Classical recurrent layer. More...

#include "all_layers.hpp"

Inheritance diagram for cv::dnn::RNNLayer:

Public Member Functions
virtual void	setProduceHiddenOutput (bool produce=false)=0
	If this flag is set to true then layer will produce \( h_t \) as second output. More...

virtual void	setWeights (const Mat &Wxh, const Mat &bh, const Mat &Whh, const Mat &Who, const Mat &bo)=0

Public Member Functions inherited from cv::dnn::Layer
	Layer ()

	Layer (const LayerParams &params)
	Initializes only name, type and blobs fields. More...

virtual	~Layer ()

virtual void	applyHalideScheduler (Ptr< BackendNode > &node, const std::vector< Mat *> &inputs, const std::vector< Mat > &outputs, int targetId) const
	Automatic Halide scheduling based on layer hyper-parameters. More...

virtual void	finalize (const std::vector< Mat *> &input, std::vector< Mat > &output)
	Computes and sets internal parameters according to inputs, outputs and blobs. More...

void	finalize (const std::vector< Mat > &inputs, std::vector< Mat > &outputs)

std::vector< Mat >	finalize (const std::vector< Mat > &inputs)

virtual void	forward (std::vector< Mat *> &input, std::vector< Mat > &output, std::vector< Mat > &internals)=0
	Given the `input` blobs, computes the output `blobs`. More...

void	forward (const std::vector< Mat > &inputs, std::vector< Mat > &outputs, std::vector< Mat > &internals)

virtual int64	getFLOPS (const std::vector< MatShape > &inputs, const std::vector< MatShape > &outputs) const

virtual bool	getMemoryShapes (const std::vector< MatShape > &inputs, const int requiredOutputs, std::vector< MatShape > &outputs, std::vector< MatShape > &internals) const

virtual Ptr< BackendNode >	initHalide (const std::vector< Ptr< BackendWrapper > > &inputs)
	Returns Halide backend node. More...

virtual int	inputNameToIndex (String inputName)
	Returns index of input blob into the input array. More...

virtual int	outputNameToIndex (String outputName)
	Returns index of output blob in output array. More...

void	run (const std::vector< Mat > &inputs, std::vector< Mat > &outputs, std::vector< Mat > &internals)
	Allocates layer and computes output. More...

virtual bool	setActivation (const Ptr< ActivationLayer > &layer)
	Tries to attach to the layer the subsequent activation layer, i.e. do the layer fusion in a partial case. More...

virtual bool	setBatchNorm (const Ptr< BatchNormLayer > &layer)
	Tries to attach to the layer the subsequent batch normalization layer, i.e. do the layer fusion in a partial case. More...

void	setParamsFrom (const LayerParams &params)
	Initializes only name, type and blobs fields. More...

virtual bool	setScale (const Ptr< ScaleLayer > &layer)
	Tries to attach to the layer the subsequent scaling layer, i.e. do the layer fusion in a partial case. More...

virtual bool	supportBackend (int backendId)
	Ask layer if it support specific backend for doing computations. More...

virtual Ptr< BackendNode >	tryAttach (const Ptr< BackendNode > &node)
	Implement layers fusing. More...

virtual void	unsetAttached ()
	"Deattaches" all the layers, attached to particular layer. More...

Public Member Functions inherited from cv::Algorithm
	Algorithm ()

virtual	~Algorithm ()

virtual void	clear ()
	Clears the algorithm state. More...

virtual bool	empty () const
	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...

virtual String	getDefaultName () const

virtual void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage. More...

virtual void	save (const String &filename) const

virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage. More...

Static Public Member Functions
static Ptr< RNNLayer >	create (const LayerParams &params)

Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file. More...

template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String. More...

template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node. More...

Additional Inherited Members
Public Attributes inherited from cv::dnn::Layer
std::vector< Mat >	blobs
	List of learned parameters must be stored here to allow read them by using Net::getParam(). More...

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

int	preferableTarget
	prefer target for layer forwarding More...

String	type
	Type name which was used for creating layer by layer factory. More...

Protected Member Functions inherited from cv::Algorithm
void	writeFormat (FileStorage &fs) const

Detailed Description

Classical recurrent layer.

Accepts two inputs \(x_t\) and \(h_{t-1}\) and compute two outputs \(o_t\) and \(h_t\).

input: should contain packed input \(x_t\).
output: should contain output \(o_t\) (and \(h_t\) if setProduceHiddenOutput() is set to true).

input[0] should have shape [T, N, data_dims] where T and N is number of timestamps and number of independent samples of \(x_t\) respectively.

output[0] will have shape [T, N, \(N_o\)], where \(N_o\) is number of rows in \( W_{xo} \) matrix.

If setProduceHiddenOutput() is set to true then output[1] will contain a Mat with shape [T, N, \(N_h\)], where \(N_h\) is number of rows in \( W_{hh} \) matrix.

Member Function Documentation

§ create()

static Ptr<RNNLayer> cv::dnn::RNNLayer::create ( const LayerParams & params )

static

Creates instance of RNNLayer

§ setProduceHiddenOutput()

virtual void cv::dnn::RNNLayer::setProduceHiddenOutput ( bool produce = false )

pure virtual

If this flag is set to true then layer will produce \( h_t \) as second output.

Shape of the second output is the same as first output.

§ setWeights()

virtual void cv::dnn::RNNLayer::setWeights	(	const Mat &	Wxh,
		const Mat &	bh,
		const Mat &	Whh,
		const Mat &	Who,
		const Mat &	bo
	)

pure virtual

Setups learned weights.

Recurrent-layer behavior on each step is defined by current input \( x_t \), previous state \( h_t \) and learned weights as follows:

\begin{eqnarray*} h_t &= tanh&(W_{hh} h_{t-1} + W_{xh} x_t + b_h), \\ o_t &= tanh&(W_{ho} h_t + b_o), \end{eqnarray*}

Parameters

Wxh	is \( W_{xh} \) matrix
bh	is \( b_{h} \) vector
Whh	is \( W_{hh} \) matrix
Who	is \( W_{xo} \) matrix
bo	is \( b_{o} \) vector

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

dnn/include/opencv2/dnn/all_layers.hpp

Public Member Functions

Static Public Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation

§ create()

§ setProduceHiddenOutput()

§ setWeights()