Specifies the parameters for the DetectionOutputLayer. More...

Inheritance diagram for MyCaffe.param.ssd.DetectionOutputParameter:

Public Member Functions
	DetectionOutputParameter ()
	The constructor. 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 DetectionOutputParameter	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
uint	num_classes `[getset]`
	Specifies the number of classes that are actually predicted - required! More...

bool	share_location `[getset]`
	Specifies whether or not to sare the bounding box is shared among different classes (default = true). More...

int	background_label_id `[getset]`
	Specifies the background class. More...

NonMaximumSuppressionParameter	nms_param `[getset]`
	Specifies the parameter used for non maximum suppression. More...

SaveOutputParameter	save_output_param `[getset]`
	Specifies the parameter used for saving the detection results. More...

PriorBoxParameter.CodeType	code_type `[getset]`
	Specifies the coding method for the bbox. More...

bool	variance_encoded_in_target `[getset]`
	Specifies whether or not the variance is encoded in the target; otherwise we need to adjust the predicted offset accordingly. More...

int	keep_top_k `[getset]`
	Specifies the number of total bboxes to be kept per image after nms step, -1 means keeping all bboxes after nms step. More...

float?	confidence_threshold `[getset]`
	Specifies the threshold for deciding which detections to consider - only those which are larger than this threshold. More...

bool	visualize `[getset]`
	Specifies whether or not to visualize the detection results. More...

float?	visualize_threshold `[getset]`
	Specifies the theshold used to visualize detection results. More...

string	save_file `[getset]`
	When provided, specifies the outputs to the video file. 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 DetectionOutputLayer.

See also: SSD: Single Shot MultiBox Detector by Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg, 2016.; GitHub: SSD: Single Shot MultiBox Detector, by weiliu89/caffe, 2016

Definition at line 19 of file DetectionOutputParameter.cs.

Constructor & Destructor Documentation

◆ DetectionOutputParameter()

MyCaffe.param.ssd.DetectionOutputParameter.DetectionOutputParameter ( )

The constructor.

Definition at line 37 of file DetectionOutputParameter.cs.

Member Function Documentation

◆ Clone()

override LayerParameterBase MyCaffe.param.ssd.DetectionOutputParameter.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 207 of file DetectionOutputParameter.cs.

◆ Copy()

override void MyCaffe.param.ssd.DetectionOutputParameter.Copy ( LayerParameterBase src )

virtual

Copy on parameter to another.

Parameters

src	Specifies the parameter to copy.

Implements MyCaffe.param.LayerParameterBase.

Definition at line 185 of file DetectionOutputParameter.cs.

◆ FromProto()

static DetectionOutputParameter MyCaffe.param.ssd.DetectionOutputParameter.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 255 of file DetectionOutputParameter.cs.

◆ Load()

override object MyCaffe.param.ssd.DetectionOutputParameter.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 170 of file DetectionOutputParameter.cs.

◆ ToProto()

override RawProto MyCaffe.param.ssd.DetectionOutputParameter.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 219 of file DetectionOutputParameter.cs.

Property Documentation

◆ background_label_id

int MyCaffe.param.ssd.DetectionOutputParameter.background_label_id

getset

Specifies the background class.

If there is no background label this should be set to -1.

Definition at line 68 of file DetectionOutputParameter.cs.

◆ code_type

PriorBoxParameter.CodeType MyCaffe.param.ssd.DetectionOutputParameter.code_type

getset

Specifies the coding method for the bbox.

Definition at line 98 of file DetectionOutputParameter.cs.

◆ confidence_threshold

float? MyCaffe.param.ssd.DetectionOutputParameter.confidence_threshold

getset

Specifies the threshold for deciding which detections to consider - only those which are larger than this threshold.

Definition at line 128 of file DetectionOutputParameter.cs.

◆ keep_top_k

int MyCaffe.param.ssd.DetectionOutputParameter.keep_top_k

getset

Specifies the number of total bboxes to be kept per image after nms step, -1 means keeping all bboxes after nms step.

Definition at line 118 of file DetectionOutputParameter.cs.

◆ nms_param

NonMaximumSuppressionParameter MyCaffe.param.ssd.DetectionOutputParameter.nms_param

getset

Specifies the parameter used for non maximum suppression.

Definition at line 78 of file DetectionOutputParameter.cs.

◆ num_classes

uint MyCaffe.param.ssd.DetectionOutputParameter.num_classes

getset

Specifies the number of classes that are actually predicted - required!

Definition at line 45 of file DetectionOutputParameter.cs.

◆ save_file

string MyCaffe.param.ssd.DetectionOutputParameter.save_file

getset

When provided, specifies the outputs to the video file.

Definition at line 158 of file DetectionOutputParameter.cs.

◆ save_output_param

SaveOutputParameter MyCaffe.param.ssd.DetectionOutputParameter.save_output_param

getset

Specifies the parameter used for saving the detection results.

Definition at line 88 of file DetectionOutputParameter.cs.

◆ share_location

bool MyCaffe.param.ssd.DetectionOutputParameter.share_location

getset

Specifies whether or not to sare the bounding box is shared among different classes (default = true).

Definition at line 55 of file DetectionOutputParameter.cs.

◆ variance_encoded_in_target

bool MyCaffe.param.ssd.DetectionOutputParameter.variance_encoded_in_target

getset

Specifies whether or not the variance is encoded in the target; otherwise we need to adjust the predicted offset accordingly.

Definition at line 108 of file DetectionOutputParameter.cs.

◆ visualize

bool MyCaffe.param.ssd.DetectionOutputParameter.visualize

getset

Specifies whether or not to visualize the detection results.

Definition at line 138 of file DetectionOutputParameter.cs.

◆ visualize_threshold

float? MyCaffe.param.ssd.DetectionOutputParameter.visualize_threshold

getset

Specifies the theshold used to visualize detection results.

Definition at line 148 of file DetectionOutputParameter.cs.

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

C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe/param.ssd/DetectionOutputParameter.cs

Public Member Functions

Static Public Member Functions

Properties

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ DetectionOutputParameter()

Member Function Documentation

◆ Clone()

◆ Copy()

◆ FromProto()

◆ Load()

◆ ToProto()

Property Documentation

◆ background_label_id

◆ code_type

◆ confidence_threshold

◆ keep_top_k

◆ nms_param

◆ num_classes

◆ save_file

◆ save_output_param

◆ share_location

◆ variance_encoded_in_target

◆ visualize

◆ visualize_threshold