cv::dnn::DetectionModel クラス

This class represents high-level API for object detection networks. [詳解]

#include <dnn.hpp>

cv::dnn::Modelを継承しています。

公開メンバ関数
CV_WRAP	DetectionModel (const String &model, const String &config="")
	Create detection model from network represented in one of the supported formats. An order of model and config arguments does not matter. [詳解]
CV_WRAP	DetectionModel (const Net &network)
	Create model from deep learning network. [詳解]
CV_WRAP DetectionModel &	setNmsAcrossClasses (bool value)
	nmsAcrossClasses defaults to false, such that when non max suppression is used during the detect() function, it will do so per-class. This function allows you to toggle this behaviour. [詳解]
CV_WRAP bool	getNmsAcrossClasses ()
	Getter for nmsAcrossClasses. This variable defaults to false, such that when non max suppression is used during the detect() function, it will do so only per-class
CV_WRAP void	detect (InputArray frame, CV_OUT std::vector< int > &classIds, CV_OUT std::vector< float > &confidences, CV_OUT std::vector< Rect > &boxes, float confThreshold=0.5f, float nmsThreshold=0.0f)
	Given the input frame, create input blob, run net and return result detections. [詳解]
基底クラス cv::dnn::Model に属する継承公開メンバ関数
	Model (const Model &)=default
	Model (Model &&)=default
Model &	operator= (const Model &)=default
Model &	operator= (Model &&)=default
CV_WRAP	Model (const String &model, const String &config="")
	Create model from deep learning network represented in one of the supported formats. An order of model and config arguments does not matter. [詳解]
CV_WRAP	Model (const Net &network)
	Create model from deep learning network. [詳解]
CV_WRAP Model &	setInputSize (const Size &size)
	Set input size for frame. [詳解]
CV_WRAP Model &	setInputSize (int width, int height)
CV_WRAP Model &	setInputMean (const Scalar &mean)
	Set mean value for frame. [詳解]
CV_WRAP Model &	setInputScale (double scale)
	Set scalefactor value for frame. [詳解]
CV_WRAP Model &	setInputCrop (bool crop)
	Set flag crop for frame. [詳解]
CV_WRAP Model &	setInputSwapRB (bool swapRB)
	Set flag swapRB for frame. [詳解]
CV_WRAP void	setInputParams (double scale=1.0, const Size &size=Size(), const Scalar &mean=Scalar(), bool swapRB=false, bool crop=false)
	Set preprocessing parameters for frame. [詳解]
CV_WRAP void	predict (InputArray frame, OutputArrayOfArrays outs) const
	Given the input frame, create input blob, run net and return the output blobs. [詳解]
CV_WRAP Model &	setPreferableBackend (dnn::Backend backendId)
CV_WRAP Model &	setPreferableTarget (dnn::Target targetId)
CV_DEPRECATED_EXTERNAL	operator Net & () const
Net &	getNetwork_ () const
Net &	getNetwork_ ()
Impl *	getImpl () const
Impl &	getImplRef () const

その他の継承メンバ
基底クラス cv::dnn::Model に属する継承限定公開変数類
Ptr< Impl >	impl

詳解

This class represents high-level API for object detection networks.

DetectionModel allows to set params for preprocessing input image. DetectionModel creates net from file with trained weights and config, sets preprocessing input, runs forward pass and return result detections. For DetectionModel SSD, Faster R-CNN, YOLO topologies are supported.

構築子と解体子

DetectionModel() [1/2]

CV_WRAP cv::dnn::DetectionModel::DetectionModel	(	const String &	model,
		const String &	config = ""
	)

Create detection model from network represented in one of the supported formats. An order of model and config arguments does not matter.

引数

[in]	model	Binary file contains trained weights.
[in]	config	Text file contains network configuration.

DetectionModel() [2/2]

CV_WRAP cv::dnn::DetectionModel::DetectionModel

(

const Net &

network

)

Create model from deep learning network.

引数

[in]

network

Net object.

関数詳解

detect()

CV_WRAP void cv::dnn::DetectionModel::detect	(	InputArray	frame,
		CV_OUT std::vector< int > &	classIds,
		CV_OUT std::vector< float > &	confidences,
		CV_OUT std::vector< Rect > &	boxes,
		float	confThreshold = 0.5f,
		float	nmsThreshold = 0.0f
	)

Given the input frame, create input blob, run net and return result detections.

引数

[in]	frame	The input image.
[out]	classIds	Class indexes in result detection.
[out]	confidences	A set of corresponding confidences.
[out]	boxes	A set of bounding boxes.
[in]	confThreshold	A threshold used to filter boxes by confidences.
[in]	nmsThreshold	A threshold used in non maximum suppression.

setNmsAcrossClasses()

CV_WRAP DetectionModel & cv::dnn::DetectionModel::setNmsAcrossClasses

(

bool

value

)

nmsAcrossClasses defaults to false, such that when non max suppression is used during the detect() function, it will do so per-class. This function allows you to toggle this behaviour.

引数

[in]

value

The new value for nmsAcrossClasses

---

このクラス詳解は次のファイルから抽出されました:

• dnn/dnn.hpp