An abstract class for implementing recurrent behavior inside of an unrolled network. This Layer type cannot be instantiated – instead, you should use one of its implementations which defines the recurrent architecture, such as RNNLayer or LSTMLayer. More...

#include <recurrent_layer.hpp>

Inheritance diagram for caffe::RecurrentLayer< Dtype >:

Public Member Functions
	RecurrentLayer (const LayerParameter &param)

virtual void	LayerSetUp (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Does layer-specific setup: your layer should implement this function as well as Reshape. More...

virtual void	Reshape (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Adjust the shapes of top blobs and internal buffers to accommodate the shapes of the bottom blobs. More...

virtual void	Reset ()

virtual const char *	type () const
	Returns the layer type.

virtual int	MinBottomBlobs () const
	Returns the minimum number of bottom blobs required by the layer, or -1 if no minimum number is required. More...

virtual int	MaxBottomBlobs () const
	Returns the maximum number of bottom blobs required by the layer, or -1 if no maximum number is required. More...

virtual int	ExactNumTopBlobs () const
	Returns the exact number of top blobs required by the layer, or -1 if no exact number is required. More...

virtual bool	AllowForceBackward (const int bottom_index) const
	Return whether to allow force_backward for a given bottom blob index. More...

Public Member Functions inherited from caffe::Layer< Dtype >
	Layer (const LayerParameter &param)

void	SetUp (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Implements common layer setup functionality. More...

Dtype	Forward (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Given the bottom blobs, compute the top blobs and the loss. More...

void	Backward (const vector< Blob< Dtype > > &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > > &bottom)
	Given the top blob error gradients, compute the bottom blob error gradients. More...

vector< shared_ptr< Blob< Dtype > > > &	blobs ()
	Returns the vector of learnable parameter blobs.

const LayerParameter &	layer_param () const
	Returns the layer parameter.

virtual void	ToProto (LayerParameter *param, bool write_diff=false)
	Writes the layer parameter to a protocol buffer.

Dtype	loss (const int top_index) const
	Returns the scalar loss associated with a top blob at a given index.

void	set_loss (const int top_index, const Dtype value)
	Sets the loss associated with a top blob at a given index.

virtual int	ExactNumBottomBlobs () const
	Returns the exact number of bottom blobs required by the layer, or -1 if no exact number is required. More...

virtual int	MinTopBlobs () const
	Returns the minimum number of top blobs required by the layer, or -1 if no minimum number is required. More...

virtual int	MaxTopBlobs () const
	Returns the maximum number of top blobs required by the layer, or -1 if no maximum number is required. More...

virtual bool	EqualNumBottomTopBlobs () const
	Returns true if the layer requires an equal number of bottom and top blobs. More...

virtual bool	AutoTopBlobs () const
	Return whether "anonymous" top blobs are created automatically by the layer. More...

bool	param_propagate_down (const int param_id)
	Specifies whether the layer should compute gradients w.r.t. a parameter at a particular index given by param_id. More...

void	set_param_propagate_down (const int param_id, const bool value)
	Sets whether the layer should compute gradients w.r.t. a parameter at a particular index given by param_id.

Protected Member Functions
virtual void	FillUnrolledNet (NetParameter *net_param) const =0
	Fills net_param with the recurrent network architecture. Subclasses should define this – see RNNLayer and LSTMLayer for examples.

virtual void	RecurrentInputBlobNames (vector< string > *names) const =0
	Fills names with the names of the 0th timestep recurrent input Blob&s. Subclasses should define this – see RNNLayer and LSTMLayer for examples.

virtual void	RecurrentInputShapes (vector< BlobShape > *shapes) const =0
	Fills shapes with the shapes of the recurrent input Blob&s. Subclasses should define this – see RNNLayer and LSTMLayer for examples.

virtual void	RecurrentOutputBlobNames (vector< string > *names) const =0
	Fills names with the names of the Tth timestep recurrent output Blob&s. Subclasses should define this – see RNNLayer and LSTMLayer for examples.

virtual void	OutputBlobNames (vector< string > *names) const =0
	Fills names with the names of the output blobs, concatenated across all timesteps. Should return a name for each top Blob. Subclasses should define this – see RNNLayer and LSTMLayer for examples.

virtual void	Forward_cpu (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)

virtual void	Forward_gpu (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Using the GPU device, compute the layer output. Fall back to Forward_cpu() if unavailable.

virtual void	Backward_cpu (const vector< Blob< Dtype > > &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > > &bottom)
	Using the CPU device, compute the gradients for any parameters and for the bottom blobs if propagate_down is true.

