org.bytedeco.opencv.opencv_dnn

Class Net

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.opencv.opencv_dnn.Net

All Implemented Interfaces:

AutoCloseable

Direct Known Subclasses:

Model

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

\brief This class allows to create and manipulate comprehensive artificial neural networks. Neural network is presented as directed acyclic graph (DAG), where vertices are Layer instances, and edges specify relationships between layers inputs and outputs. Each network layer has unique integer id and unique string name inside its network. LayerId can store either layer name or layer id. This class supports reference counting of its instances, i. e. copies point to the same instance.

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
Net() Default constructor.
Net(long size) Native array allocator.
Net(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
int	addLayer(BytePointer name, BytePointer type, LayerParams params) \brief Adds new layer to the net.
int	addLayer(String name, String type, LayerParams params)
int	addLayerToPrev(BytePointer name, BytePointer type, LayerParams params) \brief Adds new layer and connects its first input to the first output of previously added layer.
int	addLayerToPrev(String name, String type, LayerParams params)
void	connect(BytePointer outPin, BytePointer inpPin) \brief Connects output of the first layer to input of the second layer.
void	connect(int outLayerId, int outNum, int inpLayerId, int inpNum) \brief Connects #\p outNum output of the first layer to #\p inNum input of the second layer.
void	connect(String outPin, String inpPin)
BytePointer	dump() \brief Dump net to String
void	dumpToFile(BytePointer path) \brief Dump net structure, hyperparameters, backend, target and fusion to dot file
void	dumpToFile(String path)
boolean	empty() Returns true if there are no layers in the network.
void	enableFusion(boolean fusion) \brief Enables or disables layer fusion in the network.
Mat	forward()
Mat	forward(BytePointer outputName) \brief Runs forward pass to compute output of layer with name \p outputName.
void	forward(GpuMatVector outputBlobs)
void	forward(GpuMatVector outputBlobs, BytePointer outputName)
void	forward(GpuMatVector outputBlobs, String outputName)
void	forward(GpuMatVector outputBlobs, StringVector outBlobNames)
void	forward(MatVector outputBlobs)
void	forward(MatVector outputBlobs, BytePointer outputName) \brief Runs forward pass to compute output of layer with name \p outputName.
void	forward(MatVector outputBlobs, String outputName)
void	forward(MatVector outputBlobs, StringVector outBlobNames) \brief Runs forward pass to compute outputs of layers listed in \p outBlobNames.
Mat	forward(String outputName)
void	forward(UMatVector outputBlobs)
void	forward(UMatVector outputBlobs, BytePointer outputName)
void	forward(UMatVector outputBlobs, String outputName)
void	forward(UMatVector outputBlobs, StringVector outBlobNames)
void	forwardAndRetrieve(MatVectorVector outputBlobs, StringVector outBlobNames) \brief Runs forward pass to compute outputs of layers listed in \p outBlobNames.
AsyncArray	forwardAsync()
AsyncArray	forwardAsync(BytePointer outputName) \brief Runs forward pass to compute output of layer with name \p outputName.
AsyncArray	forwardAsync(String outputName)
long	getFLOPS(int layerId, IntPointer netInputShape) \overload
long	getFLOPS(int layerId, MatShapeVector netInputShapes) \overload
long	getFLOPS(IntPointer netInputShape) \overload
long	getFLOPS(MatShapeVector netInputShapes) \brief Computes FLOP for whole loaded model with specified input shapes.
Layer	getLayer(DictValue layerId) \brief Returns pointer to layer with specified id or name which the network use.
int	getLayerId(BytePointer layer) \brief Converts string name of the layer to the integer identifier.
int	getLayerId(String layer)
StringVector	getLayerNames()
int	getLayersCount(BytePointer layerType) \brief Returns count of layers of specified type.
int	getLayersCount(String layerType)
void	getLayerShapes(IntPointer netInputShape, int layerId, MatShapeVector inLayerShapes, MatShapeVector outLayerShapes) \brief Returns input and output shapes for layer with specified id in loaded model; preliminary inferencing isn't necessary.
void	getLayerShapes(MatShapeVector netInputShapes, int layerId, MatShapeVector inLayerShapes, MatShapeVector outLayerShapes) \overload
void	getLayersShapes(IntPointer netInputShape, int[] layersIds, MatShapeVectorVector inLayersShapes, MatShapeVectorVector outLayersShapes)
void	getLayersShapes(IntPointer netInputShape, IntBuffer layersIds, MatShapeVectorVector inLayersShapes, MatShapeVectorVector outLayersShapes)
void	getLayersShapes(IntPointer netInputShape, IntPointer layersIds, MatShapeVectorVector inLayersShapes, MatShapeVectorVector outLayersShapes) \overload
