This class is presented high-level API for neural networks. More...

#include <opencv2/dnn/dnn.hpp>

Collaboration diagram for cv::dnn::Model:

Public Member Functions
	Model ()

	Model (const Model &)=default

	Model (const Net &network)
	Create model from deep learning network.

	Model (CV_WRAP_FILE_PATH const String &model, CV_WRAP_FILE_PATH 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.

	Model (Model &&)=default

Model &	enableWinograd (bool useWinograd)

Impl *	getImpl () const

Impl &	getImplRef () const

Net &	getNetwork_ ()

Net &	getNetwork_ () const

	operator Net & () const

Model &	operator= (const Model &)=default

Model &	operator= (Model &&)=default

void	predict (InputArray frame, OutputArrayOfArrays outs) const
	Given the `input` frame, create input blob, run net and return the output `blobs`.

Model &	setInputCrop (bool crop)
	Set flag crop for frame.

Model &	setInputMean (const Scalar &mean)
	Set mean value for frame.

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.

Model &	setInputScale (const Scalar &scale)
	Set scalefactor value for frame.

Model &	setInputSize (const Size &size)
	Set input size for frame.

Model &	setInputSize (int width, int height)

Model &	setInputSwapRB (bool swapRB)
	Set flag swapRB for frame.

Model &	setOutputNames (const std::vector< String > &outNames)
	Set output names for frame.

Model &	setPreferableBackend (dnn::Backend backendId)

Model &	setPreferableTarget (dnn::Target targetId)

Protected Attributes
Ptr< Impl >	impl

Detailed Description

This class is presented high-level API for neural networks.

Model allows to set params for preprocessing input image. Model creates net from file with trained weights and config, sets preprocessing input and runs forward pass.

Constructor & Destructor Documentation

◆ Model() [1/5]

cv::dnn::Model::Model ( )

Python:
	cv.dnn.Model(	model[, config]	) ->	<dnn_Model object>
	cv.dnn.Model(	network	) ->	<dnn_Model object>

◆ Model() [2/5]

cv::dnn::Model::Model ( const Model & )

default

Python:
	cv.dnn.Model(	model[, config]	) ->	<dnn_Model object>
	cv.dnn.Model(	network	) ->	<dnn_Model object>

◆ Model() [3/5]

cv::dnn::Model::Model ( Model && )

default

Python:
	cv.dnn.Model(	model[, config]	) ->	<dnn_Model object>
	cv.dnn.Model(	network	) ->	<dnn_Model object>

◆ Model() [4/5]

cv::dnn::Model::Model	(	CV_WRAP_FILE_PATH const String &	model,
		CV_WRAP_FILE_PATH const String &	config = `""`
	)

Python:
	cv.dnn.Model(	model[, config]	) ->	<dnn_Model object>
	cv.dnn.Model(	network	) ->	<dnn_Model object>

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

Parameters

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

◆ Model() [5/5]

cv::dnn::Model::Model ( const Net & network )

Python:
	cv.dnn.Model(	model[, config]	) ->	<dnn_Model object>
	cv.dnn.Model(	network	) ->	<dnn_Model object>

Create model from deep learning network.

Parameters

[in] network Net object.

Member Function Documentation

◆ enableWinograd()

Model & cv::dnn::Model::enableWinograd ( bool useWinograd )

Python:
	cv.dnn.Model.enableWinograd(	useWinograd	) ->	retval

See also: Net::enableWinograd

◆ getImpl()

Impl * cv::dnn::Model::getImpl ( ) const

inline

◆ getImplRef()

Impl & cv::dnn::Model::getImplRef ( ) const

inline

◆ getNetwork_() [1/2]

Net & cv::dnn::Model::getNetwork_ ( )

inline

Here is the call graph for this function:

◆ getNetwork_() [2/2]

Net & cv::dnn::Model::getNetwork_ ( ) const

◆ operator Net &()

cv::dnn::Model::operator Net & ( ) const

inline

◆ operator=() [1/2]

Model & cv::dnn::Model::operator= ( const Model & )

default

◆ operator=() [2/2]

Model & cv::dnn::Model::operator= ( Model && )

default

◆ predict()

void cv::dnn::Model::predict	(	InputArray	frame,
		OutputArrayOfArrays	outs
	)		const

Python:
	cv.dnn.Model.predict(	frame[, outs]	) ->	outs

Given the input frame, create input blob, run net and return the output blobs.

