Implementation of the Convolution class. More...

Public Member Functions
	Convolution ()
	Create the Convolution object. More...

	Convolution (const size_t inSize, const size_t outSize, const size_t kernelWidth, const size_t kernelHeight, const size_t strideWidth=1, const size_t strideHeight=1, const size_t padW=0, const size_t padH=0, const size_t inputWidth=0, const size_t inputHeight=0, const std::string &paddingType="None")
	Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter. More...

	Convolution (const size_t inSize, const size_t outSize, const size_t kernelWidth, const size_t kernelHeight, const size_t strideWidth, const size_t strideHeight, const std::tuple< size_t, size_t > &padW, const std::tuple< size_t, size_t > &padH, const size_t inputWidth=0, const size_t inputHeight=0, const std::string &paddingType="None")
	Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter. More...

template < typename eT >
void	Backward (const arma::Mat< eT > &, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...

arma::mat const &	Bias () const
	Get the bias of the layer. More...

arma::mat &	Bias ()
	Modify the bias of the layer. More...

OutputDataType const &	Delta () const
	Get the delta. More...

OutputDataType &	Delta ()
	Modify the delta. More...

template < typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

template < typename eT >
void	Gradient (const arma::Mat< eT > &, const arma::Mat< eT > &error, arma::Mat< eT > &gradient)

OutputDataType const &	Gradient () const
	Get the gradient. More...

OutputDataType &	Gradient ()
	Modify the gradient. More...

size_t	InputHeight () const
	Get the input height. More...

size_t &	InputHeight ()
	Modify the input height. More...

InputDataType const &	InputParameter () const
	Get the input parameter. More...

InputDataType &	InputParameter ()
	Modify the input parameter. More...

size_t	InputShape () const
	Get the shape of the input. More...

size_t	InputSize () const
	Get the number of input maps. More...

size_t	InputWidth () const
	Get the input width. More...

size_t &	InputWidth ()
	Modify input the width. More...

size_t	KernelHeight () const
	Get the kernel height. More...

size_t &	KernelHeight ()
	Modify the kernel height. More...

size_t	KernelWidth () const
	Get the kernel width. More...

size_t &	KernelWidth ()
	Modify the kernel width. More...

size_t	OutputHeight () const
	Get the output height. More...

size_t &	OutputHeight ()
	Modify the output height. More...

OutputDataType const &	OutputParameter () const
	Get the output parameter. More...

OutputDataType &	OutputParameter ()
	Modify the output parameter. More...

size_t	OutputSize () const
	Get the number of output maps. More...

size_t	OutputWidth () const
	Get the output width. More...

size_t &	OutputWidth ()
	Modify the output width. More...

size_t	PadHBottom () const
	Get the bottom padding height. More...

size_t &	PadHBottom ()
	Modify the bottom padding height. More...

size_t	PadHTop () const
	Get the top padding height. More...

size_t &	PadHTop ()
	Modify the top padding height. More...

size_t	PadWLeft () const
	Get the left padding width. More...

size_t &	PadWLeft ()
	Modify the left padding width. More...

size_t	PadWRight () const
	Get the right padding width. More...

size_t &	PadWRight ()
	Modify the right padding width. More...

OutputDataType const &	Parameters () const
	Get the parameters. More...

OutputDataType &	Parameters ()
	Modify the parameters. More...

void	Reset ()

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer. More...

size_t	StrideHeight () const
	Get the stride height. More...

size_t &	StrideHeight ()
	Modify the stride height. More...

size_t	StrideWidth () const
	Get the stride width. More...

size_t &	StrideWidth ()
	Modify the stride width. More...

arma::cube const &	Weight () const
	Get the weight of the layer. More...

arma::cube &	Weight ()
	Modify the weight of the layer. More...

size_t	WeightSize () const
	Get size of weights for the layer. More...