void	getLayersShapes(MatShapeVector netInputShapes, int[] layersIds, MatShapeVectorVector inLayersShapes, MatShapeVectorVector outLayersShapes)
void	getLayersShapes(MatShapeVector netInputShapes, IntBuffer layersIds, MatShapeVectorVector inLayersShapes, MatShapeVectorVector outLayersShapes)
void	getLayersShapes(MatShapeVector netInputShapes, IntPointer layersIds, MatShapeVectorVector inLayersShapes, MatShapeVectorVector outLayersShapes) \brief Returns input and output shapes for all layers in loaded model; preliminary inferencing isn't necessary.
void	getLayerTypes(StringVector layersTypes) \brief Returns list of types for layer used in model.
void	getMemoryConsumption(int layerId, IntPointer netInputShape, SizeTPointer weights, SizeTPointer blobs) \overload
void	getMemoryConsumption(int layerId, MatShapeVector netInputShapes, SizeTPointer weights, SizeTPointer blobs) \overload
void	getMemoryConsumption(IntPointer netInputShape, int[] layerIds, SizeTPointer weights, SizeTPointer blobs)
void	getMemoryConsumption(IntPointer netInputShape, IntBuffer layerIds, SizeTPointer weights, SizeTPointer blobs)
void	getMemoryConsumption(IntPointer netInputShape, IntPointer layerIds, SizeTPointer weights, SizeTPointer blobs) \overload
void	getMemoryConsumption(IntPointer netInputShape, SizeTPointer weights, SizeTPointer blobs) \overload
void	getMemoryConsumption(MatShapeVector netInputShapes, int[] layerIds, SizeTPointer weights, SizeTPointer blobs)
void	getMemoryConsumption(MatShapeVector netInputShapes, IntBuffer layerIds, SizeTPointer weights, SizeTPointer blobs)
void	getMemoryConsumption(MatShapeVector netInputShapes, IntPointer layerIds, SizeTPointer weights, SizeTPointer blobs) \brief Computes bytes number which are required to store all weights and intermediate blobs for each layer.
void	getMemoryConsumption(MatShapeVector netInputShapes, SizeTPointer weights, SizeTPointer blobs) \brief Computes bytes number which are required to store all weights and intermediate blobs for model.
Mat	getParam(DictValue layer)
Mat	getParam(DictValue layer, int numParam) \brief Returns parameter blob of the layer.
long	getPerfProfile(double[] timings)
long	getPerfProfile(DoubleBuffer timings)
long	getPerfProfile(DoublePointer timings) \brief Returns overall time for inference and timings (in ticks) for layers.
IntPointer	getUnconnectedOutLayers() \brief Returns indexes of layers with unconnected outputs.
StringVector	getUnconnectedOutLayersNames() \brief Returns names of layers with unconnected outputs.
Net	position(long position)
static Net	readFromModelOptimizer(byte[] bufferModelConfig, byte[] bufferWeights)
static Net	readFromModelOptimizer(byte[] bufferModelConfigPtr, long bufferModelConfigSize, byte[] bufferWeightsPtr, long bufferWeightsSize)
static Net	readFromModelOptimizer(ByteBuffer bufferModelConfig, ByteBuffer bufferWeights) \brief Create a network from Intel's Model Optimizer in-memory buffers with intermediate representation (IR).
static Net	readFromModelOptimizer(ByteBuffer bufferModelConfigPtr, long bufferModelConfigSize, ByteBuffer bufferWeightsPtr, long bufferWeightsSize)
static Net	readFromModelOptimizer(BytePointer xml, BytePointer bin) \brief Create a network from Intel's Model Optimizer intermediate representation (IR).
static Net	readFromModelOptimizer(BytePointer bufferModelConfigPtr, long bufferModelConfigSize, BytePointer bufferWeightsPtr, long bufferWeightsSize) \brief Create a network from Intel's Model Optimizer in-memory buffers with intermediate representation (IR).
static Net	readFromModelOptimizer(String xml, String bin)
void	setHalideScheduler(BytePointer scheduler) \brief Compile Halide layers.
void	setHalideScheduler(String scheduler)
void	setInput(GpuMat blob)
void	setInput(GpuMat blob, BytePointer name, double scalefactor, Scalar mean)
void	setInput(GpuMat blob, String name, double scalefactor, Scalar mean)
void	setInput(Mat blob)
void	setInput(Mat blob, BytePointer name, double scalefactor, Scalar mean) \brief Sets the new input value for the network
void	setInput(Mat blob, String name, double scalefactor, Scalar mean)
void	setInput(UMat blob)
void	setInput(UMat blob, BytePointer name, double scalefactor, Scalar mean)
void	setInput(UMat blob, String name, double scalefactor, Scalar mean)
void	setInputShape(BytePointer inputName, IntPointer shape) \brief Specify shape of network input.
void	setInputShape(String inputName, IntPointer shape)
void	setInputsNames(StringVector inputBlobNames) \brief Sets outputs names of the network input pseudo layer.
void	setParam(DictValue layer, int numParam, Mat blob) \brief Sets the new value for the learned param of the layer.
void	setPreferableBackend(int backendId) \brief Ask network to use specific computation backend where it supported.
void	setPreferableTarget(int targetId) \brief Ask network to make computations on specific target device.

