Specifies the parameters for the LayerNormalizationLayer. More...

Inheritance diagram for MyCaffe.param.gpt.LayerNormParameter:

Public Member Functions
	LayerNormParameter ()
	Constructor for the parameter. More...

override object	Load (System.IO.BinaryReader br, bool bNewInstance=true)
	Load the parameter from a binary reader. More...

override void	Copy (LayerParameterBase src)
	Copy on parameter to another. More...

override LayerParameterBase	Clone ()
	Creates a new copy of this instance of the parameter. More...

override RawProto	ToProto (string strName)
	Convert the parameter into a RawProto. More...

Public Member Functions inherited from MyCaffe.param.LayerParameterBase
	LayerParameterBase ()
	Constructor for the parameter. More...

virtual string	PrepareRunModelInputs ()
	This method gives derivative classes a chance specify model inputs required by the run model. More...

virtual void	PrepareRunModel (LayerParameter p)
	This method gives derivative classes a chance to prepare the layer for a run-model. More...

void	Save (BinaryWriter bw)
	Save this parameter to a binary writer. More...

abstract object	Load (BinaryReader br, bool bNewInstance=true)
	Load the parameter from a binary reader. More...

Public Member Functions inherited from MyCaffe.basecode.BaseParameter
	BaseParameter ()
	Constructor for the parameter. More...

virtual bool	Compare (BaseParameter p)
	Compare this parameter to another parameter. More...

Static Public Member Functions
static LayerNormParameter	FromProto (RawProto rp)
	Parses the parameter from a RawProto. More...

Static Public Member Functions inherited from MyCaffe.basecode.BaseParameter
static double	ParseDouble (string strVal)
	Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static bool	TryParse (string strVal, out double df)
	Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static float	ParseFloat (string strVal)
	Parse float values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

static bool	TryParse (string strVal, out float f)
	Parse doufloatble values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More...

Properties
double	epsilon `[getset]`
	Specifies the epsilon value used to avoid invalid values (default = 1e-10). More...

bool	enable_passthrough `[getset]`
	Specifies to pass-through the data on the forward and backward pass (e.g. skip the layer norm, used only for debugging. default = false). More...

bool	enable_cuda_impl `[getset]`
	Specifies to use the low-level full cuda implementation of LayerNorm (default = false). More...

Additional Inherited Members
Public Types inherited from MyCaffe.param.LayerParameterBase
enum	LABEL_TYPE { NONE , SINGLE , MULTIPLE , ONLY_ONE }
	Defines the label type. More...

Detailed Description

Specifies the parameters for the LayerNormalizationLayer.

See also: GitHub:CyberZHG by Zhao HG (MIT Liceense).; LayerNorm PyTorch; Understanding and Improving Layer Normalization by Xu et al., 2019, arXiv:1911.07013

Definition at line 20 of file LayerNormParameter.cs.

Constructor & Destructor Documentation

◆ LayerNormParameter()

MyCaffe.param.gpt.LayerNormParameter.LayerNormParameter ( )

Constructor for the parameter.

Definition at line 27 of file LayerNormParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.gpt.LayerNormParameter.Clone ( )

virtual

Creates a new copy of this instance of the parameter.

Returns: A new instance of this parameter is returned.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 97 of file LayerNormParameter.cs.

◆ Copy()

override void MyCaffe.param.gpt.LayerNormParameter.Copy ( LayerParameterBase src )

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 85 of file LayerNormParameter.cs.

◆ FromProto()

static LayerNormParameter MyCaffe.param.gpt.LayerNormParameter.FromProto ( RawProto rp )

static

Parses the parameter from a RawProto.

Parameters

rp	Specifies the RawProto to parse.

Returns: A new instance of the parameter is returned.

Definition at line 127 of file LayerNormParameter.cs.

◆ Load()

override object MyCaffe.param.gpt.LayerNormParameter.Load	(	System.IO.BinaryReader	br,
		bool	bNewInstance = `true`
	)

Load the parameter from a binary reader.

Parameters

br	Specifies the binary reader.
bNewInstance	When true a new instance is created (the default), otherwise the existing instance is loaded from the binary reader.

Returns: Returns an instance of the parameter.

Definition at line 70 of file LayerNormParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.gpt.LayerNormParameter.ToProto ( string strName )

virtual

Convert the parameter into a RawProto.

Parameters

strName Specifies the name to associate with the RawProto.

Returns: The new RawProto is returned.

Implements MyCaffe.basecode.BaseParameter.

Definition at line 109 of file LayerNormParameter.cs.

Property Documentation

◆ enable_cuda_impl

bool MyCaffe.param.gpt.LayerNormParameter.enable_cuda_impl

getset

Specifies to use the low-level full cuda implementation of LayerNorm (default = false).

The cuda implementation runs around 30% faster when using float base types.

Definition at line 58 of file LayerNormParameter.cs.

◆ enable_passthrough

bool MyCaffe.param.gpt.LayerNormParameter.enable_passthrough

getset

Specifies to pass-through the data on the forward and backward pass (e.g. skip the layer norm, used only for debugging. default = false).

Definition at line 45 of file LayerNormParameter.cs.

◆ epsilon

double MyCaffe.param.gpt.LayerNormParameter.epsilon

getset

Specifies the epsilon value used to avoid invalid values (default = 1e-10).

Definition at line 35 of file LayerNormParameter.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/param.gpt/LayerNormParameter.cs

Public Member Functions

Static Public Member Functions

Properties

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ LayerNormParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ enable_cuda_impl

◆ enable_passthrough

◆ epsilon