Detailed Description

template<typename ForwardConvolutionRule = NaiveConvolution<ValidConvolution>, typename BackwardConvolutionRule = NaiveConvolution<FullConvolution>, typename GradientConvolutionRule = NaiveConvolution<ValidConvolution>, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >

Implementation of the Convolution class.

The Convolution class represents a single layer of a neural network. Example usage:

Suppose we want to pass a matrix M (2744x100) to a Convolution layer; in this example, M was obtained from "flattening" 100 images (or Mel cepstral coefficients, if we talk about speech, or whatever you like) of dimension 196x14. In other words, the first 196 columns of each row of M will be made of the 196 columns of the first row of each of the 100 images (or Mel cepstral coefficients). Then the next 295 columns of M (196 - 393) will be made of the 196 columns of the second row of the 100 images (or Mel cepstral coefficients), etc. Given that the size of our 2-D input images is 196x14, the parameters for our Convolution layer will be something like this:

Convolution<> c(1, // Number of input activation maps.
                14, // Number of output activation maps.
                3, // Filter width.
                3, // Filter height.
                1, // Stride along width.
                1, // Stride along height.
                0, // Padding width.
                0, // Padding height.
                196, // Input width.
                14); // Input height.

This Convolution<> layer will treat each column of the input matrix M as a 2-D image (or object) of the original 196x14 size, using this as the input for the 14 filters of this example.

Template Parameters

ForwardConvolutionRule	Convolution to perform forward process.
BackwardConvolutionRule	Convolution to perform backward process.
GradientConvolutionRule	Convolution to calculate gradient.
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).

Definition at line 77 of file convolution.hpp.

Constructor & Destructor Documentation

◆ Convolution() [1/3]

Convolution ( )

Create the Convolution object.

◆ Convolution() [2/3]

Convolution	(	const size_t	inSize,
		const size_t	outSize,
		const size_t	kernelWidth,
		const size_t	kernelHeight,
		const size_t	strideWidth = `1`,
		const size_t	strideHeight = `1`,
		const size_t	padW = `0`,
		const size_t	padH = `0`,
		const size_t	inputWidth = `0`,
		const size_t	inputHeight = `0`,
		const std::string &	paddingType = `"None"`
	)

Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter.

Parameters

inSize	The number of input maps.
outSize	The number of output maps.
kernelWidth	Width of the filter/kernel.
kernelHeight	Height of the filter/kernel.
strideWidth	Stride of filter application in the x direction.
strideHeight	Stride of filter application in the y direction.
padW	Padding width of the input.
padH	Padding height of the input.
inputWidth	The width of the input data.
inputHeight	The height of the input data.
paddingType	The type of padding (Valid or Same). Defaults to None.

◆ Convolution() [3/3]

Convolution	(	const size_t	inSize,
		const size_t	outSize,
		const size_t	kernelWidth,
		const size_t	kernelHeight,
		const size_t	strideWidth,
		const size_t	strideHeight,
		const std::tuple< size_t, size_t > &	padW,
		const std::tuple< size_t, size_t > &	padH,
		const size_t	inputWidth = `0`,
		const size_t	inputHeight = `0`,
		const std::string &	paddingType = `"None"`
	)

Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter.

Parameters

inSize	The number of input maps.
outSize	The number of output maps.
kernelWidth	Width of the filter/kernel.
kernelHeight	Height of the filter/kernel.
strideWidth	Stride of filter application in the x direction.
strideHeight	Stride of filter application in the y direction.
padW	A two-value tuple indicating padding widths of the input. First value is padding at left side. Second value is padding on right side.
padH	A two-value tuple indicating padding heights of the input. First value is padding at top. Second value is padding on bottom.
inputWidth	The width of the input data.
inputHeight	The height of the input data.
paddingType	The type of padding (Valid or Same). Defaults to None.

Member Function Documentation

◆ Backward()

void Backward	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f.

Using the results from the feed forward pass.

Parameters

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

◆ Bias() [1/2]

arma::mat const& Bias ( ) const

inline

Get the bias of the layer.

