Specifies training parameters (multipliers on global learning constants, and the name of other settings used for weight sharing). More...

Inheritance diagram for MyCaffe.param.ParamSpec:

Public Types
enum	DimCheckMode { STRICT = 0 , PERMISSIVE = 1 }
	Defines the dimension check mode. More...

Public Member Functions
	ParamSpec ()
	The ParamSpec constructor. More...

	ParamSpec (string strName)
	The ParamSpec constructor. More...

	ParamSpec (double dfLrMult, double dfDecayMult, string strName=null)
	The ParamSpec constructor. More...

void	Save (BinaryWriter bw)
	Saves the ParamSpec to a binary writer. More...

object	Load (BinaryReader br, bool bNewInstance)
	Loads a ParamSpec from a binary reader. More...

object	Clone ()
	Creates a new copy of the ParamSpec. More...

override RawProto	ToProto (string strName)
	Converts the ParamSpec into a RawProto. 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 ParamSpec	FromProto (RawProto rp)
	Parses a new ParamSpec 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
string	name `[getset]`
	Specifies the name of this parameter. More...

DimCheckMode	share_mode `[getset]`
	Specifies whether to require shared weights to have the same shape, or just the same count - defaults to STICT (same shape). More...

double	lr_mult `[getset]`
	Specifies the multiplier used on the global learning rate for this parameter. More...

double	decay_mult `[getset]`
	Specifies the multiplier used on the global weight decay for this parameter. More...

Detailed Description

Specifies training parameters (multipliers on global learning constants, and the name of other settings used for weight sharing).

Definition at line 18 of file ParamSpec.cs.

Member Enumeration Documentation

◆ DimCheckMode

enum MyCaffe.param.ParamSpec.DimCheckMode

Defines the dimension check mode.

Enumerator
STRICT	STRICT (default) requires that num, channels, height, width each match.
PERMISSIVE	PERMISSIVE requires only the count (numchannelsheight*width) to match.

Definition at line 36 of file ParamSpec.cs.

Constructor & Destructor Documentation

◆ ParamSpec() [1/3]

MyCaffe.param.ParamSpec.ParamSpec ( )

The ParamSpec constructor.

Definition at line 62 of file ParamSpec.cs.

◆ ParamSpec() [2/3]

MyCaffe.param.ParamSpec.ParamSpec ( string strName )

The ParamSpec constructor.

Parameters

strName Specifies a name given to the ParamSpec.

Definition at line 70 of file ParamSpec.cs.

◆ ParamSpec() [3/3]

MyCaffe.param.ParamSpec.ParamSpec	(	double	dfLrMult,
		double	dfDecayMult,
		string	strName = `null`
	)

The ParamSpec constructor.

Parameters

dfLrMult	Specifies the learning rate multiplier given to the ParamSpec.
dfDecayMult	Specifies the decay rate multiplier given to the ParamSpec.
strName	Specifies the name given to the ParamSpec.

Definition at line 81 of file ParamSpec.cs.

Member Function Documentation

◆ Clone()

object MyCaffe.param.ParamSpec.Clone ( )

Creates a new copy of the ParamSpec.

Returns: A new instance of the ParamSpec is returned.

Definition at line 177 of file ParamSpec.cs.

◆ FromProto()

static ParamSpec MyCaffe.param.ParamSpec.FromProto ( RawProto rp )

static

Parses a new ParamSpec from a RawProto.

Parameters

rp	Specifies the RawProto representing the ParamSpec.

Returns: The new ParamSpec instance is returned.

Definition at line 217 of file ParamSpec.cs.

◆ Load()

object MyCaffe.param.ParamSpec.Load	(	BinaryReader	br,
		bool	bNewInstance
	)

Loads a ParamSpec from a binary reader.

Parameters

br	Specifies the binary reader to use.
bNewInstance	When true, a new ParamSpec instance is created and loaded, otherwise this instance is loaded.

Returns: The ParamSpec instance loaded is returned.

Implements MyCaffe.basecode.IBinaryPersist.

Definition at line 108 of file ParamSpec.cs.

◆ Save()

void MyCaffe.param.ParamSpec.Save ( BinaryWriter bw )

Saves the ParamSpec to a binary writer.

Parameters

bw	Specifies the binary writer to use.

Implements MyCaffe.basecode.IBinaryPersist.

Definition at line 94 of file ParamSpec.cs.

◆ ToProto()

override RawProto MyCaffe.param.ParamSpec.ToProto ( string strName )

virtual

Converts the ParamSpec into a RawProto.

Parameters

strName Specifies a name given to the RawProto.

Returns: The new RawProto representing the ParamSpec is returned.

Implements MyCaffe.basecode.BaseParameter.

Definition at line 194 of file ParamSpec.cs.

Property Documentation

◆ decay_mult

double MyCaffe.param.ParamSpec.decay_mult

getset

Specifies the multiplier used on the global weight decay for this parameter.

Definition at line 167 of file ParamSpec.cs.

◆ lr_mult

double MyCaffe.param.ParamSpec.lr_mult

getset

Specifies the multiplier used on the global learning rate for this parameter.

Definition at line 157 of file ParamSpec.cs.

◆ name

string MyCaffe.param.ParamSpec.name

getset

Specifies the name of this parameter.

Definition at line 137 of file ParamSpec.cs.

◆ share_mode

DimCheckMode MyCaffe.param.ParamSpec.share_mode

getset

Specifies whether to require shared weights to have the same shape, or just the same count - defaults to STICT (same shape).

Definition at line 147 of file ParamSpec.cs.

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

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

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ DimCheckMode

Constructor & Destructor Documentation

◆ ParamSpec() [1/3]

◆ ParamSpec() [2/3]

◆ ParamSpec() [3/3]

Member Function Documentation

◆ Clone()

◆ FromProto()

◆ Load()

◆ Save()

◆ ToProto()

Property Documentation

◆ decay_mult

◆ lr_mult

◆ name

◆ share_mode