org.bytedeco.javacpp

Class opencv_dnn.Layer

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.javacpp.opencv_core.Algorithm

org.bytedeco.javacpp.opencv_dnn.Layer

All Implemented Interfaces:

AutoCloseable

Direct Known Subclasses:

opencv_dnn.ActivationLayer, opencv_dnn.BaseConvolutionLayer, opencv_dnn.BlankLayer, opencv_dnn.ConcatLayer, opencv_dnn.CropAndResizeLayer, opencv_dnn.CropLayer, opencv_dnn.DetectionOutputLayer, opencv_dnn.EltwiseLayer, opencv_dnn.FlattenLayer, opencv_dnn.InnerProductLayer, opencv_dnn.InterpLayer, opencv_dnn.LRNLayer, opencv_dnn.LSTMLayer, opencv_dnn.MaxUnpoolLayer, opencv_dnn.MVNLayer, opencv_dnn.NormalizeBBoxLayer, opencv_dnn.PaddingLayer, opencv_dnn.PermuteLayer, opencv_dnn.PoolingLayer, opencv_dnn.PriorBoxLayer, opencv_dnn.ProposalLayer, opencv_dnn.RegionLayer, opencv_dnn.ReorgLayer, opencv_dnn.ReshapeLayer, opencv_dnn.ResizeLayer, opencv_dnn.RNNLayer, opencv_dnn.ScaleLayer, opencv_dnn.ShiftLayer, opencv_dnn.ShuffleChannelLayer, opencv_dnn.SliceLayer, opencv_dnn.SoftmaxLayer, opencv_dnn.SplitLayer

Enclosing class:

opencv_dnn

@Namespace(value="cv::dnn")
 @NoOffset
public static class opencv_dnn.Layer
extends opencv_core.Algorithm

\brief This interface class allows to build new Layers - are building blocks of networks. Each class, derived from Layer, must implement allocate() methods to declare own outputs and forward() to compute outputs. Also before using the new layer into networks you must register your layer by using one of \ref dnnLayerFactory "LayerFactory" macros.

Nested Class Summary

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

org.bytedeco.javacpp.Pointer.CustomDeallocator, org.bytedeco.javacpp.Pointer.Deallocator, org.bytedeco.javacpp.Pointer.NativeDeallocator

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
Layer(org.bytedeco.javacpp.Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
void	applyHalideScheduler(opencv_dnn.BackendNode node, opencv_dnn.MatPointerVector inputs, opencv_core.MatVector outputs, int targetId) \brief Automatic Halide scheduling based on layer hyper-parameters.
opencv_core.MatVector	blobs() List of learned parameters must be stored here to allow read them by using Net::getParam().
opencv_dnn.Layer	blobs(opencv_core.MatVector blobs)
opencv_core.MatVector	finalize(opencv_core.MatVector inputs) \brief \overload
void	finalize(opencv_core.MatVector inputs, opencv_core.MatVector outputs) \brief \overload
void	finalize(opencv_dnn.MatPointerVector input, opencv_core.MatVector output) \brief Computes and sets internal parameters according to inputs, outputs and blobs.
void	forward_fallback(opencv_core.GpuMatVector inputs, opencv_core.GpuMatVector outputs, opencv_core.GpuMatVector internals)
void	forward_fallback(opencv_core.MatVector inputs, opencv_core.MatVector outputs, opencv_core.MatVector internals) \brief Given the \p input blobs, computes the output \p blobs.
void	forward_fallback(opencv_core.UMatVector inputs, opencv_core.UMatVector outputs, opencv_core.UMatVector internals)
void	forward(opencv_core.GpuMatVector inputs, opencv_core.GpuMatVector outputs, opencv_core.GpuMatVector internals)
void	forward(opencv_core.MatVector inputs, opencv_core.MatVector outputs, opencv_core.MatVector internals) \brief Given the \p input blobs, computes the output \p blobs.
void	forward(opencv_core.UMatVector inputs, opencv_core.UMatVector outputs, opencv_core.UMatVector internals)
void	forward(opencv_dnn.MatPointerVector input, opencv_core.MatVector output, opencv_core.MatVector internals) \brief Given the \p input blobs, computes the output \p blobs.
long	getFLOPS(opencv_dnn.MatShapeVector inputs, opencv_dnn.MatShapeVector outputs)
boolean	getMemoryShapes(opencv_dnn.MatShapeVector inputs, int requiredOutputs, opencv_dnn.MatShapeVector outputs, opencv_dnn.MatShapeVector internals)
void	getScaleShift(opencv_core.Mat scale, opencv_core.Mat shift) \brief Returns parameters of layers with channel-wise multiplication and addition.
int	inputNameToIndex(org.bytedeco.javacpp.BytePointer inputName) \brief Returns index of input blob into the input array.
int	inputNameToIndex(String inputName)
org.bytedeco.javacpp.BytePointer	name() Name of the layer instance, can be used for logging or other internal purposes.
opencv_dnn.Layer	name(org.bytedeco.javacpp.BytePointer name)
int	outputNameToIndex(org.bytedeco.javacpp.BytePointer outputName) \brief Returns index of output blob in output array.
int	outputNameToIndex(String outputName)
int	preferableTarget() prefer target for layer forwarding
opencv_dnn.Layer	preferableTarget(int preferableTarget)
void	run(opencv_core.MatVector inputs, opencv_core.MatVector outputs, opencv_core.MatVector internals) \brief Allocates layer and computes output.
boolean	setActivation(opencv_dnn.ActivationLayer layer) \brief Tries to attach to the layer the subsequent activation layer, i.e.
void	setParamsFrom(opencv_dnn.LayerParams params) Initializes only #name, #type and #blobs fields.
boolean	supportBackend(int backendId) \brief Ask layer if it support specific backend for doing computations.
opencv_dnn.BackendNode	tryAttach(opencv_dnn.BackendNode node) \brief Implement layers fusing.
boolean	tryFuse(opencv_dnn.Layer top) \brief Try to fuse current layer with a next one
org.bytedeco.javacpp.BytePointer	type() Type name which was used for creating layer by layer factory.
opencv_dnn.Layer	type(org.bytedeco.javacpp.BytePointer type)
void	unsetAttached() \brief "Deattaches" all the layers, attached to particular layer.