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

Net

public Net(Pointer p)

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

Net

public Net(long size)

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

Net

public Net()

Default constructor.

Method Detail

position

public Net position(long position)

Overrides:

position in class Pointer

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@opencv_core.Str
                                                BytePointer xml,
                                                @opencv_core.Str
                                                BytePointer bin)

\brief Create a network from Intel's Model Optimizer intermediate representation (IR).

Parameters:

xml - [in] XML configuration file with network's topology.

bin - [in] Binary file with trained weights. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@opencv_core.Str
                                                String xml,
                                                @opencv_core.Str
                                                String bin)

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@Cast(value="uchar*") @StdVector
                                                ByteBuffer bufferModelConfig,
                                                @Cast(value="uchar*") @StdVector
                                                ByteBuffer bufferWeights)

\brief Create a network from Intel's Model Optimizer in-memory buffers with intermediate representation (IR).

Parameters:

bufferModelConfig - [in] buffer with model's configuration.

bufferWeights - [in] buffer with model's trained weights.

Returns:

Net object.

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@Cast(value="uchar*") @StdVector
                                                byte[] bufferModelConfig,
                                                @Cast(value="uchar*") @StdVector
                                                byte[] bufferWeights)

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@Cast(value="const uchar*")
                                                BytePointer bufferModelConfigPtr,
                                                @Cast(value="size_t")
                                                long bufferModelConfigSize,
                                                @Cast(value="const uchar*")
                                                BytePointer bufferWeightsPtr,
                                                @Cast(value="size_t")
                                                long bufferWeightsSize)

\brief Create a network from Intel's Model Optimizer in-memory buffers with intermediate representation (IR).

Parameters:

bufferModelConfigPtr - [in] buffer pointer of model's configuration.

bufferModelConfigSize - [in] buffer size of model's configuration.

bufferWeightsPtr - [in] buffer pointer of model's trained weights.

bufferWeightsSize - [in] buffer size of model's trained weights.

Returns:

Net object.

