Specifies the parameters for the GradientScaleLayer. More...

Inheritance diagram for MyCaffe.param.GradientScaleParameter:

Public Member Functions
	GradientScaleParameter ()
	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 GradientScaleParameter	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	lower_bound `[getset]`
	Specifies the lower bound of the height used for scaling. More...

double	upper_bound `[getset]`
	Specifies the upper bound of the height used for scaling. More...

double	alpha `[getset]`
	Specifies the alpha value applied to the current iter/max_iter, used when scaling. More...

double	max_iter `[getset]`
	Specifies the maximum iteration used when scaling. 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 GradientScaleLayer.

Scaling is performed according to the schedule: $y = \frac{2 \cdot height} {1 + \exp(-\alpha \cot progress)} - upper\_bound$ , where $height = upper\_bound - lower\_bound$ , $lower\_bound$ is the smallest scaling factor, $upper\_bound$ is the largest scaling factor, $\alpha$ controls how fast the transition occurs between the scaling factors, $progress = \min(iter / max\_iter, 1)$ corresponds to the current transition state (the is the current iteration of the solver).

The GradientScaleLayer can be used to implement gradient reversals.

See also: Domain-Adversarial Training of Neural Networks by Ganin et al., 2015, v4 in 2016.; Github/ddtm/caffe for original source.

Definition at line 30 of file GradientScaleParameter.cs.

Constructor & Destructor Documentation

◆ GradientScaleParameter()

MyCaffe.param.GradientScaleParameter.GradientScaleParameter ( )

Constructor for the parameter.

Definition at line 38 of file GradientScaleParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.GradientScaleParameter.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 116 of file GradientScaleParameter.cs.

◆ Copy()

override void MyCaffe.param.GradientScaleParameter.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 GradientScaleParameter.cs.

◆ FromProto()

static GradientScaleParameter MyCaffe.param.GradientScaleParameter.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 145 of file GradientScaleParameter.cs.

◆ Load()

override object MyCaffe.param.GradientScaleParameter.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 88 of file GradientScaleParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.GradientScaleParameter.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 128 of file GradientScaleParameter.cs.

Property Documentation

◆ alpha

double MyCaffe.param.GradientScaleParameter.alpha

getset

Specifies the alpha value applied to the current iter/max_iter, used when scaling.

Definition at line 66 of file GradientScaleParameter.cs.

◆ lower_bound

double MyCaffe.param.GradientScaleParameter.lower_bound

getset

Specifies the lower bound of the height used for scaling.

Definition at line 46 of file GradientScaleParameter.cs.

◆ max_iter

double MyCaffe.param.GradientScaleParameter.max_iter

getset

Specifies the maximum iteration used when scaling.

Definition at line 76 of file GradientScaleParameter.cs.

◆ upper_bound

double MyCaffe.param.GradientScaleParameter.upper_bound

getset

Specifies the upper bound of the height used for scaling.

Definition at line 56 of file GradientScaleParameter.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/param/GradientScaleParameter.cs

Public Member Functions

Static Public Member Functions

Properties

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ GradientScaleParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ alpha

◆ lower_bound

◆ max_iter

◆ upper_bound