Specifies the parameters for the VarSelNetLayer (Variable Selection Network).
More...

Inheritance diagram for MyCaffe.param.tft.VarSelNetParameter:

Public Member Functions
	VarSelNetParameter ()
	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 VarSelNetParameter	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	num_inputs `[getset]`
	Specifies the quantity of input variables, including both numeric and categorical for the relevant channel. More...

int	input_dim `[getset]`
	Specifies the attribute/embedding dimension of the input, associated witht he 'state_size' of the model. More...

int	hidden_dim `[getset]`
	Specifies the embedding width of the output. More...

int?	context_dim `[getset]`
	Specifies the embedding width of the context signal expected to be fed as an auxiliary input (optional, can be null). More...

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

bool	batch_first `[getset]`
	Specifies a boolean indicating whether the batch dimension is expected to be the first dimension of the input 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 computations; all preceding axes are retained in the output. May be negative to index from the end (e.g., -1 for the last axis) 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 VarSelNetLayer (Variable Selection Network).

The VSN enables instance-wise variable selection and is applied to both the static covariates and time-dependent covariates as the specific contribution of each input to the output is typically unknown. The VSN provides insights into which variables contribute the most for the prediction problem and allows the model to remove unnecessarily noisy inputs which could negatively impact the performance.

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 26 of file VarSetLnetParameter.cs.

Constructor & Destructor Documentation

◆ VarSelNetParameter()

MyCaffe.param.tft.VarSelNetParameter.VarSelNetParameter ( )

Constructor for the parameter.

Definition at line 39 of file VarSetLnetParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.tft.VarSelNetParameter.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 170 of file VarSetLnetParameter.cs.

◆ Copy()

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

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 150 of file VarSetLnetParameter.cs.

◆ FromProto()

static VarSelNetParameter MyCaffe.param.tft.VarSelNetParameter.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 210 of file VarSetLnetParameter.cs.

◆ Load()

override object MyCaffe.param.tft.VarSelNetParameter.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 138 of file VarSetLnetParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.tft.VarSelNetParameter.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 182 of file VarSetLnetParameter.cs.

Property Documentation

◆ axis

int MyCaffe.param.tft.VarSelNetParameter.axis

getset

Specifies the first axis to be lumped into a single inner product computations; 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 131 of file VarSetLnetParameter.cs.

◆ batch_first

bool MyCaffe.param.tft.VarSelNetParameter.batch_first

getset

Specifies a boolean indicating whether the batch dimension is expected to be the first dimension of the input or not.

Definition at line 97 of file VarSetLnetParameter.cs.

◆ bias_filler

FillerParameter MyCaffe.param.tft.VarSelNetParameter.bias_filler

getset

The filler for the bias.

Definition at line 119 of file VarSetLnetParameter.cs.

◆ context_dim

int? MyCaffe.param.tft.VarSelNetParameter.context_dim

getset

Specifies the embedding width of the context signal expected to be fed as an auxiliary input (optional, can be null).

Definition at line 77 of file VarSetLnetParameter.cs.

◆ dropout_ratio

float MyCaffe.param.tft.VarSelNetParameter.dropout_ratio

getset

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

Definition at line 87 of file VarSetLnetParameter.cs.

◆ hidden_dim

int MyCaffe.param.tft.VarSelNetParameter.hidden_dim

getset

Specifies the embedding width of the output.

Definition at line 67 of file VarSetLnetParameter.cs.

◆ input_dim

int MyCaffe.param.tft.VarSelNetParameter.input_dim

getset

Specifies the attribute/embedding dimension of the input, associated witht he 'state_size' of the model.

Definition at line 57 of file VarSetLnetParameter.cs.

◆ num_inputs

int MyCaffe.param.tft.VarSelNetParameter.num_inputs

getset

Specifies the quantity of input variables, including both numeric and categorical for the relevant channel.

Definition at line 47 of file VarSetLnetParameter.cs.

◆ weight_filler

FillerParameter MyCaffe.param.tft.VarSelNetParameter.weight_filler

getset

The filler for the weights.

Definition at line 108 of file VarSetLnetParameter.cs.

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

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

Public Member Functions

Static Public Member Functions

Properties

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ VarSelNetParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ axis

◆ batch_first

◆ bias_filler

◆ context_dim

◆ dropout_ratio

◆ hidden_dim

◆ input_dim

◆ num_inputs

◆ weight_filler