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@Cast(value="const uchar*")
                                                ByteBuffer bufferModelConfigPtr,
                                                @Cast(value="size_t")
                                                long bufferModelConfigSize,
                                                @Cast(value="const uchar*")
                                                ByteBuffer bufferWeightsPtr,
                                                @Cast(value="size_t")
                                                long bufferWeightsSize)

readFromModelOptimizer

@ByVal
public static Net readFromModelOptimizer(@Cast(value="const uchar*")
                                                byte[] bufferModelConfigPtr,
                                                @Cast(value="size_t")
                                                long bufferModelConfigSize,
                                                @Cast(value="const uchar*")
                                                byte[] bufferWeightsPtr,
                                                @Cast(value="size_t")
                                                long bufferWeightsSize)

empty

@Cast(value="bool")
public boolean empty()

Returns true if there are no layers in the network.

dump

@opencv_core.Str
public BytePointer dump()

\brief Dump net to String

Returns:

String with structure, hyperparameters, backend, target and fusion Call method after setInput(). To see correct backend, target and fusion run after forward().

dumpToFile

public void dumpToFile(@opencv_core.Str
                       BytePointer path)

\brief Dump net structure, hyperparameters, backend, target and fusion to dot file

Parameters:

path - path to output file with .dot extension

See Also:

dump()

dumpToFile

public void dumpToFile(@opencv_core.Str
                       String path)

addLayer

public int addLayer(@opencv_core.Str
                    BytePointer name,
                    @opencv_core.Str
                    BytePointer type,
                    @ByRef
                    LayerParams params)

\brief Adds new layer to the net.

Parameters:

name - unique name of the adding layer.

type - typename of the adding layer (type must be registered in LayerRegister).

params - parameters which will be used to initialize the creating layer.

Returns:

unique identifier of created layer, or -1 if a failure will happen.

addLayer

public int addLayer(@opencv_core.Str
                    String name,
                    @opencv_core.Str
                    String type,
                    @ByRef
                    LayerParams params)

addLayerToPrev

public int addLayerToPrev(@opencv_core.Str
                          BytePointer name,
                          @opencv_core.Str
                          BytePointer type,
                          @ByRef
                          LayerParams params)

\brief Adds new layer and connects its first input to the first output of previously added layer.

See Also:

addLayer()

addLayerToPrev

public int addLayerToPrev(@opencv_core.Str
                          String name,
                          @opencv_core.Str
                          String type,
                          @ByRef
                          LayerParams params)

getLayerId

public int getLayerId(@opencv_core.Str
                      BytePointer layer)

\brief Converts string name of the layer to the integer identifier.

Returns:

id of the layer, or -1 if the layer wasn't found.

getLayerId

public int getLayerId(@opencv_core.Str
                      String layer)

getLayerNames

@ByVal
public StringVector getLayerNames()

getLayer

@opencv_core.Ptr
public Layer getLayer(@ByVal @Cast(value="cv::dnn::Net::LayerId*")
                                       DictValue layerId)

\brief Returns pointer to layer with specified id or name which the network use.

connect

public void connect(@opencv_core.Str
                    BytePointer outPin,
                    @opencv_core.Str
                    BytePointer inpPin)

\brief Connects output of the first layer to input of the second layer.

Parameters:

outPin - descriptor of the first layer output.

inpPin - descriptor of the second layer input. Descriptors have the following template <layer_name>[.input_number]: - the first part of the template layer_name is string name of the added layer. If this part is empty then the network input pseudo layer will be used; - the second optional part of the template input_number is either number of the layer input, either label one. If this part is omitted then the first layer input will be used.

See Also:

setNetInputs(), Layer::inputNameToIndex(), Layer::outputNameToIndex()

connect

public void connect(@opencv_core.Str
                    String outPin,
                    @opencv_core.Str
                    String inpPin)

connect

public void connect(int outLayerId,
                    int outNum,
                    int inpLayerId,
                    int inpNum)

\brief Connects #\p outNum output of the first layer to #\p inNum input of the second layer.

