iganet::LayerNorm Class Reference

Layer Normalization as described in the paper. More...

#include </home/runner/work/iganet/iganet/include/layer.hpp>

Inheritance diagram for iganet::LayerNorm:

Public Member Functions
	LayerNorm (std::vector< int64_t > normalized_shape)
	LayerNorm (std::vector< int64_t > normalized_shape, const torch::Tensor &weight, const torch::Tensor &bias, double eps)
	LayerNorm (torch::nn::functional::LayerNormFuncOptions options)
	~LayerNorm () override=default
torch::Tensor	apply (const torch::Tensor &input) const override
	Applies the activation function to the given input.
torch::nn::functional::LayerNormFuncOptions &	options ()
	Returns non-constant reference to options.
const torch::nn::functional::LayerNormFuncOptions &	options () const
	Returns constant reference to options.
virtual void	pretty_print (std::ostream &os=Log(log::info)) const noexcept override
	Returns a string representation of the activation function.
torch::serialize::InputArchive &	read (torch::serialize::InputArchive &archive, const std::string &key="layer_norm") override
	Reads the activation function from a torch::serialize::InputArchive object.
torch::serialize::OutputArchive &	write (torch::serialize::OutputArchive &archive, const std::string &key="layer_norm") const override
	Writes the activation function into a torch::serialize::OutputArchive object.
Public Member Functions inherited from iganet::ActivationFunction
virtual	~ActivationFunction ()=default

Private Attributes
torch::nn::functional::LayerNormFuncOptions	options_

Additional Inherited Members
Protected Member Functions inherited from iganet::utils::FullQualifiedName
virtual const std::string &	name () const noexcept
	Returns the full qualified name of the object.
Protected Attributes inherited from iganet::utils::FullQualifiedName
at::optional< std::string >	name_
	String storing the full qualified name of the object.

Detailed Description

Layer Normalization as described in the paper.

Layer Normalization, https://arxiv.org/abs/1607.06450

Constructor & Destructor Documentation

LayerNorm() [1/3]

iganet::LayerNorm::LayerNorm ( std::vector< int64_t >  normalized_shape )

inlineexplicit

LayerNorm() [2/3]

iganet::LayerNorm::LayerNorm ( torch::nn::functional::LayerNormFuncOptions  options )

inlineexplicit

LayerNorm() [3/3]

iganet::LayerNorm::LayerNorm ( std::vector< int64_t >  normalized_shape, const torch::Tensor &  weight, const torch::Tensor &  bias, double  eps  )

inlineexplicit

~LayerNorm()

iganet::LayerNorm::~LayerNorm ( )

overridedefault

Member Function Documentation

apply()

torch::Tensor iganet::LayerNorm::apply ( const torch::Tensor &  input ) const

inlineoverridevirtual

Applies the activation function to the given input.

Implements iganet::ActivationFunction.

options() [1/2]

torch::nn::functional::LayerNormFuncOptions & iganet::LayerNorm::options ( )

inline

Returns non-constant reference to options.

options() [2/2]

const torch::nn::functional::LayerNormFuncOptions & iganet::LayerNorm::options ( ) const

inline

Returns constant reference to options.

pretty_print()

virtual void iganet::LayerNorm::pretty_print ( std::ostream &  os = Log(log::info) ) const

inlineoverridevirtualnoexcept

Returns a string representation of the activation function.

Implements iganet::ActivationFunction.

read()

torch::serialize::InputArchive & iganet::LayerNorm::read ( torch::serialize::InputArchive &  archive, const std::string &  key = "layer_norm"  )

inlineoverridevirtual

Reads the activation function from a torch::serialize::InputArchive object.

Implements iganet::ActivationFunction.

write()

torch::serialize::OutputArchive & iganet::LayerNorm::write ( torch::serialize::OutputArchive &  archive, const std::string &  key = "layer_norm"  ) const

inlineoverridevirtual

Writes the activation function into a torch::serialize::OutputArchive object.

Implements iganet::ActivationFunction.

Member Data Documentation

options_

torch::nn::functional::LayerNormFuncOptions iganet::LayerNorm::options_

private

---

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

• include/layer.hpp