AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType > Class Template Reference

Implementation of the Atrous Convolution class. More...

Public Member Functions

 AtrousConvolution ()
 Create the AtrousConvolution object. More...

 
 AtrousConvolution (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 size_t dilationWidth=1, const size_t dilationHeight=1, const std::string &paddingType="None")
 Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation and padding parameter. More...

 
 AtrousConvolution (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 size_t dilationWidth=1, const size_t dilationHeight=1, const std::string &paddingType="None")
 Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation 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...

 
size_t DilationHeight () const
 Get the dilation rate on the Y axis. More...

 
size_t & DilationHeight ()
 Modify the dilation rate on the Y axis. More...

 
size_t DilationWidth () const
 Get the dilation rate on the X axis. More...

 
size_t & DilationWidth ()
 Modify the dilation rate on the X axis. 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...

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

 
size_t InputSize () const
 Get the input size. 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 output size. More...

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

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

 
ann::Padding const & Padding () const
 Get the internal Padding layer. More...

 
ann::PaddingPadding ()
 Modify the internal Padding layer. 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 the weight matrix. 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::AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >

Implementation of the Atrous Convolution class.

The Atrous Convolution class represents a single layer of a neural network. Atrous (or Dilated) Convolutions are just simple convolutions applied to input with the defined, spaces included between the kernel cells, in order to capture a larger field of reception, without having to increase dicrete kernel sizes.

Template Parameters
ForwardConvolutionRuleAtrous Convolution to perform forward process.
BackwardConvolutionRuleAtrous Convolution to perform backward process.
GradientConvolutionRuleAtrous Convolution to calculate gradient.
InputDataTypeType of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataTypeType of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Definition at line 52 of file atrous_convolution.hpp.

Constructor & Destructor Documentation

◆ AtrousConvolution() [1/3]

Create the AtrousConvolution object.

◆ AtrousConvolution() [2/3]

AtrousConvolution ( 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 size_t  dilationWidth = 1,
const size_t  dilationHeight = 1,
const std::string &  paddingType = "None" 
)

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

Parameters
inSizeThe number of input maps.
outSizeThe number of output maps.
kernelWidthWidth of the filter/kernel.
kernelHeightHeight of the filter/kernel.
strideWidthStride of filter application in the x direction.
strideHeightStride of filter application in the y direction.
padWPadding width of the input.
padHPadding height of the input.
inputWidthThe widht of the input data.
inputHeightThe height of the input data.
dilationWidthThe space between the cells of filters in x direction.
dilationHeightThe space between the cells of filters in y direction.
paddingTypeThe type of padding (Valid or Same). Defaults to None.

◆ AtrousConvolution() [3/3]

AtrousConvolution ( 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 size_t  dilationWidth = 1,
const size_t  dilationHeight = 1,
const std::string &  paddingType = "None" 
)

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

Parameters
inSizeThe number of input maps.
outSizeThe number of output maps.
kernelWidthWidth of the filter/kernel.
kernelHeightHeight of the filter/kernel.
strideWidthStride of filter application in the x direction.
strideHeightStride of filter application in the y direction.
padWA two-value tuple indicating padding widths of the input. First value is padding at left side. Second value is padding on right side.
padHA two-value tuple indicating padding heights of the input. First value is padding at top. Second value is padding on bottom.
inputWidthThe widht of the input data.
inputHeightThe height of the input data.
dilationWidthThe space between the cells of filters in x direction.
dilationHeightThe space between the cells of filters in y direction.
paddingTypeThe type of padding (Valid/Same/None). 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.
gyThe backpropagated error.
gThe calculated gradient.

◆ Bias() [1/2]

arma::mat const& Bias ( ) const
inline

Get the bias of the layer.

Definition at line 180 of file atrous_convolution.hpp.

◆ Bias() [2/2]

arma::mat& Bias ( )
inline

Modify the bias of the layer.

Definition at line 182 of file atrous_convolution.hpp.

◆ Delta() [1/2]

OutputDataType const& Delta ( ) const
inline

Get the delta.

Definition at line 190 of file atrous_convolution.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )
inline

Modify the delta.

Definition at line 192 of file atrous_convolution.hpp.

◆ DilationHeight() [1/2]

size_t DilationHeight ( ) const
inline

Get the dilation rate on the Y axis.

Definition at line 251 of file atrous_convolution.hpp.

◆ DilationHeight() [2/2]

size_t& DilationHeight ( )
inline

Modify the dilation rate on the Y axis.

Definition at line 253 of file atrous_convolution.hpp.

◆ DilationWidth() [1/2]

size_t DilationWidth ( ) const
inline

Get the dilation rate on the X axis.

Definition at line 246 of file atrous_convolution.hpp.