Parameters:

outLayerId - identifier of the first layer

outNum - number of the first layer output

inpLayerId - identifier of the second layer

inpNum - number of the second layer input

setInputsNames

public void setInputsNames(@Const @ByRef
                           StringVector inputBlobNames)

\brief Sets outputs names of the network input pseudo layer. Each net always has special own the network input pseudo layer with id=0. This layer stores the user blobs only and don't make any computations. In fact, this layer provides the only way to pass user data into the network. As any other layer, this layer can label its outputs and this function provides an easy way to do this.

setInputShape

public void setInputShape(@opencv_core.Str
                          BytePointer inputName,
                          @Const @StdVector @ByRef
                          IntPointer shape)

\brief Specify shape of network input.

setInputShape

public void setInputShape(@opencv_core.Str
                          String inputName,
                          @Const @StdVector @ByRef
                          IntPointer shape)

forward

@ByVal
public Mat forward(@opencv_core.Str
                          BytePointer outputName)

\brief Runs forward pass to compute output of layer with name \p outputName.

Parameters:

outputName - name for layer which output is needed to get

Returns:

blob for first output of specified layer. \details By default runs forward pass for the whole network.

forward

@ByVal
public Mat forward()

forward

@ByVal
public Mat forward(@opencv_core.Str
                          String outputName)

forwardAsync

@ByVal
public AsyncArray forwardAsync(@opencv_core.Str
                                      BytePointer outputName)

\brief Runs forward pass to compute output of layer with name \p outputName.

Parameters:

outputName - name for layer which output is needed to get \details By default runs forward pass for the whole network. This is an asynchronous version of forward(const String&). dnn::DNN_BACKEND_INFERENCE_ENGINE backend is required.

forwardAsync

@ByVal
public AsyncArray forwardAsync()

forwardAsync

@ByVal
public AsyncArray forwardAsync(@opencv_core.Str
                                      String outputName)

forward

public void forward(@ByVal
                    MatVector outputBlobs,
                    @opencv_core.Str
                    BytePointer outputName)

\brief Runs forward pass to compute output of layer with name \p outputName.

Parameters:

outputBlobs - contains all output blobs for specified layer.

outputName - name for layer which output is needed to get \details If \p outputName is empty, runs forward pass for the whole network.

forward

public void forward(@ByVal
                    MatVector outputBlobs)

forward

public void forward(@ByVal
                    UMatVector outputBlobs,
                    @opencv_core.Str
                    String outputName)

forward

public void forward(@ByVal
                    UMatVector outputBlobs)

forward

public void forward(@ByVal
                    GpuMatVector outputBlobs,
                    @opencv_core.Str
                    BytePointer outputName)

forward

public void forward(@ByVal
                    GpuMatVector outputBlobs)

forward

public void forward(@ByVal
                    MatVector outputBlobs,
                    @opencv_core.Str
                    String outputName)

forward

public void forward(@ByVal
                    UMatVector outputBlobs,
                    @opencv_core.Str
                    BytePointer outputName)

forward

public void forward(@ByVal
                    GpuMatVector outputBlobs,
                    @opencv_core.Str
                    String outputName)

forward

public void forward(@ByVal
                    MatVector outputBlobs,
                    @Const @ByRef
                    StringVector outBlobNames)

\brief Runs forward pass to compute outputs of layers listed in \p outBlobNames.

Parameters:

outputBlobs - contains blobs for first outputs of specified layers.

outBlobNames - names for layers which outputs are needed to get

forward

public void forward(@ByVal
                    UMatVector outputBlobs,
                    @Const @ByRef
                    StringVector outBlobNames)

forward

public void forward(@ByVal
                    GpuMatVector outputBlobs,
                    @Const @ByRef
                    StringVector outBlobNames)

forwardAndRetrieve

@Name(value="forward")
public void forwardAndRetrieve(@ByRef
                                                      MatVectorVector outputBlobs,
                                                      @Const @ByRef
                                                      StringVector outBlobNames)

\brief Runs forward pass to compute outputs of layers listed in \p outBlobNames.

Parameters:

outputBlobs - contains all output blobs for each layer specified in \p outBlobNames.

outBlobNames - names for layers which outputs are needed to get

setHalideScheduler

public void setHalideScheduler(@opencv_core.Str
                               BytePointer scheduler)

\brief Compile Halide layers.

Parameters:

scheduler - [in] Path to YAML file with scheduling directives.

See Also:

Schedule layers that support Halide backend. Then compile them for specific target. For layers that not represented in scheduling file or if no manual scheduling used at all, automatic scheduling will be applied.

setHalideScheduler

public void setHalideScheduler(@opencv_core.Str
                               String scheduler)

setPreferableBackend

public void setPreferableBackend(int backendId)

\brief Ask network to use specific computation backend where it supported.

