Specifies the parameters for the ReshapeTemporalLayer.
More...

Inheritance diagram for MyCaffe.param.tft.ReshapeTemporalParameter:

Public Types
enum	MODE { BEFORE , AFTER }
	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
	ReshapeTemporalParameter ()
	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 ReshapeTemporalParameter	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	forced_repeat_count `[getset]`
	Specifies the forced repeat steps bottom(1). A value of -1 specifies to use the temporal axis as the repeat count (default), otherwise the forced count is used to compy the entire blob that number of times. More...

bool	enable_clip_output `[getset]`
	Specifies to output the clip for the data output in the AFTER mode. More...

bool	enable_weight_output `[getset]`
	Specifies to output the weights for the data output in the AFTER mode. More...

MODE	mode `[getset]`
	Specifies the mode of operation. More...

Detailed Description

Specifies the parameters for the ReshapeTemporalLayer.

When run using the BEFORE mode, this layer is used to reshape static inputs along time while stacking temporal and time distributed contexts along the batch. When run using the AFTER mode, this layer reshapes the outputs and weight back into their num samples x temporal steps shape.

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 23 of file ReshapeTemporalParameter.cs.

Member Enumeration Documentation

◆ MODE

enum MyCaffe.param.tft.ReshapeTemporalParameter.MODE

Defines the modulation type.

Enumerator
BEFORE	Specifies to reshape in preparation for a temporal operation.
AFTER	Specifies to reshape after a temporal operation.

Definition at line 33 of file ReshapeTemporalParameter.cs.

Constructor & Destructor Documentation

◆ ReshapeTemporalParameter()

MyCaffe.param.tft.ReshapeTemporalParameter.ReshapeTemporalParameter ( )

Constructor for the parameter.

Definition at line 46 of file ReshapeTemporalParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.tft.ReshapeTemporalParameter.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 114 of file ReshapeTemporalParameter.cs.

◆ Copy()

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

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 103 of file ReshapeTemporalParameter.cs.

◆ FromProto()

static ReshapeTemporalParameter MyCaffe.param.tft.ReshapeTemporalParameter.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 143 of file ReshapeTemporalParameter.cs.

◆ Load()

override object MyCaffe.param.tft.ReshapeTemporalParameter.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 91 of file ReshapeTemporalParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.tft.ReshapeTemporalParameter.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 126 of file ReshapeTemporalParameter.cs.

Property Documentation

◆ enable_clip_output

bool MyCaffe.param.tft.ReshapeTemporalParameter.enable_clip_output

getset

Specifies to output the clip for the data output in the AFTER mode.

Definition at line 64 of file ReshapeTemporalParameter.cs.

◆ enable_weight_output

bool MyCaffe.param.tft.ReshapeTemporalParameter.enable_weight_output

getset

Specifies to output the weights for the data output in the AFTER mode.

Definition at line 74 of file ReshapeTemporalParameter.cs.

◆ forced_repeat_count

int MyCaffe.param.tft.ReshapeTemporalParameter.forced_repeat_count

getset

Specifies the forced repeat steps bottom(1). A value of -1 specifies to use the temporal axis as the repeat count (default), otherwise the forced count is used to compy the entire blob that number of times.

Definition at line 54 of file ReshapeTemporalParameter.cs.

◆ mode

MODE MyCaffe.param.tft.ReshapeTemporalParameter.mode

getset

Specifies the mode of operation.

Definition at line 84 of file ReshapeTemporalParameter.cs.

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

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

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ MODE

Constructor & Destructor Documentation

◆ ReshapeTemporalParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ enable_clip_output

◆ enable_weight_output

◆ forced_repeat_count

◆ mode