Specifies the parameters for the GluLayer (Gated Linear Unit).
More...

Inheritance diagram for MyCaffe.param.tft.GluParameter:

Public Types
enum	MODULATION { SIGMOID }
	Defines the modulation type. More...

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

Public Member Functions
	GluParameter ()
	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 GluParameter	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
int	input_dim `[getset]`
	Specifies the input dimension. More...

MODULATION	modulation `[getset]`
	Specifies the gate modulation type. More...

bool	enable_noise `[getset]`
	Enable/disable noise in the inner-product layer (default = false). More...

double	sigma_init `[getset]`
	Specifies the initialization value for the sigma weight and sigma bias used when 'enable_noise' = true. More...

bool	bias_term `[getset]`
	Whether to have bias terms or not. More...

FillerParameter	weight_filler `[getset]`
	The filler for the weights. More...

FillerParameter	bias_filler `[getset]`
	The filler for the bias. More...

int	axis `[getset]`
	Specifies the first axis to be lumped into a single inner product computation; all preceding axes are retained in the output. May be negative to index from the end (e.g., -1 for the last axis) More...

Detailed Description

Specifies the parameters for the GluLayer (Gated Linear Unit).

The output of the layer is a linear projection (X * W + b) modulated by the gates sigmoid (X * V + c). These gates multiply each element of the matrix X * W + b and control the information passed in. The simplified gating mechanism in this layer is for non-deterministic gates that reduce the vanishing gradient problem, by having linear units couypled to the gates. This retains the non-linear capabilities of the layer while allowing the gradient to propagate through the linear unit without scaling.

See also: Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting by Bryan Lim, Sercan O. Arik, Nicolas Loeff, and Tomas Pfister, 2019, arXiv 1912.09363; Github - PlaytikaOSS/tft-torch by Playtika Research, 2021.; Github - PlaytikaOSS/tft-torch tft.py by Playtika Research, 2021.; "Language modeling with gated convolution networks by Dauphin, Yann N., et al., International conference on machine learning, PMLR, 2017

Definition at line 27 of file GluParameter.cs.

Member Enumeration Documentation

◆ MODULATION

enum MyCaffe.param.tft.GluParameter.MODULATION

Defines the modulation type.

Enumerator
SIGMOID	Specifies to use Sigmoid modulation.

Definition at line 41 of file GluParameter.cs.

Constructor & Destructor Documentation

◆ GluParameter()

MyCaffe.param.tft.GluParameter.GluParameter ( )

Constructor for the parameter.

Definition at line 50 of file GluParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.tft.GluParameter.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 175 of file GluParameter.cs.

◆ Copy()

override void MyCaffe.param.tft.GluParameter.Copy ( LayerParameterBase src )

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 155 of file GluParameter.cs.

◆ FromProto()

static GluParameter MyCaffe.param.tft.GluParameter.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 217 of file GluParameter.cs.

◆ Load()

override object MyCaffe.param.tft.GluParameter.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 143 of file GluParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.tft.GluParameter.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 187 of file GluParameter.cs.

Property Documentation

◆ axis

int MyCaffe.param.tft.GluParameter.axis

getset

Specifies the first axis to be lumped into a single inner product computation; all preceding axes are retained in the output. May be negative to index from the end (e.g., -1 for the last axis)

Definition at line 135 of file GluParameter.cs.

◆ bias_filler

FillerParameter MyCaffe.param.tft.GluParameter.bias_filler

getset

The filler for the bias.

Definition at line 123 of file GluParameter.cs.

◆ bias_term

bool MyCaffe.param.tft.GluParameter.bias_term

getset

Whether to have bias terms or not.

Definition at line 101 of file GluParameter.cs.

◆ enable_noise

bool MyCaffe.param.tft.GluParameter.enable_noise

getset

Enable/disable noise in the inner-product layer (default = false).

When enabled, noise is only used during the training phase.

Definition at line 81 of file GluParameter.cs.

◆ input_dim

int MyCaffe.param.tft.GluParameter.input_dim

getset

Specifies the input dimension.

Definition at line 58 of file GluParameter.cs.

◆ modulation

MODULATION MyCaffe.param.tft.GluParameter.modulation

getset

Specifies the gate modulation type.

Definition at line 68 of file GluParameter.cs.

◆ sigma_init

double MyCaffe.param.tft.GluParameter.sigma_init

getset

Specifies the initialization value for the sigma weight and sigma bias used when 'enable_noise' = true.

Definition at line 91 of file GluParameter.cs.

◆ weight_filler

FillerParameter MyCaffe.param.tft.GluParameter.weight_filler

getset

The filler for the weights.

Definition at line 112 of file GluParameter.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/param.tft/GluParameter.cs

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ MODULATION

Constructor & Destructor Documentation

◆ GluParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ axis

◆ bias_filler

◆ bias_term

◆ enable_noise

◆ input_dim

◆ modulation

◆ sigma_init

◆ weight_filler