Parameters:

backendId - [in] backend identifier.

See Also:

If OpenCV is compiled with Intel's Inference Engine library, DNN_BACKEND_DEFAULT means DNN_BACKEND_INFERENCE_ENGINE. Otherwise it equals to DNN_BACKEND_OPENCV.

setPreferableTarget

public void setPreferableTarget(int targetId)

\brief Ask network to make computations on specific target device.

Parameters:

targetId - [in] target identifier.

See Also:

List of supported combinations backend / target: | | DNN_BACKEND_OPENCV | DNN_BACKEND_INFERENCE_ENGINE | DNN_BACKEND_HALIDE | DNN_BACKEND_CUDA | |------------------------|--------------------|------------------------------|--------------------|-------------------| | DNN_TARGET_CPU | + | + | + | | | DNN_TARGET_OPENCL | + | + | + | | | DNN_TARGET_OPENCL_FP16 | + | + | | | | DNN_TARGET_MYRIAD | | + | | | | DNN_TARGET_FPGA | | + | | | | DNN_TARGET_CUDA | | | | + | | DNN_TARGET_CUDA_FP16 | | | | + |

setInput

public void setInput(@ByVal
                     Mat blob,
                     @opencv_core.Str
                     BytePointer name,
                     double scalefactor,
                     @Const @ByRef(nullValue="cv::Scalar()")
                     Scalar mean)

\brief Sets the new input value for the network

Parameters:

blob - A new blob. Should have CV_32F or CV_8U depth.

name - A name of input layer.

scalefactor - An optional normalization scale.

mean - An optional mean subtraction values.

See Also:

to know format of the descriptor. If scale or mean values are specified, a final input blob is computed as:

{@code \[input(n,c,h,w) = scalefactor \times (blob(n,c,h,w) - mean_c)\]}

setInput

public void setInput(@ByVal
                     Mat blob)

setInput

public void setInput(@ByVal
                     Mat blob,
                     @opencv_core.Str
                     String name,
                     double scalefactor,
                     @Const @ByRef(nullValue="cv::Scalar()")
                     Scalar mean)

setInput

public void setInput(@ByVal
                     UMat blob,
                     @opencv_core.Str
                     String name,
                     double scalefactor,
                     @Const @ByRef(nullValue="cv::Scalar()")
                     Scalar mean)

setInput

public void setInput(@ByVal
                     UMat blob)

setInput

public void setInput(@ByVal
                     UMat blob,
                     @opencv_core.Str
                     BytePointer name,
                     double scalefactor,
                     @Const @ByRef(nullValue="cv::Scalar()")
                     Scalar mean)

setInput

public void setInput(@ByVal
                     GpuMat blob,
                     @opencv_core.Str
                     BytePointer name,
                     double scalefactor,
                     @Const @ByRef(nullValue="cv::Scalar()")
                     Scalar mean)

setInput

public void setInput(@ByVal
                     GpuMat blob)

setInput

public void setInput(@ByVal
                     GpuMat blob,
                     @opencv_core.Str
                     String name,
                     double scalefactor,
                     @Const @ByRef(nullValue="cv::Scalar()")
                     Scalar mean)

setParam

public void setParam(@ByVal @Cast(value="cv::dnn::Net::LayerId*")
                     DictValue layer,
                     int numParam,
                     @Const @ByRef
                     Mat blob)

\brief Sets the new value for the learned param of the layer.

Parameters:

layer - name or id of the layer.

numParam - index of the layer parameter in the Layer::blobs array.

blob - the new value.

See Also:

\note If shape of the new blob differs from the previous shape, then the following forward pass may fail.

getParam

@ByVal
public Mat getParam(@ByVal @Cast(value="cv::dnn::Net::LayerId*")
                           DictValue layer,
                           int numParam)

\brief Returns parameter blob of the layer.

Parameters:

layer - name or id of the layer.

numParam - index of the layer parameter in the Layer::blobs array.