Definition at line 195 of file convolution.hpp.

◆ Bias() [2/2]

arma::mat& Bias ( )

inline

Modify the bias of the layer.

Definition at line 197 of file convolution.hpp.

◆ Delta() [1/2]

OutputDataType const& Delta ( ) const

inline

Get the delta.

Definition at line 210 of file convolution.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 212 of file convolution.hpp.

◆ Forward()

void Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters

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

◆ Gradient() [1/3]

void Gradient	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	error,
		arma::Mat< eT > &	gradient
	)

◆ Gradient() [2/3]

OutputDataType const& Gradient ( ) const

inline

Get the gradient.

Definition at line 215 of file convolution.hpp.

◆ Gradient() [3/3]

OutputDataType& Gradient ( )

inline

Modify the gradient.

Definition at line 217 of file convolution.hpp.

◆ InputHeight() [1/2]

size_t InputHeight ( ) const

inline

Get the input height.

Definition at line 225 of file convolution.hpp.

◆ InputHeight() [2/2]

size_t& InputHeight ( )

inline

Modify the input height.

Definition at line 227 of file convolution.hpp.

◆ InputParameter() [1/2]

InputDataType const& InputParameter ( ) const

inline

Get the input parameter.

Definition at line 200 of file convolution.hpp.

◆ InputParameter() [2/2]

InputDataType& InputParameter ( )

inline

Modify the input parameter.

Definition at line 202 of file convolution.hpp.

◆ InputShape()

size_t InputShape ( ) const

inline

Get the shape of the input.

Definition at line 292 of file convolution.hpp.

References Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::serialize().

◆ InputSize()

size_t InputSize ( ) const

inline

Get the number of input maps.

Definition at line 240 of file convolution.hpp.

◆ InputWidth() [1/2]

size_t InputWidth ( ) const

inline

Get the input width.

Definition at line 220 of file convolution.hpp.

◆ InputWidth() [2/2]

size_t& InputWidth ( )

inline

Modify input the width.

Definition at line 222 of file convolution.hpp.

◆ KernelHeight() [1/2]

size_t KernelHeight ( ) const

inline

Get the kernel height.

Definition at line 251 of file convolution.hpp.

◆ KernelHeight() [2/2]

size_t& KernelHeight ( )

inline

Modify the kernel height.

Definition at line 253 of file convolution.hpp.

◆ KernelWidth() [1/2]

size_t KernelWidth ( ) const

inline

Get the kernel width.

Definition at line 246 of file convolution.hpp.

◆ KernelWidth() [2/2]

size_t& KernelWidth ( )

inline

Modify the kernel width.

Definition at line 248 of file convolution.hpp.

◆ OutputHeight() [1/2]

size_t OutputHeight ( ) const

inline

Get the output height.

Definition at line 235 of file convolution.hpp.

◆ OutputHeight() [2/2]

size_t& OutputHeight ( )

inline

Modify the output height.

Definition at line 237 of file convolution.hpp.

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 205 of file convolution.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 207 of file convolution.hpp.

◆ OutputSize()

size_t OutputSize ( ) const

inline

Get the number of output maps.

Definition at line 243 of file convolution.hpp.

◆ OutputWidth() [1/2]

size_t OutputWidth ( ) const

inline

Get the output width.

Definition at line 230 of file convolution.hpp.

◆ OutputWidth() [2/2]

size_t& OutputWidth ( )

inline

Modify the output width.

Definition at line 232 of file convolution.hpp.

◆ PadHBottom() [1/2]

size_t PadHBottom ( ) const

inline

Get the bottom padding height.

Definition at line 271 of file convolution.hpp.

◆ PadHBottom() [2/2]

size_t& PadHBottom ( )

inline

Modify the bottom padding height.

Definition at line 273 of file convolution.hpp.

◆ PadHTop() [1/2]

size_t PadHTop ( ) const

inline

Get the top padding height.

Definition at line 266 of file convolution.hpp.

