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

Implementation of the PixelShuffle layer. More...

#include <pixel_shuffle.hpp>

Public Member Functions
	PixelShuffle ()
	Create the PixelShuffle object.
	PixelShuffle (const size_t upscaleFactor, const size_t height, const size_t width, const size_t size)
	Create the PixelShuffle object using the specified parameters. More...
template<typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of the PixelShuffle layer. More...
template<typename eT >
void	Backward (const arma::Mat< eT > &input, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of the PixelShuffle layer. More...
OutputDataType const &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
OutputDataType const &	Delta () const
	Get the delta.
OutputDataType &	Delta ()
	Modify the delta.
size_t	UpscaleFactor () const
	Get the upscale factor.
size_t &	UpscaleFactor ()
	Modify the upscale factor.
size_t	InputHeight () const
	Get the input image height.
size_t &	InputHeight ()
	Modify the input image height.
size_t	InputWidth () const
	Get the input image width.
size_t &	InputWidth ()
	Modify the input image width.
size_t	InputChannels () const
	Get the number of input channels.
size_t &	InputChannels ()
	Modify the number of input channels.
size_t	OutputHeight () const
	Get the output image height.
size_t	OutputWidth () const
	Get the output image width.
size_t	OutputChannels () const
	Get the number of output channels.
template<typename Archive >
void	serialize (Archive &ar, const unsigned int)
	Serialize the layer.

Detailed Description

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

Implementation of the PixelShuffle layer.

For more information, refer to the following paper,

@article{Shi16,
  author    = {Wenzhe Shi, Jose Caballero,Ferenc Huszár, Johannes Totz,
              Andrew P. Aitken, Rob Bishop, Daniel Rueckert, Zehan Wang},
  title     = {Real-Time Single Image and Video Super-Resolution Using an
              Efficient Sub-Pixel Convolutional Neural Network},
  journal   = {CoRR},
  volume    = {abs/1609.05158},
  year      = {2016},
  url       = {https://arxiv.org/abs/1609.05158},
  eprint    = {1609.05158},
}

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

PixelShuffle()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::PixelShuffle< InputDataType, OutputDataType >::PixelShuffle	(	const size_t	upscaleFactor,
		const size_t	height,
		const size_t	width,
		const size_t	size
	)

Create the PixelShuffle object using the specified parameters.

The number of input channels should be an integral multiple of the square of the upscale factor.

Parameters

upscaleFactor	The scaling factor for Pixel Shuffle.
height	The height of each input image.
width	The width of each input image.
size	The number of channels of each input image.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename eT >

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

Ordinary feed backward pass of the PixelShuffle 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::PixelShuffle< InputDataType, OutputDataType >::Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed forward pass of the PixelShuffle layer.

Parameters

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

---

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

• src/mlpack/methods/ann/layer/pixel_shuffle.hpp
• src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp