Mila::Dnn::EncoderConfig Class Reference

Configuration class for Encoder module. More...

Inheritance diagram for Mila::Dnn::EncoderConfig:

Collaboration diagram for Mila::Dnn::EncoderConfig:

Public Member Functions
	EncoderConfig ()=default
	Default constructor.
size_t	getChannels () const
	Get the configured embedding dimension.
size_t	getMaxSequenceLength () const
	Get the configured maximum sequence length.
size_t	getVocabularyLength () const
	Get the configured vocabulary length.
void	validate () const
	Validate configuration parameters.
EncoderConfig &	withChannels (size_t channels)
	Set the embedding dimension.
EncoderConfig &	withMaxSequenceLength (size_t max_seq_len)
	Set the maximum sequence length.
EncoderConfig &	withVocabularyLength (size_t vocab_len)
	Set the vocabulary length.
Public Member Functions inherited from Mila::Dnn::ComponentConfig
virtual	~ComponentConfig ()=default
	Virtual destructor to support proper polymorphic destruction.
const std::string &	getName () const
	Gets the configured component name.
ComputePrecision::Policy	getPrecision () const
	Gets the configured precision policy.
bool	isTraining () const
	Gets the configured training mode.
template<typename Self >
auto &	withName (this Self &&self, std::string name)
	Sets the name of the component with fluent interface.
template<typename Self >
auto &	withPrecision (this Self &&self, ComputePrecision::Policy policy)
	Sets the compute precision policy with fluent interface.
template<typename Self >
auto &	withTraining (this Self &&self, bool is_training)
	Sets the training mode with fluent interface.

Private Attributes
size_t	channels_ = 0
	The embedding dimension size.
size_t	max_seq_len_ = 512
	The maximum sequence length.
size_t	vocab_len_ = 50000
	The vocabulary size.

Additional Inherited Members
Protected Attributes inherited from Mila::Dnn::ComponentConfig
bool	is_training_ = false
	Training mode flag, defaults to false (inference mode)
std::string	name_ = "unnamed"
	Component name, defaults to "unnamed" if not explicitly set.
ComputePrecision::Policy	precision_ = ComputePrecision::Policy::Auto
	Precision policy for computation, defaults to Auto.

Detailed Description

Configuration class for Encoder module.

Provides a type-safe fluent interface for configuring Encoder modules.

Constructor & Destructor Documentation

EncoderConfig()

Mila::Dnn::EncoderConfig::EncoderConfig ( )

default

Default constructor.

Member Function Documentation

getChannels()

size_t Mila::Dnn::EncoderConfig::getChannels ( ) const

inline

Get the configured embedding dimension.

Returns

size_t The embedding dimension

getMaxSequenceLength()

size_t Mila::Dnn::EncoderConfig::getMaxSequenceLength ( ) const

inline

Get the configured maximum sequence length.

Returns

size_t The maximum sequence length

getVocabularyLength()

size_t Mila::Dnn::EncoderConfig::getVocabularyLength ( ) const

inline

Get the configured vocabulary length.

Returns

size_t The vocabulary length

validate()

void Mila::Dnn::EncoderConfig::validate ( ) const

inlinevirtual

Validate configuration parameters.

Exceptions

std::invalid_argument

If validation fails

Reimplemented from Mila::Dnn::ComponentConfig.

Here is the call graph for this function:

withChannels()

EncoderConfig & Mila::Dnn::EncoderConfig::withChannels ( size_t  channels )

inline

Set the embedding dimension.

Parameters

channels

The embedding dimension size

Returns

EncoderConfig& Reference to this for method chaining

withMaxSequenceLength()

EncoderConfig & Mila::Dnn::EncoderConfig::withMaxSequenceLength ( size_t  max_seq_len )

inline

Set the maximum sequence length.

Parameters

max_seq_len

Maximum sequence length

Returns

EncoderConfig& Reference to this for method chaining

withVocabularyLength()

EncoderConfig & Mila::Dnn::EncoderConfig::withVocabularyLength ( size_t  vocab_len )

inline

Set the vocabulary length.

Parameters

vocab_len

Size of the vocabulary

Returns

EncoderConfig& Reference to this for method chaining

Member Data Documentation

channels_

size_t Mila::Dnn::EncoderConfig::channels_ = 0

private

The embedding dimension size.

max_seq_len_

size_t Mila::Dnn::EncoderConfig::max_seq_len_ = 512

private

The maximum sequence length.

vocab_len_

size_t Mila::Dnn::EncoderConfig::vocab_len_ = 50000

private

The vocabulary size.

---

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

• /home/runner/work/Mila/Mila/Mila/Src/Dnn/Modules/Layers/EncoderConfig.ixx