DetectionNetwork, base for different network specializations. More...

#include <DetectionNetwork.hpp>

Inheritance diagram for dai::node::DetectionNetwork:

Public Member Functions
float	getConfidenceThreshold () const

void	setConfidenceThreshold (float thresh)

Public Member Functions inherited from dai::NodeCRTP< NeuralNetwork, DetectionNetwork, DetectionNetworkProperties >
std::unique_ptr< Node >	clone () const override

const char *	getName () const override

Public Attributes
Output	out {*this, "out", Output::Type::MSender, {{DatatypeEnum::ImgDetections, false}}}

Output	outNetwork {*this, "outNetwork", Output::Type::MSender, {{DatatypeEnum::NNData, false}}}

Public Attributes inherited from dai::NodeCRTP< NeuralNetwork, DetectionNetwork, DetectionNetworkProperties >
Properties &	properties
	Underlying properties. More...

Static Public Attributes
constexpr static const char *	NAME = "DetectionNetwork"

Protected Member Functions
	DetectionNetwork (const std::shared_ptr< PipelineImpl > &par, int64_t nodeId)

	DetectionNetwork (const std::shared_ptr< PipelineImpl > &par, int64_t nodeId, std::unique_ptr< Properties > props)

Additional Inherited Members
Public Types inherited from dai::NodeCRTP< NeuralNetwork, DetectionNetwork, DetectionNetworkProperties >
using	Properties = DetectionNetworkProperties

Detailed Description

DetectionNetwork, base for different network specializations.

Definition at line 20 of file DetectionNetwork.hpp.

Constructor & Destructor Documentation

◆ DetectionNetwork() [1/2]

DetectionNetwork::DetectionNetwork	(	const std::shared_ptr< PipelineImpl > &	par,
		int64_t	nodeId
	)

protected

Definition at line 14 of file DetectionNetwork.cpp.

◆ DetectionNetwork() [2/2]

DetectionNetwork::DetectionNetwork	(	const std::shared_ptr< PipelineImpl > &	par,
		int64_t	nodeId,
		std::unique_ptr< Properties >	props
	)

protected

Definition at line 15 of file DetectionNetwork.cpp.

Member Function Documentation

◆ getConfidenceThreshold()

float DetectionNetwork::getConfidenceThreshold ( ) const

Retrieves threshold at which to filter the rest of the detections.

Returns: Detection confidence

Definition at line 28 of file DetectionNetwork.cpp.

◆ setConfidenceThreshold()

void DetectionNetwork::setConfidenceThreshold ( float thresh )

Specifies confidence threshold at which to filter the rest of the detections.

Parameters

thresh Detection confidence must be greater than specified threshold to be added to the list

Definition at line 24 of file DetectionNetwork.cpp.

Member Data Documentation

◆ NAME

constexpr static const char* dai::node::DetectionNetwork::NAME = "DetectionNetwork"

staticconstexpr

Definition at line 22 of file DetectionNetwork.hpp.

◆ out

Output dai::node::DetectionNetwork::out {*this, "out", Output::Type::MSender, {{DatatypeEnum::ImgDetections, false}}}

Outputs ImgDetections message that carries parsed detection results. Overrides NeuralNetwork 'out' with ImgDetections output message type.

Definition at line 33 of file DetectionNetwork.hpp.

◆ outNetwork

Output dai::node::DetectionNetwork::outNetwork {*this, "outNetwork", Output::Type::MSender, {{DatatypeEnum::NNData, false}}}

Outputs unparsed inference results.

Definition at line 38 of file DetectionNetwork.hpp.

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

Public Member Functions

Public Attributes

Static Public Attributes

Protected Member Functions

Additional Inherited Members