Methods inherited from class org.bytedeco.javacpp.opencv_core.Algorithm

clear, empty, getDefaultName, position, read, save, save, write, write, write

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, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, parseBytes, physicalBytes, position, put, realloc, setNull, sizeof, toString, totalBytes, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

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

Constructor Detail

Layer

public Layer(org.bytedeco.javacpp.Pointer p)

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

Method Detail

blobs

@ByRef
public opencv_core.MatVector blobs()

List of learned parameters must be stored here to allow read them by using Net::getParam().

blobs

public opencv_dnn.Layer blobs(opencv_core.MatVector blobs)

finalize

public void finalize(@Const @ByRef
                     opencv_dnn.MatPointerVector input,
                     @ByRef
                     opencv_core.MatVector output)

\brief Computes and sets internal parameters according to inputs, outputs and blobs.

Parameters:

[in] - input vector of already allocated input blobs

[out] - output vector of already allocated output blobs If this method is called after network has allocated all memory for input and output blobs and before inferencing.

forward

public void forward(@ByRef
                    opencv_dnn.MatPointerVector input,
                    @ByRef
                    opencv_core.MatVector output,
                    @ByRef
                    opencv_core.MatVector internals)

\brief Given the \p input blobs, computes the output \p blobs.

Parameters:

[in] - input the input blobs.

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

[out] - internals allocated internal blobs

forward

public void forward(@ByVal
                    opencv_core.MatVector inputs,
                    @ByVal
                    opencv_core.MatVector outputs,
                    @ByVal
                    opencv_core.MatVector internals)

\brief Given the \p input blobs, computes the output \p blobs.

Parameters:

[in] - inputs the input blobs.

[out] - outputs allocated output blobs, which will store results of the computation.

[out] - internals allocated internal blobs

forward

public void forward(@ByVal
                    opencv_core.UMatVector inputs,
                    @ByVal
                    opencv_core.UMatVector outputs,
                    @ByVal
                    opencv_core.UMatVector internals)

forward

public void forward(@ByVal
                    opencv_core.GpuMatVector inputs,
                    @ByVal
                    opencv_core.GpuMatVector outputs,
                    @ByVal
                    opencv_core.GpuMatVector internals)

forward_fallback

public void forward_fallback(@ByVal
                             opencv_core.MatVector inputs,
                             @ByVal
                             opencv_core.MatVector outputs,
                             @ByVal
                             opencv_core.MatVector internals)

\brief Given the \p input blobs, computes the output \p blobs.

Parameters:

[in] - inputs the input blobs.

[out] - outputs allocated output blobs, which will store results of the computation.

[out] - internals allocated internal blobs

forward_fallback

public void forward_fallback(@ByVal
                             opencv_core.UMatVector inputs,
                             @ByVal
                             opencv_core.UMatVector outputs,
                             @ByVal
                             opencv_core.UMatVector internals)

forward_fallback

public void forward_fallback(@ByVal
                             opencv_core.GpuMatVector inputs,
                             @ByVal
                             opencv_core.GpuMatVector outputs,
                             @ByVal
                             opencv_core.GpuMatVector internals)

finalize

public void finalize(@Const @ByRef
                     opencv_core.MatVector inputs,
                     @ByRef
                     opencv_core.MatVector outputs)

\brief \overload

finalize

@ByVal
public opencv_core.MatVector finalize(@Const @ByRef
                                             opencv_core.MatVector inputs)

\brief \overload

run

public void run(@Const @ByRef
                opencv_core.MatVector inputs,
                @ByRef
                opencv_core.MatVector outputs,
                @ByRef
                opencv_core.MatVector internals)

\brief Allocates layer and computes output.

inputNameToIndex

public int inputNameToIndex(@opencv_core.Str
                            org.bytedeco.javacpp.BytePointer inputName)

\brief Returns index of input blob into the input array.