Protected Member Functions inherited from caffe::Layer< Dtype >
virtual void	Backward_gpu (const vector< Blob< Dtype > > &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > > &bottom)
	Using the GPU device, compute the gradients for any parameters and for the bottom blobs if propagate_down is true. Fall back to Backward_cpu() if unavailable.

virtual void	CheckBlobCounts (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)

void	SetLossWeights (const vector< Blob< Dtype > *> &top)

Protected Attributes
shared_ptr< Net< Dtype > >	unrolled_net_
	A Net to implement the Recurrent functionality.

int	N_
	The number of independent streams to process simultaneously.

int	T_
	The number of timesteps in the layer's input, and the number of timesteps over which to backpropagate through time.

bool	static_input_
	Whether the layer has a "static" input copied across all timesteps.

int	last_layer_index_
	The last layer to run in the network. (Any later layers are losses added to force the recurrent net to do backprop.)

bool	expose_hidden_
	Whether the layer's hidden state at the first and last timesteps are layer inputs and outputs, respectively.

vector< Blob< Dtype > *>	recur_input_blobs_

vector< Blob< Dtype > *>	recur_output_blobs_

vector< Blob< Dtype > *>	output_blobs_

Blob< Dtype > *	x_input_blob_

Blob< Dtype > *	x_static_input_blob_

Blob< Dtype > *	cont_input_blob_

Protected Attributes inherited from caffe::Layer< Dtype >
LayerParameter	layer_param_

Phase	phase_

vector< shared_ptr< Blob< Dtype > > >	blobs_

vector< bool >	param_propagate_down_

vector< Dtype >	loss_

Detailed Description

template<typename Dtype>
class caffe::RecurrentLayer< Dtype >

An abstract class for implementing recurrent behavior inside of an unrolled network. This Layer type cannot be instantiated – instead, you should use one of its implementations which defines the recurrent architecture, such as RNNLayer or LSTMLayer.

Member Function Documentation

◆ AllowForceBackward()

template<typename Dtype >

virtual bool caffe::RecurrentLayer< Dtype >::AllowForceBackward ( const int bottom_index ) const

inlinevirtual

Return whether to allow force_backward for a given bottom blob index.

If AllowForceBackward(i) == false, we will ignore the force_backward setting and backpropagate to blob i only if it needs gradient information (as is done when force_backward == false).

Reimplemented from caffe::Layer< Dtype >.

◆ ExactNumTopBlobs()

template<typename Dtype >

virtual int caffe::RecurrentLayer< Dtype >::ExactNumTopBlobs ( ) const

inlinevirtual

Returns the exact number of top blobs required by the layer, or -1 if no exact number is required.

This method should be overridden to return a non-negative value if your layer expects some exact number of top blobs.

Reimplemented from caffe::Layer< Dtype >.

◆ Forward_cpu()

template<typename Dtype >

void caffe::RecurrentLayer< Dtype >::Forward_cpu	(	const vector< Blob< Dtype > *> &	bottom,
		const vector< Blob< Dtype > *> &	top
	)

protectedvirtual

Parameters

bottom input Blob vector (length 2-3)