◆ DilationWidth() [2/2]

size_t& DilationWidth ( )
inline

Modify the dilation rate on the X axis.

Definition at line 248 of file atrous_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
inputInput data used for evaluating the specified function.
outputResulting 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 195 of file atrous_convolution.hpp.

◆ Gradient() [3/3]

OutputDataType& Gradient ( )
inline

Modify the gradient.

Definition at line 197 of file atrous_convolution.hpp.

◆ InputHeight() [1/2]

size_t InputHeight ( ) const
inline

Get the input height.

Definition at line 205 of file atrous_convolution.hpp.

◆ InputHeight() [2/2]

size_t& InputHeight ( )
inline

Modify the input height.

Definition at line 207 of file atrous_convolution.hpp.

◆ InputShape()

◆ InputSize()

size_t InputSize ( ) const
inline

Get the input size.

Definition at line 220 of file atrous_convolution.hpp.

◆ InputWidth() [1/2]

size_t InputWidth ( ) const
inline

Get the input width.

Definition at line 200 of file atrous_convolution.hpp.

◆ InputWidth() [2/2]

size_t& InputWidth ( )
inline

Modify input the width.

Definition at line 202 of file atrous_convolution.hpp.

◆ KernelHeight() [1/2]

size_t KernelHeight ( ) const
inline

Get the kernel height.

Definition at line 231 of file atrous_convolution.hpp.

◆ KernelHeight() [2/2]

size_t& KernelHeight ( )
inline

Modify the kernel height.

Definition at line 233 of file atrous_convolution.hpp.

◆ KernelWidth() [1/2]

size_t KernelWidth ( ) const
inline

Get the kernel width.

Definition at line 226 of file atrous_convolution.hpp.

◆ KernelWidth() [2/2]

size_t& KernelWidth ( )
inline

Modify the kernel width.

Definition at line 228 of file atrous_convolution.hpp.

◆ OutputHeight() [1/2]

size_t OutputHeight ( ) const
inline

Get the output height.

Definition at line 215 of file atrous_convolution.hpp.

◆ OutputHeight() [2/2]

size_t& OutputHeight ( )
inline

Modify the output height.

Definition at line 217 of file atrous_convolution.hpp.

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const
inline

Get the output parameter.

Definition at line 185 of file atrous_convolution.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )
inline

Modify the output parameter.

Definition at line 187 of file atrous_convolution.hpp.

◆ OutputSize()

size_t OutputSize ( ) const
inline

Get the output size.

Definition at line 223 of file atrous_convolution.hpp.

◆ OutputWidth() [1/2]

size_t OutputWidth ( ) const
inline

Get the output width.

Definition at line 210 of file atrous_convolution.hpp.

◆ OutputWidth() [2/2]

size_t& OutputWidth ( )
inline

Modify the output width.

Definition at line 212 of file atrous_convolution.hpp.

◆ Padding() [1/2]

ann::Padding const& Padding ( ) const
inline

Get the internal Padding layer.

Definition at line 256 of file atrous_convolution.hpp.

◆ Padding() [2/2]

ann::Padding& Padding ( )
inline

Modify the internal Padding layer.

Definition at line 258 of file atrous_convolution.hpp.

◆ Parameters() [1/2]

OutputDataType const& Parameters ( ) const
inline

Get the parameters.

Definition at line 170 of file atrous_convolution.hpp.

◆ Parameters() [2/2]

OutputDataType& Parameters ( )
inline

Modify the parameters.

Definition at line 172 of file atrous_convolution.hpp.

◆ Reset()

void Reset ( )

◆ serialize()

void serialize ( Archive &  ar,
const uint32_t   
)

◆ StrideHeight() [1/2]

size_t StrideHeight ( ) const
inline

Get the stride height.

Definition at line 241 of file atrous_convolution.hpp.

◆ StrideHeight() [2/2]

size_t& StrideHeight ( )
inline

Modify the stride height.

Definition at line 243 of file atrous_convolution.hpp.

◆ StrideWidth() [1/2]

size_t StrideWidth ( ) const
inline

Get the stride width.

Definition at line 236 of file atrous_convolution.hpp.

◆ StrideWidth() [2/2]

size_t& StrideWidth ( )
inline

Modify the stride width.

Definition at line 238 of file atrous_convolution.hpp.

◆ Weight() [1/2]

arma::cube const& Weight ( ) const
inline

Get the weight of the layer.

Definition at line 175 of file atrous_convolution.hpp.

◆ Weight() [2/2]

arma::cube& Weight ( )
inline

Modify the weight of the layer.

Definition at line 177 of file atrous_convolution.hpp.

◆ WeightSize()

size_t WeightSize ( ) const
inline

Get size of the weight matrix.

Definition at line 261 of file atrous_convolution.hpp.


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