org.bytedeco.opencv.opencv_dnn

Class Model

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.opencv.opencv_dnn.Net

org.bytedeco.opencv.opencv_dnn.Model

All Implemented Interfaces:

AutoCloseable

Direct Known Subclasses:

ClassificationModel, DetectionModel, KeypointsModel, SegmentationModel

@Namespace(value="cv::dnn")
 @NoOffset
 @Properties(inherit=opencv_dnn.class)
public class Model
extends Net

\brief 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.

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
Model() \brief Default constructor.
Model(BytePointer model)
Model(BytePointer model, BytePointer config) \brief Create model from deep learning network represented in one of the supported formats.
Model(long size) Native array allocator.
Model(Net network) \brief Create model from deep learning network.
Model(Pointer p) Pointer cast constructor.
Model(String model)
Model(String model, String config)

Method Summary

Modifier and Type	Method and Description
Model	position(long position)
void	predict(GpuMat frame, GpuMatVector outs)
void	predict(GpuMat frame, MatVector outs)
void	predict(GpuMat frame, UMatVector outs)
void	predict(Mat frame, GpuMatVector outs)
void	predict(Mat frame, MatVector outs) \brief Given the \p input frame, create input blob, run net and return the output \p blobs.
void	predict(Mat frame, UMatVector outs)
void	predict(UMat frame, GpuMatVector outs)
void	predict(UMat frame, MatVector outs)
void	predict(UMat frame, UMatVector outs)
Model	setInputCrop(boolean crop) \brief Set flag crop for frame.
Model	setInputMean(Scalar mean) \brief Set mean value for frame.
void	setInputParams()
void	setInputParams(double scale, Size size, Scalar mean, boolean swapRB, boolean crop) \brief Set preprocessing parameters for frame.
Model	setInputScale(double scale) \brief Set scalefactor value for frame.
Model	setInputSize(int width, int height) \brief Set input size for frame.
Model	setInputSize(Size size) \brief Set input size for frame.
Model	setInputSwapRB(boolean swapRB) \brief Set flag swapRB for frame.

Methods inherited from class org.bytedeco.opencv.opencv_dnn.Net

addLayer, addLayer, addLayerToPrev, addLayerToPrev, connect, connect, connect, dump, dumpToFile, dumpToFile, empty, enableFusion, forward, forward, forward, forward, forward, forward, forward, forward, forward, forward, forward, forward, forward, forward, forward, forwardAndRetrieve, forwardAsync, forwardAsync, forwardAsync, getFLOPS, getFLOPS, getFLOPS, getFLOPS, getLayer, getLayerId, getLayerId, getLayerNames, getLayersCount, getLayersCount, getLayerShapes, getLayerShapes, getLayersShapes, getLayersShapes, getLayersShapes, getLayersShapes, getLayersShapes, getLayersShapes, getLayerTypes, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getParam, getParam, getPerfProfile, getPerfProfile, getPerfProfile, getUnconnectedOutLayers, getUnconnectedOutLayersNames, readFromModelOptimizer, readFromModelOptimizer, readFromModelOptimizer, readFromModelOptimizer, readFromModelOptimizer, readFromModelOptimizer, readFromModelOptimizer, setHalideScheduler, setHalideScheduler, setInput, setInput, setInput, setInput, setInput, setInput, setInput, setInput, setInput, setInputShape, setInputShape, setInputsNames, setParam, setPreferableBackend, setPreferableTarget

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, hashCode, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, parseBytes, physicalBytes, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, toString, totalBytes, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

Model

public Model(Pointer p)

Pointer cast constructor. Invokes Pointer.Pointer(Pointer).

Model

public Model(long size)

Native array allocator. Access with Pointer.position(long).

Model

public Model()

\brief Default constructor.

Model

public Model(@opencv_core.Str
             BytePointer model,
             @opencv_core.Str
             BytePointer config)

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

Parameters:

model - [in] Binary file contains trained weights.

config - [in] Text file contains network configuration.

Model

public Model(@opencv_core.Str
             BytePointer model)

Model

public Model(@opencv_core.Str
             String model,
             @opencv_core.Str
             String config)

Model

public Model(@opencv_core.Str
             String model)

Model

public Model(@Const @ByRef
             Net network)

\brief Create model from deep learning network.

Parameters:

network - [in] Net object.

Method Detail

position

public Model position(long position)

Overrides:

position in class Net

setInputSize

@ByRef
public Model setInputSize(@Const @ByRef
                                 Size size)

\brief Set input size for frame.

Parameters:

size - [in] New input size. \note If shape of the new blob less than 0, then frame size not change.

setInputSize

@ByRef
public Model setInputSize(int width,
                                 int height)

\brief Set input size for frame.

Parameters:

width - [in] New input width.

height - [in] New input height. \note If shape of the new blob less than 0, then frame size not change.

setInputMean

@ByRef
public Model setInputMean(@Const @ByRef
                                 Scalar mean)

\brief Set mean value for frame.

Parameters:

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

setInputScale

@ByRef
public Model setInputScale(double scale)

\brief Set scalefactor value for frame.

Parameters:

scale - [in] Multiplier for frame values.

setInputCrop

@ByRef
public Model setInputCrop(@Cast(value="bool")
                                 boolean crop)

\brief Set flag crop for frame.

Parameters:

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

setInputSwapRB

@ByRef
public Model setInputSwapRB(@Cast(value="bool")
                                   boolean swapRB)

\brief Set flag swapRB for frame.

Parameters:

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

setInputParams

public void setInputParams(double scale,
                           @Const @ByRef(nullValue="cv::Size()")
                           Size size,
                           @Const @ByRef(nullValue="cv::Scalar()")
                           Scalar mean,
                           @Cast(value="bool")
                           boolean swapRB,
                           @Cast(value="bool")
                           boolean crop)

\brief Set preprocessing parameters for frame.

Parameters:

size - [in] New input size.

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

scale - [in] Multiplier for frame values.

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

crop - [in] 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()

predict

public void predict(@ByVal
                    Mat frame,
                    @ByVal
                    MatVector outs)

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

Parameters:

frame - [in] The input image.

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

predict

public void predict(@ByVal
                    Mat frame,
                    @ByVal
                    UMatVector outs)

predict

public void predict(@ByVal
                    Mat frame,
                    @ByVal
                    GpuMatVector outs)

predict

public void predict(@ByVal
                    UMat frame,
                    @ByVal
                    MatVector outs)

predict

public void predict(@ByVal
                    UMat frame,
                    @ByVal
                    UMatVector outs)

predict

public void predict(@ByVal
                    UMat frame,
                    @ByVal
                    GpuMatVector outs)

predict

public void predict(@ByVal
                    GpuMat frame,
                    @ByVal
                    MatVector outs)

predict

public void predict(@ByVal
                    GpuMat frame,
                    @ByVal
                    UMatVector outs)

predict

public void predict(@ByVal
                    GpuMat frame,
                    @ByVal
                    GpuMatVector outs)