layer. More...

RTNEURAL_REALTIME void	reset ()
	Reset is a no-op, since Dense does not have state. More...

RTNEURAL_REALTIME void	forward (const T(&ins)[in_size]) noexcept
	Performs forward propagation for this layer. More...

RTNEURAL_REALTIME void	setWeights (const std::vector< std::vector< T >> &newWeights)
	Sets the layer weights from a given vector. More...

RTNEURAL_REALTIME void	setWeights (T **newWeights)
	Sets the layer weights from a given vector. More...

RTNEURAL_REALTIME void	setBias (const T *b)
	Sets the layer bias from a given array of size bias[out_size]. 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>
class RTNEURAL_NAMESPACE::DenseT< T, in_sizet, out_sizet >

Static implementation of a fully-connected (dense) layer, with no activation.

Constructor & Destructor Documentation

◆ DenseT()

DenseT ( )

References DenseT< T, in_sizet, out_sizet >::out_size, and DenseT< T, in_sizet, out_sizet >::outs.

Member Function Documentation

◆ getName()

std::string getName ( ) const

noexcept

Returns the name of this layer.

◆ isActivation()

constexpr bool isActivation ( ) const

constexprnoexcept

Returns false since dense is not an activation layer.

◆ reset()

RTNEURAL_REALTIME void reset ( )

Reset is a no-op, since Dense does not have state.

◆ forward()

RTNEURAL_REALTIME void forward ( const T(&) ins[in_size] )

noexcept

Performs forward propagation for this layer.

References DenseT< T, in_sizet, out_sizet >::in_size, DenseT< T, in_sizet, out_sizet >::out_size, and DenseT< T, in_sizet, out_sizet >::outs.

◆ setWeights() [1/2]

RTNEURAL_REALTIME void setWeights ( const std::vector< std::vector< T >> & newWeights )

Sets the layer weights from a given vector.

The dimension of the weights vector must be weights[out_size][in_size]

References DenseT< T, in_sizet, out_sizet >::in_size, and DenseT< T, in_sizet, out_sizet >::out_size.

◆ setWeights() [2/2]

RTNEURAL_REALTIME void setWeights ( T ** newWeights )

Sets the layer weights from a given vector.

The dimension of the weights array must be weights[out_size][in_size]

References DenseT< T, in_sizet, out_sizet >::in_size, and DenseT< T, in_sizet, out_sizet >::out_size.

◆ setBias()

RTNEURAL_REALTIME void setBias ( const T * b )

Sets the layer bias from a given array of size bias[out_size].

References DenseT< T, in_sizet, out_sizet >::out_size.

Member Data Documentation

◆ in_size

constexpr auto in_size = in_sizet

staticconstexpr

Referenced by DenseT< T, in_sizet, out_sizet >::forward(), and DenseT< T, in_sizet, out_sizet >::setWeights().

◆ out_size

constexpr auto out_size = out_sizet

staticconstexpr

Referenced by DenseT< T, in_sizet, out_sizet >::DenseT(), DenseT< T, in_sizet, out_sizet >::forward(), DenseT< T, in_sizet, out_sizet >::setBias(), and DenseT< T, in_sizet, out_sizet >::setWeights().

◆ outs

T outs[out_size]

Referenced by DenseT< T, in_sizet, out_sizet >::DenseT(), and DenseT< T, in_sizet, out_sizet >::forward().

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

dense.h

Public Member Functions

Public Attributes

Static Public Attributes