Parameters

[in]	frame	The input image.
[out]	outs	Allocated output blobs, which will store results of the computation.

◆ setInputCrop()

Model & cv::dnn::Model::setInputCrop ( bool crop )

Python:
	cv.dnn.Model.setInputCrop(	crop	) ->	retval

Set flag crop for frame.

Parameters

[in] crop Flag which indicates whether image will be cropped after resize or not.

◆ setInputMean()

Model & cv::dnn::Model::setInputMean ( const Scalar & mean )

Python:
	cv.dnn.Model.setInputMean(	mean	) ->	retval

Set mean value for frame.

Parameters

[in] mean Scalar with mean values which are subtracted from channels.

◆ setInputParams()

void cv::dnn::Model::setInputParams	(	double	scale = `1.0`,
		const Size &	size = `Size()`,
		const Scalar &	mean = `Scalar()`,
		bool	swapRB = `false`,
		bool	crop = `false`
	)

Python:
	cv.dnn.Model.setInputParams(	[, scale[, size[, mean[, swapRB[, crop]]]]]	) ->	None

Set preprocessing parameters for frame.

Parameters

[in]	size	New input size.
[in]	mean	Scalar with mean values which are subtracted from channels.
[in]	scale	Multiplier for frame values.
[in]	swapRB	Flag which indicates that swap first and last channels.
[in]	crop	Flag which indicates whether image will be cropped after resize or not. blob(n, c, y, x) = scale * resize( frame(y, x, c) ) - mean(c) )

◆ setInputScale()

Model & cv::dnn::Model::setInputScale ( const Scalar & scale )

Python:
	cv.dnn.Model.setInputScale(	scale	) ->	retval

Set scalefactor value for frame.

Parameters

[in] scale Multiplier for frame values.

◆ setInputSize() [1/2]

Model & cv::dnn::Model::setInputSize ( const Size & size )

Python:
	cv.dnn.Model.setInputSize(	size	) ->	retval
	cv.dnn.Model.setInputSize(	width, height	) ->	retval

Set input size for frame.

Parameters

[in] size New input size.

Note: If shape of the new blob less than 0, then frame size not change.

◆ setInputSize() [2/2]

Model & cv::dnn::Model::setInputSize	(	int	width,
		int	height
	)

inline

Python:
	cv.dnn.Model.setInputSize(	size	) ->	retval
	cv.dnn.Model.setInputSize(	width, height	) ->	retval

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

[in]	width	New input width.
[in]	height	New input height.

Here is the call graph for this function:

◆ setInputSwapRB()

Model & cv::dnn::Model::setInputSwapRB ( bool swapRB )

Python:
	cv.dnn.Model.setInputSwapRB(	swapRB	) ->	retval

Set flag swapRB for frame.

Parameters

[in] swapRB Flag which indicates that swap first and last channels.

◆ setOutputNames()

Model & cv::dnn::Model::setOutputNames ( const std::vector< String > & outNames )

Python:
	cv.dnn.Model.setOutputNames(	outNames	) ->	retval

Set output names for frame.

Parameters

[in] outNames Names for output layers.

◆ setPreferableBackend()

Model & cv::dnn::Model::setPreferableBackend ( dnn::Backend backendId )

Python:
	cv.dnn.Model.setPreferableBackend(	backendId	) ->	retval

See also: Net::setPreferableBackend

◆ setPreferableTarget()

Model & cv::dnn::Model::setPreferableTarget ( dnn::Target targetId )

Python:
	cv.dnn.Model.setPreferableTarget(	targetId	) ->	retval

See also: Net::setPreferableTarget

Member Data Documentation

◆ impl

Ptr<Impl> cv::dnn::Model::impl

protected

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

opencv2/dnn/dnn.hpp

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ Model() [1/5]

◆ Model() [2/5]

◆ Model() [3/5]

◆ Model() [4/5]

◆ Model() [5/5]

Member Function Documentation

◆ enableWinograd()

◆ getImpl()

◆ getImplRef()

◆ getNetwork_() [1/2]

◆ getNetwork_() [2/2]

◆ operator Net &()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ predict()

◆ setInputCrop()

◆ setInputMean()

◆ setInputParams()

◆ setInputScale()

◆ setInputSize() [1/2]

◆ setInputSize() [2/2]

◆ setInputSwapRB()

◆ setOutputNames()

◆ setPreferableBackend()

◆ setPreferableTarget()

Member Data Documentation

◆ impl