Specifies the parameter for the data normalizer layer. More...

Inheritance diagram for MyCaffe.param.DataNormalizerParameter:

Public Types
enum	NORMALIZATION_STEP { CENTER , STDEV , RANGE , ADDITIVE , RETURNS , LOG }
	Specifies the normalization step to run. More...

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

Public Member Functions
	DataNormalizerParameter ()
	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 DataNormalizerParameter	FromProto (RawProto rp, DataNormalizerParameter p=null)
	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?	label_data_channel `[getset]`
	Specifies to data channel used for the label (if any). More...

bool	across_data_and_label `[getset]`
	Specifies to normalize across both the data and label data together. More...

List< NORMALIZATION_STEP >	steps `[getset]`
	Specifies the normalization steps which are performed in the order for which they are listed. More...

List< int >	ignore_channels `[getset]`
	Specifies the channels to ignore and just pass through in their original form. More...

double?	input_stdev `[getset]`
	Specifies the input standard deviation, if known. When not specified input_stdev is determined dynamically from the data input itself. More...

double?	input_mean `[getset]`
	Specifies the input mean, if known. When not specified the input_mean is determined dynamically from the data input itself. More...

double	input_min `[getset]`
	Specifies the minimum data range of the intput, if known. If both input_min and input_max are 0 the input_min/input_max are determined dynamically from the data input itself. More...

double	input_max `[getset]`
	Specifies the maximum data range of the intput, if known. If both input_min and input_max are 0 the input_min/input_max are determined dynamically from the data input itself. More...

double	output_min `[getset]`
	Specifies the minimum data range of the output. More...

double	output_max `[getset]`
	Specifies the maximum data range of the output. More...

Detailed Description

Specifies the parameter for the data normalizer layer.

The data normalizer layer provides a detailed normalization that is applied to the data (and label if desired).

Definition at line 18 of file DataNormalizerParameter.cs.

Member Enumeration Documentation

◆ NORMALIZATION_STEP

enum MyCaffe.param.DataNormalizerParameter.NORMALIZATION_STEP

Specifies the normalization step to run.

Enumerator
CENTER	Center the data by subtracting the mean.
STDEV	Normalize the data by dividing by the standard deviation.
RANGE	Normalize the data by fitting the data into the 'output_min'/'output_max' range.
ADDITIVE	Add each data value to the previous data value.
RETURNS	Create the percentage change of the current data from the previous.
LOG	Normalize the data by taking the LOG on each item.

Definition at line 34 of file DataNormalizerParameter.cs.

Constructor & Destructor Documentation

◆ DataNormalizerParameter()

MyCaffe.param.DataNormalizerParameter.DataNormalizerParameter ( )

Constructor for the parameter.

Definition at line 63 of file DataNormalizerParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.DataNormalizerParameter.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 194 of file DataNormalizerParameter.cs.

◆ Copy()

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

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 188 of file DataNormalizerParameter.cs.

◆ FromProto()

static DataNormalizerParameter MyCaffe.param.DataNormalizerParameter.FromProto	(	RawProto	rp,
		DataNormalizerParameter	p = `null`
	)

static

Parses the parameter from a RawProto.

Parameters

rp	Specifies the RawProto to parse.
p	Optionally, specifies an instance to load. If null, a new instance is created and loaded.

Returns: A new instance of the parameter is returned.

Definition at line 242 of file DataNormalizerParameter.cs.

◆ Load()

override object MyCaffe.param.DataNormalizerParameter.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 176 of file DataNormalizerParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.DataNormalizerParameter.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 206 of file DataNormalizerParameter.cs.

Property Documentation

◆ across_data_and_label

bool MyCaffe.param.DataNormalizerParameter.across_data_and_label

getset

Specifies to normalize across both the data and label data together.

When true centering and other normalization takes place across the entire data range within both the data and label together. When false centering and other normalization takes place separately for data and separately for the label (if supplied).

Definition at line 89 of file DataNormalizerParameter.cs.

◆ ignore_channels

List<int> MyCaffe.param.DataNormalizerParameter.ignore_channels

getset

Specifies the channels to ignore and just pass through in their original form.

Definition at line 109 of file DataNormalizerParameter.cs.

◆ input_max

double MyCaffe.param.DataNormalizerParameter.input_max

getset

Specifies the maximum data range of the intput, if known. If both input_min and input_max are 0 the input_min/input_max are determined dynamically from the data input itself.

Definition at line 149 of file DataNormalizerParameter.cs.

◆ input_mean

double? MyCaffe.param.DataNormalizerParameter.input_mean

getset

Specifies the input mean, if known. When not specified the input_mean is determined dynamically from the data input itself.

Definition at line 129 of file DataNormalizerParameter.cs.

◆ input_min

double MyCaffe.param.DataNormalizerParameter.input_min

getset

Specifies the minimum data range of the intput, if known. If both input_min and input_max are 0 the input_min/input_max are determined dynamically from the data input itself.

Definition at line 139 of file DataNormalizerParameter.cs.

◆ input_stdev

double? MyCaffe.param.DataNormalizerParameter.input_stdev

getset

Specifies the input standard deviation, if known. When not specified input_stdev is determined dynamically from the data input itself.

Definition at line 119 of file DataNormalizerParameter.cs.

◆ label_data_channel

int? MyCaffe.param.DataNormalizerParameter.label_data_channel

getset

Specifies to data channel used for the label (if any).

Some models, such as LSTM, use input data as part of the label. The label_data_channel specifies which channel within the data is used as the label. When not specified, the label must have the same number of channels as the data.

Definition at line 75 of file DataNormalizerParameter.cs.

◆ output_max

double MyCaffe.param.DataNormalizerParameter.output_max

getset

Specifies the maximum data range of the output.

Definition at line 169 of file DataNormalizerParameter.cs.

◆ output_min

double MyCaffe.param.DataNormalizerParameter.output_min

getset

Specifies the minimum data range of the output.

Definition at line 159 of file DataNormalizerParameter.cs.

◆ steps

List<NORMALIZATION_STEP> MyCaffe.param.DataNormalizerParameter.steps

getset

Specifies the normalization steps which are performed in the order for which they are listed.

Definition at line 99 of file DataNormalizerParameter.cs.

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

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

Public Types

Public Member Functions

Static Public Member Functions

Properties

Detailed Description

Member Enumeration Documentation

◆ NORMALIZATION_STEP

Constructor & Destructor Documentation

◆ DataNormalizerParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ across_data_and_label

◆ ignore_channels

◆ input_max

◆ input_mean

◆ input_min

◆ input_stdev

◆ label_data_channel

◆ output_max

◆ output_min

◆ steps