ConstantType< InputType, OutputType > Class Template Reference

Implementation of the constant layer. More...

Inheritance diagram for ConstantType< InputType, OutputType >:

Public Member Functions

 ConstantType ()
 Create an empty Constant layer. More...

 
 ConstantType (const size_t outSize, const double scalar=0)
 Create the Constant object that outputs a given constant scalar value given any input value. More...

 
 ConstantType (const ConstantType &layer)
 Copy another ConstantType. More...

 
 ConstantType (ConstantType &&layer)
 Take ownership of another ConstantType. More...

 
void Backward (const InputType &, const OutputType &, OutputType &g)
 Ordinary feed backward pass of a neural network. More...

 
ConstantTypeClone () const
 Clone the ConstantType object. This handles polymorphism correctly. More...

 
void Forward (const InputType &input, OutputType &output)
 Ordinary feed forward pass of a neural network. More...

 
ConstantTypeoperator= (const ConstantType &layer)
 Copy another ConstantType. More...

 
ConstantTypeoperator= (ConstantType &&layer)
 Take ownership of another ConstantType. More...

 
const std::vector< size_t > & OutputDimensions () const
 Get the output size. More...

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

 
- Public Member Functions inherited from Layer< InputType, OutputType >
 Layer ()
 Default constructor. More...

 
 Layer (const Layer &layer)
 Copy constructor. This is not responsible for copying weights! More...

 
 Layer (Layer &&layer)
 Move constructor. This is not responsible for moving weights! More...

 
virtual ~Layer ()
 Default deconstructor. More...

 
virtual void Backward (const InputType &, const InputType &, InputType &)
 Performs a backpropagation step through the layer, with respect to the given input. More...

 
virtual void ComputeOutputDimensions ()
 Compute the output dimensions. More...

 
virtual void CustomInitialize (InputType &, const size_t)
 Override the weight matrix of the layer. More...

 
virtual void Forward (const InputType &, InputType &)
 Takes an input object, and computes the corresponding output of the layer. More...

 
virtual void Forward (const InputType &, const InputType &)
 Takes an input and output object, and computes the corresponding loss of the layer. More...

 
virtual void Gradient (const InputType &, const InputType &, InputType &)
 Computing the gradient of the layer with respect to its own input. More...

 
const std::vector< size_t > & InputDimensions () const
 Get the input dimensions. More...

 
std::vector< size_t > & InputDimensions ()
 Modify the input dimensions. More...

 
virtual double Loss ()
 Get the layer loss. More...

 
virtual Layeroperator= (const Layer &layer)
 Copy assignment operator. This is not responsible for copying weights! More...

 
virtual Layeroperator= (Layer &&layer)
 Move assignment operator. This is not responsible for moving weights! More...

 
const std::vector< size_t > & OutputDimensions ()
 Get the output dimensions. More...

 
virtual size_t OutputSize () final
 Get the number of elements in the output from this layer. More...

 
virtual const InputType & Parameters () const
 Get the parameters. More...

 
virtual InputType & Parameters ()
 Set the parameters. More...

 
void serialize (Archive &ar, const uint32_t)
 Serialize the layer. More...

 
virtual void SetWeights (typename InputType ::elem_type *)
 Reset the layer parameter. More...

 
virtual bool const & Training () const
 Get whether the layer is currently in training mode. More...

 
virtual bool & Training ()
 Modify whether the layer is currently in training mode. More...

 
virtual size_t WeightSize () const
 Get the total number of trainable weights in the layer. More...

 

Additional Inherited Members

- Protected Attributes inherited from Layer< InputType, OutputType >
std::vector< size_t > inputDimensions
 Logical input dimensions of each point. More...

 
std::vector< size_t > outputDimensions
 Logical output dimensions of each point. More...

 
bool training
 If true, the layer is in training mode; otherwise, it is in testing mode. More...

 
bool validOutputDimensions
 This is true if ComputeOutputDimensions() has been called, and outputDimensions can be considered to be up-to-date. More...

 

Detailed Description


template
<
typename
InputType
=
arma::mat
,
typename
OutputType
=
arma::mat
>

class mlpack::ann::ConstantType< InputType, OutputType >

Implementation of the constant layer.

The constant layer outputs a given constant value given any input value.

Template Parameters
InputTypeThe type of the layer's inputs. The layer automatically cast inputs to this type (Default: arma::mat).
OutputTypeThe type of the computation which also causes the output to also be in this type. The type also allows the computation and weight type to differ from the input type (Default: arma::mat).

Definition at line 34 of file constant.hpp.

Constructor & Destructor Documentation

◆ ConstantType() [1/4]

Create an empty Constant layer.

Referenced by ConstantType< InputType, OutputType >::Clone().

◆ ConstantType() [2/4]

ConstantType ( const size_t  outSize,
const double  scalar = 0 
)

Create the Constant object that outputs a given constant scalar value given any input value.

Parameters
outSizeThe number of output units.
scalarThe constant value used to create the constant output.

◆ ConstantType() [3/4]

ConstantType ( const ConstantType< InputType, OutputType > &  layer)

Copy another ConstantType.

◆ ConstantType() [4/4]

ConstantType ( ConstantType< InputType, OutputType > &&  layer)

Take ownership of another ConstantType.

Member Function Documentation

◆ Backward()

void Backward ( const InputType &  ,
const OutputType &  ,
OutputType &  g 
)

Ordinary feed backward pass of a neural network.

The backward pass of the constant layer is returns always a zero output error matrix.

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

Referenced by ConstantType< InputType, OutputType >::Clone().

◆ Clone()

ConstantType* Clone ( ) const
inlinevirtual

◆ Forward()

void Forward ( const InputType &  input,
OutputType &  output 
)

Ordinary feed forward pass of a neural network.

The forward pass fills the output with the specified constant parameter.

Parameters
inputInput data used for evaluating the specified function.
outputResulting output activation.

Referenced by ConstantType< InputType, OutputType >::Clone().

◆ operator=() [1/2]

ConstantType& operator= ( const ConstantType< InputType, OutputType > &  layer)

Copy another ConstantType.

◆ operator=() [2/2]

ConstantType& operator= ( ConstantType< InputType, OutputType > &&  layer)

Take ownership of another ConstantType.

◆ OutputDimensions()

const std::vector<size_t>& OutputDimensions ( ) const
inline

◆ serialize()

void serialize ( Archive &  ar,
const uint32_t   
)

Serialize the layer.

Referenced by ConstantType< InputType, OutputType >::OutputDimensions().


The documentation for this class was generated from the following file:
  • /home/jenkins-mlpack/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/not_adapted/constant.hpp