See Also:

Layer::blobs

getParam

@ByVal
public Mat getParam(@ByVal @Cast(value="cv::dnn::Net::LayerId*")
                           DictValue layer)

getUnconnectedOutLayers

@StdVector
public IntPointer getUnconnectedOutLayers()

\brief Returns indexes of layers with unconnected outputs.

getUnconnectedOutLayersNames

@ByVal
public StringVector getUnconnectedOutLayersNames()

\brief Returns names of layers with unconnected outputs.

getLayersShapes

public void getLayersShapes(@Const @ByRef
                            MatShapeVector netInputShapes,
                            @StdVector
                            IntPointer layersIds,
                            @ByRef
                            MatShapeVectorVector inLayersShapes,
                            @ByRef
                            MatShapeVectorVector outLayersShapes)

\brief Returns input and output shapes for all layers in loaded model; preliminary inferencing isn't necessary.

Parameters:

netInputShapes - shapes for all input blobs in net input layer.

layersIds - output parameter for layer IDs.

inLayersShapes - output parameter for input layers shapes; order is the same as in layersIds

outLayersShapes - output parameter for output layers shapes; order is the same as in layersIds

getLayersShapes

public void getLayersShapes(@Const @ByRef
                            MatShapeVector netInputShapes,
                            @StdVector
                            IntBuffer layersIds,
                            @ByRef
                            MatShapeVectorVector inLayersShapes,
                            @ByRef
                            MatShapeVectorVector outLayersShapes)

getLayersShapes

public void getLayersShapes(@Const @ByRef
                            MatShapeVector netInputShapes,
                            @StdVector
                            int[] layersIds,
                            @ByRef
                            MatShapeVectorVector inLayersShapes,
                            @ByRef
                            MatShapeVectorVector outLayersShapes)

getLayersShapes

public void getLayersShapes(@Const @StdVector @ByRef
                            IntPointer netInputShape,
                            @StdVector
                            IntPointer layersIds,
                            @ByRef
                            MatShapeVectorVector inLayersShapes,
                            @ByRef
                            MatShapeVectorVector outLayersShapes)

\overload

getLayersShapes

public void getLayersShapes(@Const @StdVector @ByRef
                            IntPointer netInputShape,
                            @StdVector
                            IntBuffer layersIds,
                            @ByRef
                            MatShapeVectorVector inLayersShapes,
                            @ByRef
                            MatShapeVectorVector outLayersShapes)

getLayersShapes

public void getLayersShapes(@Const @StdVector @ByRef
                            IntPointer netInputShape,
                            @StdVector
                            int[] layersIds,
                            @ByRef
                            MatShapeVectorVector inLayersShapes,
                            @ByRef
                            MatShapeVectorVector outLayersShapes)

getLayerShapes

public void getLayerShapes(@Const @StdVector @ByRef
                           IntPointer netInputShape,
                           int layerId,
                           @ByRef
                           MatShapeVector inLayerShapes,
                           @ByRef
                           MatShapeVector outLayerShapes)

\brief Returns input and output shapes for layer with specified id in loaded model; preliminary inferencing isn't necessary.

Parameters:

netInputShape - shape input blob in net input layer.

layerId - id for layer.

inLayerShapes - output parameter for input layers shapes; order is the same as in layersIds

outLayerShapes - output parameter for output layers shapes; order is the same as in layersIds

getLayerShapes

public void getLayerShapes(@Const @ByRef
                           MatShapeVector netInputShapes,
                           int layerId,
                           @ByRef
                           MatShapeVector inLayerShapes,
                           @ByRef
                           MatShapeVector outLayerShapes)

\overload

getFLOPS

@Cast(value="int64")
public long getFLOPS(@Const @ByRef
                                          MatShapeVector netInputShapes)

\brief Computes FLOP for whole loaded model with specified input shapes.

Parameters:

netInputShapes - vector of shapes for all net inputs.