$(T \times N \times ...)$ the time-varying input . After the first two axes, whose dimensions must correspond to the number of timesteps and the number of independent streams , respectively, its dimensions may be arbitrary. Note that the ordering of dimensions – $(T \times N \times ...)$ , rather than $(N \times T \times ...)$ – means that the independent input streams must be "interleaved".
$(T \times N)$ the sequence continuation indicators $\delta$ . These inputs should be binary (0 or 1) indicators, where $\delta_{t,n} = 0$ means that timestep of stream is the beginning of a new sequence, and hence the previous hidden state $h_{t-1}$ is multiplied by $\delta_t = 0$ and has no effect on the cell's output at timestep , and a value of $\delta_{t,n} = 1$ means that timestep of stream is a continuation from the previous timestep , and the previous hidden state $h_{t-1}$ affects the updated hidden state and output.
$(N \times ...)$ (optional) the static (non-time-varying) input $x_{static}$ . After the first axis, whose dimension must be the number of independent streams, its dimensions may be arbitrary. This is mathematically equivalent to using a time-varying input of $x'_t = [x_t; x_{static}]$ – i.e., tiling the static input across the timesteps and concatenating with the time-varying input. Note that if this input is used, all timesteps in a single batch within a particular one of the streams must share the same static input, even if the sequence continuation indicators suggest that difference sequences are ending and beginning within a single batch. This may require padding and/or truncation for uniform length.

Parameters

top	output Blob vector (length 1) $(T \times N \times D)$ the time-varying output , where is `recurrent_param.num_output()`. Refer to documentation for particular RecurrentLayer implementations (such as RNNLayer and LSTMLayer) for the definition of .

Implements caffe::Layer< Dtype >.

◆ LayerSetUp()

template<typename Dtype >

void caffe::RecurrentLayer< Dtype >::LayerSetUp	(	const vector< Blob< Dtype > *> &	bottom,
		const vector< Blob< Dtype > *> &	top
	)

virtual

Does layer-specific setup: your layer should implement this function as well as Reshape.

Parameters

bottom	the preshaped input blobs, whose data fields store the input data for this layer
top	the allocated but unshaped output blobs

This method should do one-time layer specific setup. This includes reading and processing relevent parameters from the layer_param_. Setting up the shapes of top blobs and internal buffers should be done in Reshape, which will be called before the forward pass to adjust the top blob sizes.

Reimplemented from caffe::Layer< Dtype >.

◆ MaxBottomBlobs()

template<typename Dtype >

virtual int caffe::RecurrentLayer< Dtype >::MaxBottomBlobs ( ) const

inlinevirtual

Returns the maximum number of bottom blobs required by the layer, or -1 if no maximum number is required.

This method should be overridden to return a non-negative value if your layer expects some maximum number of bottom blobs.

Reimplemented from caffe::Layer< Dtype >.

◆ MinBottomBlobs()

template<typename Dtype >

virtual int caffe::RecurrentLayer< Dtype >::MinBottomBlobs ( ) const

inlinevirtual

Returns the minimum number of bottom blobs required by the layer, or -1 if no minimum number is required.

This method should be overridden to return a non-negative value if your layer expects some minimum number of bottom blobs.

Reimplemented from caffe::Layer< Dtype >.

◆ Reshape()

template<typename Dtype >

void caffe::RecurrentLayer< Dtype >::Reshape	(	const vector< Blob< Dtype > *> &	bottom,
		const vector< Blob< Dtype > *> &	top
	)

virtual

Adjust the shapes of top blobs and internal buffers to accommodate the shapes of the bottom blobs.

Parameters

bottom	the input blobs, with the requested input shapes
top	the top blobs, which should be reshaped as needed

This method should reshape top blobs as needed according to the shapes of the bottom (input) blobs, as well as reshaping any internal buffers and making any other necessary adjustments so that the layer can accommodate the bottom blobs.

Implements caffe::Layer< Dtype >.

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

include/caffe/layers/lstm_layer.hpp
include/caffe/layers/recurrent_layer.hpp
src/caffe/layers/recurrent_layer.cpp

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

template<typename Dtype> class caffe::RecurrentLayer< Dtype >

Member Function Documentation

◆ AllowForceBackward()

◆ ExactNumTopBlobs()

◆ Forward_cpu()

◆ LayerSetUp()

◆ MaxBottomBlobs()

◆ MinBottomBlobs()

◆ Reshape()

template<typename Dtype>
class caffe::RecurrentLayer< Dtype >