org.opencv.dnn

Class Model

java.lang.Object

org.opencv.dnn.Model

Direct Known Subclasses:

ClassificationModel, DetectionModel, KeypointsModel, SegmentationModel, TextDetectionModel, TextRecognitionModel

public class Model
extends Object

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.

Field Summary

Fields

Modifier and Type	Field and Description
protected long	nativeObj

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	Model(long addr)
	Model(Net network) Create model from deep learning network.
	Model(String model) Create model from deep learning network represented in one of the supported formats.
	Model(String model, String config) Create model from deep learning network represented in one of the supported formats.

Method Summary

Modifier and Type	Method and Description
static Model	__fromPtr__(long addr)
Model	enableWinograd(boolean useWinograd)
protected void	finalize()
long	getNativeObjAddr()
void	predict(Mat frame, List<Mat> outs) Given the input frame, create input blob, run net and return the output blobs.
Model	setInputCrop(boolean crop) Set flag crop for frame.
Model	setInputMean(Scalar mean) Set mean value for frame.
void	setInputParams() Set preprocessing parameters for frame.
void	setInputParams(double scale) Set preprocessing parameters for frame.
void	setInputParams(double scale, Size size) Set preprocessing parameters for frame.
void	setInputParams(double scale, Size size, Scalar mean) Set preprocessing parameters for frame.
void	setInputParams(double scale, Size size, Scalar mean, boolean swapRB) Set preprocessing parameters for frame.
void	setInputParams(double scale, Size size, Scalar mean, boolean swapRB, boolean crop) Set preprocessing parameters for frame.
Model	setInputScale(Scalar scale) Set scalefactor value for frame.
Model	setInputSize(int width, int height)
Model	setInputSize(Size size) Set input size for frame.
Model	setInputSwapRB(boolean swapRB) Set flag swapRB for frame.
Model	setOutputNames(List<String> outNames) Set output names for frame.
Model	setPreferableBackend(int backendId)
Model	setPreferableTarget(int targetId)

Methods inherited from class java.lang.Object

clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

nativeObj

protected final long nativeObj

Constructor Detail

Model

protected Model(long addr)

Model

public Model(String model,
             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.

Parameters:

model - Binary file contains trained weights.

config - Text file contains network configuration.

Model

public Model(String model)

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

Parameters:

model - Binary file contains trained weights.

Model

public Model(Net network)

Create model from deep learning network.

Parameters:

network - Net object.

Method Detail

getNativeObjAddr

public long getNativeObjAddr()

__fromPtr__

public static Model __fromPtr__(long addr)

setInputSize

public Model setInputSize(Size size)

Set input size for frame.

Parameters:

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

Returns:

automatically generated

setInputSize

public Model setInputSize(int width,
                          int height)

Parameters:

width - New input width.

height - New input height.

Returns:

automatically generated

setInputMean

public Model setInputMean(Scalar mean)

Set mean value for frame.

Parameters:

mean - Scalar with mean values which are subtracted from channels.

Returns:

automatically generated

setInputScale

public Model setInputScale(Scalar scale)

Set scalefactor value for frame.

Parameters:

scale - Multiplier for frame values.

Returns:

automatically generated

setInputCrop

public Model setInputCrop(boolean crop)

Set flag crop for frame.

Parameters:

crop - Flag which indicates whether image will be cropped after resize or not.

Returns:

automatically generated

setInputSwapRB

public Model setInputSwapRB(boolean swapRB)

Set flag swapRB for frame.

Parameters:

swapRB - Flag which indicates that swap first and last channels.

Returns:

automatically generated

setOutputNames

public Model setOutputNames(List<String> outNames)

Set output names for frame.

Parameters:

outNames - Names for output layers.

Returns:

automatically generated

setInputParams

public void setInputParams(double scale,
                           Size size,
                           Scalar mean,
                           boolean swapRB,
                           boolean crop)

Set preprocessing parameters for frame.

Parameters:

size - New input size.

mean - Scalar with mean values which are subtracted from channels.

scale - Multiplier for frame values.

swapRB - Flag which indicates that swap first and last channels.

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) )

setInputParams

public void setInputParams(double scale,
                           Size size,
                           Scalar mean,
                           boolean swapRB)

Set preprocessing parameters for frame.

Parameters:

size - New input size.

mean - Scalar with mean values which are subtracted from channels.

scale - Multiplier for frame values.

swapRB - Flag which indicates that swap first and last channels. blob(n, c, y, x) = scale * resize( frame(y, x, c) ) - mean(c) )

setInputParams

public void setInputParams(double scale,
                           Size size,
                           Scalar mean)

Set preprocessing parameters for frame.

Parameters:

size - New input size.

mean - Scalar with mean values which are subtracted from channels.

scale - Multiplier for frame values. blob(n, c, y, x) = scale * resize( frame(y, x, c) ) - mean(c) )

setInputParams

public void setInputParams(double scale,
                           Size size)

Set preprocessing parameters for frame.

Parameters:

size - New input size.

scale - Multiplier for frame values. blob(n, c, y, x) = scale * resize( frame(y, x, c) ) - mean(c) )

setInputParams

public void setInputParams(double scale)

Set preprocessing parameters for frame.

Parameters:

scale - Multiplier for frame values. blob(n, c, y, x) = scale * resize( frame(y, x, c) ) - mean(c) )

setInputParams

public void setInputParams()

Set preprocessing parameters for frame. blob(n, c, y, x) = scale * resize( frame(y, x, c) ) - mean(c) )

predict

public void predict(Mat frame,
                    List<Mat> outs)

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

Parameters:

outs - Allocated output blobs, which will store results of the computation.

frame - automatically generated

setPreferableBackend

public Model setPreferableBackend(int backendId)

setPreferableTarget

public Model setPreferableTarget(int targetId)

enableWinograd

public Model enableWinograd(boolean useWinograd)

finalize

protected void finalize()
                 throws Throwable

Overrides:

finalize in class Object

Throws:

Throwable