Parameters:

inputName - label of input blob Each layer input and output can be labeled to easily identify them using "%[.output_name]" notation. This method maps label of input blob to its index into input vector.

inputNameToIndex

public int inputNameToIndex(@opencv_core.Str
                            String inputName)

outputNameToIndex

public int outputNameToIndex(@opencv_core.Str
                             org.bytedeco.javacpp.BytePointer outputName)

\brief Returns index of output blob in output array.

See Also:

inputNameToIndex()

outputNameToIndex

public int outputNameToIndex(@opencv_core.Str
                             String outputName)

supportBackend

@Cast(value="bool")
public boolean supportBackend(int backendId)

\brief Ask layer if it support specific backend for doing computations.

Parameters:

[in] - backendId computation backend identifier.

See Also:

Backend

applyHalideScheduler

public void applyHalideScheduler(@opencv_core.Ptr
                                 opencv_dnn.BackendNode node,
                                 @Const @ByRef
                                 opencv_dnn.MatPointerVector inputs,
                                 @Const @ByRef
                                 opencv_core.MatVector outputs,
                                 int targetId)

\brief Automatic Halide scheduling based on layer hyper-parameters.

Parameters:

[in] - node Backend node with Halide functions.

[in] - inputs Blobs that will be used in forward invocations.

[in] - outputs Blobs that will be used in forward invocations.

[in] - targetId Target identifier

See Also:

BackendNode, Target Layer don't use own Halide::Func members because we can have applied layers fusing. In this way the fused function should be scheduled.

tryAttach

@opencv_core.Ptr
public opencv_dnn.BackendNode tryAttach(@opencv_core.Ptr
                                                         opencv_dnn.BackendNode node)

\brief Implement layers fusing.

Parameters:

[in] - node Backend node of bottom layer.

See Also:

Actual for graph-based backends. If layer attached successfully, returns non-empty cv::Ptr to node of the same backend. Fuse only over the last function.

setActivation

@Cast(value="bool")
public boolean setActivation(@opencv_core.Ptr
                                                 opencv_dnn.ActivationLayer layer)

\brief Tries to attach to the layer the subsequent activation layer, i.e. do the layer fusion in a partial case.

Parameters:

[in] - layer The subsequent activation layer. Returns true if the activation layer has been attached successfully.

tryFuse

@Cast(value="bool")
public boolean tryFuse(@opencv_core.Ptr
                                           opencv_dnn.Layer top)

\brief Try to fuse current layer with a next one

Parameters:

[in] - top Next layer to be fused.

Returns:

True if fusion was performed.

getScaleShift

public void getScaleShift(@ByRef
                          opencv_core.Mat scale,
                          @ByRef
                          opencv_core.Mat shift)

\brief Returns parameters of layers with channel-wise multiplication and addition.

Parameters:

[out] - scale Channel-wise multipliers. Total number of values should be equal to number of channels.

[out] - shift Channel-wise offsets. Total number of values should be equal to number of channels. Some layers can fuse their transformations with further layers. In example, convolution + batch normalization. This way base layer use weights from layer after it. Fused layer is skipped. By default, \p scale and \p shift are empty that means layer has no element-wise multiplications or additions.

unsetAttached

public void unsetAttached()

\brief "Deattaches" all the layers, attached to particular layer.

getMemoryShapes

@Cast(value="bool")
public boolean getMemoryShapes(@Const @ByRef
                                                   opencv_dnn.MatShapeVector inputs,
                                                   int requiredOutputs,
                                                   @ByRef
                                                   opencv_dnn.MatShapeVector outputs,
                                                   @ByRef
                                                   opencv_dnn.MatShapeVector internals)

getFLOPS

@Cast(value="int64")
public long getFLOPS(@Const @ByRef
                                          opencv_dnn.MatShapeVector inputs,
                                          @Const @ByRef
                                          opencv_dnn.MatShapeVector outputs)

name

@opencv_core.Str
public org.bytedeco.javacpp.BytePointer name()

Name of the layer instance, can be used for logging or other internal purposes.

name

public opencv_dnn.Layer name(org.bytedeco.javacpp.BytePointer name)

type

@opencv_core.Str
public org.bytedeco.javacpp.BytePointer type()

Type name which was used for creating layer by layer factory.

type

public opencv_dnn.Layer type(org.bytedeco.javacpp.BytePointer type)

preferableTarget

public int preferableTarget()

prefer target for layer forwarding

preferableTarget

public opencv_dnn.Layer preferableTarget(int preferableTarget)

setParamsFrom

public void setParamsFrom(@Const @ByRef
                          opencv_dnn.LayerParams params)

Initializes only #name, #type and #blobs fields.