◆ PadHTop() [2/2]

size_t& PadHTop ( )

inline

Modify the top padding height.

Definition at line 268 of file convolution.hpp.

◆ PadWLeft() [1/2]

size_t PadWLeft ( ) const

inline

Get the left padding width.

Definition at line 276 of file convolution.hpp.

◆ PadWLeft() [2/2]

size_t& PadWLeft ( )

inline

Modify the left padding width.

Definition at line 278 of file convolution.hpp.

◆ PadWRight() [1/2]

size_t PadWRight ( ) const

inline

Get the right padding width.

Definition at line 281 of file convolution.hpp.

◆ PadWRight() [2/2]

size_t& PadWRight ( )

inline

Modify the right padding width.

Definition at line 283 of file convolution.hpp.

◆ Parameters() [1/2]

OutputDataType const& Parameters ( ) const

inline

Get the parameters.

Definition at line 185 of file convolution.hpp.

◆ Parameters() [2/2]

OutputDataType& Parameters ( )

inline

Modify the parameters.

Definition at line 187 of file convolution.hpp.

◆ Reset()

void Reset ( )

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputShape().

◆ StrideHeight() [1/2]

size_t StrideHeight ( ) const

inline

Get the stride height.

Definition at line 261 of file convolution.hpp.

◆ StrideHeight() [2/2]

size_t& StrideHeight ( )

inline

Modify the stride height.

Definition at line 263 of file convolution.hpp.

◆ StrideWidth() [1/2]

size_t StrideWidth ( ) const

inline

Get the stride width.

Definition at line 256 of file convolution.hpp.

◆ StrideWidth() [2/2]

size_t& StrideWidth ( )

inline

Modify the stride width.

Definition at line 258 of file convolution.hpp.

◆ Weight() [1/2]

arma::cube const& Weight ( ) const

inline

Get the weight of the layer.

Definition at line 190 of file convolution.hpp.

◆ Weight() [2/2]

arma::cube& Weight ( )

inline

Modify the weight of the layer.

Definition at line 192 of file convolution.hpp.

◆ WeightSize()

size_t WeightSize ( ) const

inline

Get size of weights for the layer.

Definition at line 286 of file convolution.hpp.

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

/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/convolution.hpp

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ Convolution() [1/3]

◆ Convolution() [2/3]

◆ Convolution() [3/3]

Member Function Documentation

◆ Backward()

◆ Bias() [1/2]

◆ Bias() [2/2]

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Forward()

◆ Gradient() [1/3]

◆ Gradient() [2/3]

◆ Gradient() [3/3]

◆ InputHeight() [1/2]

◆ InputHeight() [2/2]

◆ InputParameter() [1/2]

◆ InputParameter() [2/2]

◆ InputShape()

◆ InputSize()

◆ InputWidth() [1/2]

◆ InputWidth() [2/2]

◆ KernelHeight() [1/2]

◆ KernelHeight() [2/2]

◆ KernelWidth() [1/2]

◆ KernelWidth() [2/2]

◆ OutputHeight() [1/2]

◆ OutputHeight() [2/2]

◆ OutputParameter() [1/2]

◆ OutputParameter() [2/2]

◆ OutputSize()

◆ OutputWidth() [1/2]

◆ OutputWidth() [2/2]

◆ PadHBottom() [1/2]

◆ PadHBottom() [2/2]

◆ PadHTop() [1/2]

◆ PadHTop() [2/2]

◆ PadWLeft() [1/2]

◆ PadWLeft() [2/2]

◆ PadWRight() [1/2]

◆ PadWRight() [2/2]

◆ Parameters() [1/2]

◆ Parameters() [2/2]

◆ Reset()

◆ serialize()

◆ StrideHeight() [1/2]

◆ StrideHeight() [2/2]

◆ StrideWidth() [1/2]

◆ StrideWidth() [2/2]

◆ Weight() [1/2]

◆ Weight() [2/2]

◆ WeightSize()