Returns:

computed FLOP.

getFLOPS

@Cast(value="int64")
public long getFLOPS(@Const @StdVector @ByRef
                                          IntPointer netInputShape)

\overload

getFLOPS

@Cast(value="int64")
public long getFLOPS(int layerId,
                                          @Const @ByRef
                                          MatShapeVector netInputShapes)

\overload

getFLOPS

@Cast(value="int64")
public long getFLOPS(int layerId,
                                          @Const @StdVector @ByRef
                                          IntPointer netInputShape)

\overload

getLayerTypes

public void getLayerTypes(@ByRef
                          StringVector layersTypes)

\brief Returns list of types for layer used in model.

Parameters:

layersTypes - output parameter for returning types.

getLayersCount

public int getLayersCount(@opencv_core.Str
                          BytePointer layerType)

\brief Returns count of layers of specified type.

Parameters:

layerType - type.

Returns:

count of layers

getLayersCount

public int getLayersCount(@opencv_core.Str
                          String layerType)

getMemoryConsumption

public void getMemoryConsumption(@Const @ByRef
                                 MatShapeVector netInputShapes,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer blobs)

\brief Computes bytes number which are required to store all weights and intermediate blobs for model.

Parameters:

netInputShapes - vector of shapes for all net inputs.

weights - output parameter to store resulting bytes for weights.

blobs - output parameter to store resulting bytes for intermediate blobs.

getMemoryConsumption

public void getMemoryConsumption(@Const @StdVector @ByRef
                                 IntPointer netInputShape,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer blobs)

\overload

getMemoryConsumption

public void getMemoryConsumption(int layerId,
                                 @Const @ByRef
                                 MatShapeVector netInputShapes,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer blobs)

\overload

getMemoryConsumption

public void getMemoryConsumption(int layerId,
                                 @Const @StdVector @ByRef
                                 IntPointer netInputShape,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @ByRef
                                 SizeTPointer blobs)

\overload

getMemoryConsumption

public void getMemoryConsumption(@Const @ByRef
                                 MatShapeVector netInputShapes,
                                 @StdVector
                                 IntPointer layerIds,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer blobs)

\brief Computes bytes number which are required to store all weights and intermediate blobs for each layer.

Parameters:

netInputShapes - vector of shapes for all net inputs.

layerIds - output vector to save layer IDs.

weights - output parameter to store resulting bytes for weights.

blobs - output parameter to store resulting bytes for intermediate blobs.

getMemoryConsumption

public void getMemoryConsumption(@Const @ByRef
                                 MatShapeVector netInputShapes,
                                 @StdVector
                                 IntBuffer layerIds,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer blobs)

getMemoryConsumption

public void getMemoryConsumption(@Const @ByRef
                                 MatShapeVector netInputShapes,
                                 @StdVector
                                 int[] layerIds,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer blobs)

getMemoryConsumption

public void getMemoryConsumption(@Const @StdVector @ByRef
                                 IntPointer netInputShape,
                                 @StdVector
                                 IntPointer layerIds,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer blobs)

\overload

getMemoryConsumption

public void getMemoryConsumption(@Const @StdVector @ByRef
                                 IntPointer netInputShape,
                                 @StdVector
                                 IntBuffer layerIds,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer blobs)

getMemoryConsumption

public void getMemoryConsumption(@Const @StdVector @ByRef
                                 IntPointer netInputShape,
                                 @StdVector
                                 int[] layerIds,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer weights,
                                 @Cast(value="size_t*") @StdVector
                                 SizeTPointer blobs)

enableFusion

public void enableFusion(@Cast(value="bool")
                         boolean fusion)

\brief Enables or disables layer fusion in the network.

Parameters:

fusion - true to enable the fusion, false to disable. The fusion is enabled by default.

getPerfProfile

@Cast(value="int64")
public long getPerfProfile(@StdVector
                                                DoublePointer timings)

\brief Returns overall time for inference and timings (in ticks) for layers. Indexes in returned vector correspond to layers ids. Some layers can be fused with others, in this case zero ticks count will be return for that skipped layers.

Parameters:

timings - vector for tick timings for all layers.

Returns:

overall ticks for model inference.

getPerfProfile

@Cast(value="int64")
public long getPerfProfile(@StdVector
                                                DoubleBuffer timings)

getPerfProfile

@Cast(value="int64")
public long getPerfProfile(@StdVector
                                                double[] timings)