Stores the parameters used by loss layers. More...

Inheritance diagram for MyCaffe.param.LossParameter:

Public Types
enum	NormalizationMode { FULL = 0 , VALID = 1 , BATCH_SIZE = 2 , NONE = 3 }
	How to normalize the loss for loss layers that aggregate across batches, spatial dimensions, or other dimensions. Currenly only implemented in SoftmaxWithLoss layer. More...

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

Public Member Functions
	LossParameter (NormalizationMode norm=NormalizationMode.VALID)
	The constructor for the LossParameter. 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 LossParameter	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?	ignore_label `[getset]`
	If specified, the ignore instances with the given label. More...

NormalizationMode?	normalization `[getset]`
	Specifies the normalization mode (default = VALID). More...

bool	normalize `[getset]`
	DEPRECIATED. Ignore if normalization is specified. If normalization is not specified, then setting this to false will be equivalent to normalization = BATCH_SIZE to be consistent with previous behavior. More...

Detailed Description

Stores the parameters used by loss layers.

Definition at line 15 of file LossParameter.cs.

Member Enumeration Documentation

◆ NormalizationMode

enum MyCaffe.param.LossParameter.NormalizationMode

How to normalize the loss for loss layers that aggregate across batches, spatial dimensions, or other dimensions. Currenly only implemented in SoftmaxWithLoss layer.

Enumerator
FULL	Divide by the number of examples in the batch times spatial dimensions. Outputs that receive the ignore label will NOT be ignored in computing the normalization factor.
VALID	Divide by the total number of output locations that do not take the ignore label. If ignore label is not set, this behaves like FULL.
BATCH_SIZE	Divide by the batch size.
NONE	Do not normalize the loss.

Definition at line 26 of file LossParameter.cs.

Constructor & Destructor Documentation

◆ LossParameter()

MyCaffe.param.LossParameter.LossParameter ( NormalizationMode norm = NormalizationMode.VALID )

The constructor for the LossParameter.

The default VALID normalization mode is used for all loss layers, except for the SigmoidCrossEntropyLoss layer which uses BATCH_SIZE as the default for historical reasons.

Parameters

norm	Specifies the default normalization mode.

Definition at line 61 of file LossParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.LossParameter.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 122 of file LossParameter.cs.

◆ Copy()

override void MyCaffe.param.LossParameter.Copy ( LayerParameterBase src )

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 112 of file LossParameter.cs.

◆ FromProto()

static LossParameter MyCaffe.param.LossParameter.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 154 of file LossParameter.cs.

◆ Load()

override object MyCaffe.param.LossParameter.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 100 of file LossParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.LossParameter.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 134 of file LossParameter.cs.

Property Documentation

◆ ignore_label

int? MyCaffe.param.LossParameter.ignore_label

getset

If specified, the ignore instances with the given label.

Definition at line 70 of file LossParameter.cs.

◆ normalization

NormalizationMode? MyCaffe.param.LossParameter.normalization

getset

Specifies the normalization mode (default = VALID).

Definition at line 80 of file LossParameter.cs.

◆ normalize

bool MyCaffe.param.LossParameter.normalize

getset

DEPRECIATED. Ignore if normalization is specified. If normalization is not specified, then setting this to false will be equivalent to normalization = BATCH_SIZE to be consistent with previous behavior.

Definition at line 93 of file LossParameter.cs.

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

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

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ NormalizationMode

Constructor & Destructor Documentation

◆ LossParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ ignore_label

◆ normalization

◆ normalize