mlpack::ann::Glimpse< InputDataType, OutputDataType > Class Template Reference

The glimpse layer returns a retina-like representation (down-scaled cropped images) of increasing scale around a given location in a given image. More...

#include <glimpse.hpp>

Public Member Functions
	Glimpse (const size_t inSize=0, const size_t size=0, const size_t depth=3, const size_t scale=2, const size_t inputWidth=0, const size_t inputHeight=0)
	Create the GlimpseLayer object using the specified ratio and rescale parameter. More...
template<typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of the glimpse layer. More...
template<typename eT >
void	Backward (const arma::Mat< eT > &, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of the glimpse layer. More...
OutputDataType &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
OutputDataType &	Delta () const
	Get the detla.
OutputDataType &	Delta ()
	Modify the delta.
void	Location (const arma::mat &location)
	Set the locationthe x and y coordinate of the center of the output glimpse. More...
size_t const &	InputWidth () const
	Get the input width.
size_t &	InputWidth ()
	Modify input the width.
size_t const &	InputHeight () const
	Get the input height.
size_t &	InputHeight ()
	Modify the input height.
size_t const &	OutputWidth () const
	Get the output width.
size_t &	OutputWidth ()
	Modify the output width.
size_t const &	OutputHeight () const
	Get the output height.
size_t &	OutputHeight ()
	Modify the output height.
bool	Deterministic () const
	Get the value of the deterministic parameter.
bool &	Deterministic ()
	Modify the value of the deterministic parameter.
size_t const &	Depth () const
	Get the number of patches to crop per glimpse.
size_t const &	Scale () const
	Get the scale fraction.
size_t	InSize () const
	Get the size of the input units.
size_t	GlimpseSize () const
	Get the used glimpse size (height = width).
size_t	InputShape () const
	Get the shape of the input.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::Glimpse< InputDataType, OutputDataType >

The glimpse layer returns a retina-like representation (down-scaled cropped images) of increasing scale around a given location in a given image.

Template Parameters

InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Constructor & Destructor Documentation

Glimpse()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::Glimpse< InputDataType, OutputDataType >::Glimpse	(	const size_t	inSize = 0,
		const size_t	size = 0,
		const size_t	depth = 3,
		const size_t	scale = 2,
		const size_t	inputWidth = 0,
		const size_t	inputHeight = 0
	)

Create the GlimpseLayer object using the specified ratio and rescale parameter.

Parameters

inSize	The size of the input units.
size	The used glimpse size (height = width).
depth	The number of patches to crop per glimpse.
scale	The scaling factor used to create the increasing retina-like representation.
inputWidth	The input width of the given input data.
inputHeight	The input height of the given input data.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::Glimpse< InputDataType, OutputDataType >::Backward	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

Ordinary feed backward pass of the glimpse layer.

Parameters

*	(input) The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::Glimpse< InputDataType, OutputDataType >::Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed forward pass of the glimpse layer.

Parameters

input	Input data used for evaluating the specified function.
output	Resulting output activation.

Location()

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

void mlpack::ann::Glimpse< InputDataType, OutputDataType >::Location ( const arma::mat &  location )

inline

Set the locationthe x and y coordinate of the center of the output glimpse.

---

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

• src/mlpack/methods/ann/layer/glimpse.hpp
• src/mlpack/methods/ann/layer/glimpse_impl.hpp