Specifies the parameters for the GrnLayer (Gated Response Network).
More...

Inheritance diagram for MyCaffe.param.tft.GrnParameter:

Public Types
enum	ACTIVATION { ELU , RELU }
	Defines the activation 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
	GrnParameter ()
	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 GrnParameter	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
ACTIVATION	activation `[getset]`
	Specifies the activation type to use (default=ELU) More...

int	input_dim `[getset]`
	Specifies the input dimension. More...

int	hidden_dim `[getset]`
	Specifies the input dimension. More...

int	output_dim `[getset]`
	Specifies the output dimension. More...

int?	context_dim `[getset]`
	Specifies the context dimension, or null to ignore. More...

float	dropout_ratio `[getset]`
	Specifies the dropout ratio (default = 0.05 or 5%). More...

bool	batch_first `[getset]`
	Specifies the batch_first setting. 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 GrnLayer (Gated Response Network).

This layer takes as input a primary input 'x' and optional context vector 'c'. A GLU (Gated Linear Unit) is used for controlling the extent to which the module will contribute to the original input 'x', potentially skipping over the layer entirely as the GLU outputs could all be close to zero by the GLU supressing. In cases where no context vector is used, the GRN treats the context input as zero. During training dropout is applied before gating.

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.

Definition at line 27 of file GrnParameter.cs.

Member Enumeration Documentation

◆ ACTIVATION

enum MyCaffe.param.tft.GrnParameter.ACTIVATION

Defines the activation type.

Enumerator
ELU	Specifies to use an ELU activation (default).
RELU	Specifies to use a RELU activation.

Definition at line 43 of file GrnParameter.cs.

Constructor & Destructor Documentation

◆ GrnParameter()

MyCaffe.param.tft.GrnParameter.GrnParameter ( )

Constructor for the parameter.

Definition at line 57 of file GrnParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.tft.GrnParameter.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 199 of file GrnParameter.cs.

◆ Copy()

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

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 178 of file GrnParameter.cs.

◆ FromProto()

static GrnParameter MyCaffe.param.tft.GrnParameter.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 240 of file GrnParameter.cs.

◆ Load()

override object MyCaffe.param.tft.GrnParameter.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 166 of file GrnParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.tft.GrnParameter.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 211 of file GrnParameter.cs.

Property Documentation

◆ activation

ACTIVATION MyCaffe.param.tft.GrnParameter.activation

getset

Specifies the activation type to use (default=ELU)

Definition at line 65 of file GrnParameter.cs.

◆ axis

int MyCaffe.param.tft.GrnParameter.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 159 of file GrnParameter.cs.

◆ batch_first

bool MyCaffe.param.tft.GrnParameter.batch_first

getset

Specifies the batch_first setting.

Definition at line 125 of file GrnParameter.cs.

◆ bias_filler

FillerParameter MyCaffe.param.tft.GrnParameter.bias_filler

getset

The filler for the bias.

Definition at line 147 of file GrnParameter.cs.

◆ context_dim

int? MyCaffe.param.tft.GrnParameter.context_dim

getset

Specifies the context dimension, or null to ignore.

Definition at line 105 of file GrnParameter.cs.

◆ dropout_ratio

float MyCaffe.param.tft.GrnParameter.dropout_ratio

getset

Specifies the dropout ratio (default = 0.05 or 5%).

Definition at line 115 of file GrnParameter.cs.

◆ hidden_dim

int MyCaffe.param.tft.GrnParameter.hidden_dim

getset

Specifies the input dimension.

Definition at line 85 of file GrnParameter.cs.

◆ input_dim

int MyCaffe.param.tft.GrnParameter.input_dim

getset

Specifies the input dimension.

Definition at line 75 of file GrnParameter.cs.

◆ output_dim

int MyCaffe.param.tft.GrnParameter.output_dim

getset

Specifies the output dimension.

Definition at line 95 of file GrnParameter.cs.

◆ weight_filler

FillerParameter MyCaffe.param.tft.GrnParameter.weight_filler

getset

The filler for the weights.

Definition at line 136 of file GrnParameter.cs.

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

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

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ ACTIVATION

Constructor & Destructor Documentation

◆ GrnParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ activation

◆ axis

◆ batch_first

◆ bias_filler

◆ context_dim

◆ dropout_ratio

◆ hidden_dim

◆ input_dim

◆ output_dim

◆ weight_filler