LookupType< InputType, OutputType > Class Template Reference

The Lookup class stores word embeddings and retrieves them using tokens. More...

Inheritance diagram for LookupType< InputType, OutputType >:

Public Member Functions

 LookupType (const size_t vocabSize=0, const size_t embeddingSize=0)
 Create the Lookup object using the specified vocabulary and embedding size. More...

 
void Backward (const InputType &, const OutputType &gy, OutputType &g)
 Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. More...

 
LookupTypeClone () const
 Clone the LookupType object. This handles polymorphism correctly. More...

 
size_t EmbeddingSize () const
 Get the length of each embedding vector. More...

 
void Forward (const InputType &input, OutputType &output)
 Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

 
void Gradient (const InputType &input, const OutputType &error, OutputType &gradient)
 Calculate the gradient using the output delta and the input activation. More...

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

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

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

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

 
size_t VocabSize () const
 Get the size of the vocabulary. More...

 
const size_t WeightSize () const
 Get the number of trainable parameters. 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...

 
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...

 

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::LookupType< InputType, OutputType >

The Lookup class stores word embeddings and retrieves them using tokens.

The Lookup layer is always the first layer of the network. The input to the Lookup class is a matrix of shape (sequenceLength, batchSize). The matrix consists of tokens which are used to lookup the table (i.e. weights) to find the embeddings of those tokens.

The input shape : (sequenceLength, batchSize). The output shape : (embeddingSize, sequenceLength, batchSize).

Template Parameters
InputTypeType of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputTypeType of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Definition at line 41 of file lookup.hpp.

Constructor & Destructor Documentation

◆ LookupType()

LookupType ( const size_t  vocabSize = 0,
const size_t  embeddingSize = 0 
)

Create the Lookup object using the specified vocabulary and embedding size.

Parameters
vocabSizeThe size of the vocabulary.
embeddingSizeThe length of each embedding vector.

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

Member Function Documentation

◆ Backward()

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

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

Using the results from the feed forward pass.

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

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

◆ Clone()

◆ EmbeddingSize()

size_t EmbeddingSize ( ) const
inline

Get the length of each embedding vector.

Definition at line 97 of file lookup.hpp.

◆ Forward()

void Forward ( const InputType &  input,
OutputType &  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.

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

◆ Gradient()

void Gradient ( const InputType &  input,
const OutputType &  error,
OutputType &  gradient 
)

Calculate the gradient using the output delta and the input activation.

Parameters
inputThe input parameter used for calculating the gradient.
errorThe calculated error.
gradientThe calculated gradient.

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

◆ OutputDimensions()

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

Get the dimensions of the output.

This layer adds an extra dimension for the embedding.

Definition at line 104 of file lookup.hpp.

References Layer< InputType, OutputType >::inputDimensions, and LookupType< InputType, OutputType >::serialize().

◆ Parameters() [1/2]

OutputType const& Parameters ( ) const
inlinevirtual

Get the parameters.

Reimplemented from Layer< InputType, OutputType >.

Definition at line 89 of file lookup.hpp.

◆ Parameters() [2/2]

OutputType& Parameters ( )
inlinevirtual

Modify the parameters.

Reimplemented from Layer< InputType, OutputType >.

Definition at line 91 of file lookup.hpp.

◆ serialize()

void serialize ( Archive &  ar,
const uint32_t   
)

Serialize the layer.

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

◆ VocabSize()

size_t VocabSize ( ) const
inline

Get the size of the vocabulary.

Definition at line 94 of file lookup.hpp.

◆ WeightSize()

const size_t WeightSize ( ) const
inlinevirtual

Get the number of trainable parameters.

Reimplemented from Layer< InputType, OutputType >.

Definition at line 100 of file lookup.hpp.


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/lookup.hpp