Interface with objective function and metrics. More...

#include <evaluation.hpp>

Inheritance diagram for lbann::abstract_evaluation_layer< TensorDataType >:

Collaboration diagram for lbann::abstract_evaluation_layer< TensorDataType >:

Public Types
using	EvalDataType = TensorDataType

using	CPUMatType = El::Matrix< EvalDataType, El::Device::CPU >

Public Types inherited from lbann::data_type_layer< TensorDataType >
using	InputAbsDistMatrixType = El::AbstractDistMatrix< TensorDataType >
	The tensor type expected in this object. More...

using	OutputAbsDistMatrixType = El::AbstractDistMatrix< TensorDataType >

using	InputAbsDistMatReadProxyType = El::AbstractDistMatrixReadDeviceProxy< TensorDataType, D >
	The proxy tensor type expected in this object. More...

using	OutputAbsDistMatReadProxyType = El::AbstractDistMatrixReadDeviceProxy< TensorDataType, D >

using	InputAbsMatrixType = El::AbstractMatrix< TensorDataType >
	The local tensor type expected in this object. More...

using	OutputAbsMatrixType = El::AbstractMatrix< TensorDataType >

using	WeightsProxyType = weights_proxy< TensorDataType >
	The proxy type for weights used by this object. More...

Public Member Functions
EvalType	get_scale () const

void	set_scale (EvalType scale)

EvalType	get_value (bool scaled=true)

Public Member Functions inherited from lbann::data_type_layer< TensorDataType >
	data_type_layer (lbann_comm *, bool persistent_error_signals=false)

virtual	~data_type_layer ()=default

std::string	get_datatype_name () const override

void	forward_prop () final

void	summarize_matrices (lbann_summary &summarizer, int step) override

void	check_setup () override

const OutputAbsDistMatrixType &	get_activations (const Layer &child) const override

OutputAbsDistMatrixType &	get_activations (int child_index=0)

const OutputAbsDistMatrixType &	get_activations (int child_index=0) const

const InputAbsDistMatrixType &	get_error_signals (const Layer &parent) const override

InputAbsDistMatrixType &	get_error_signals (int parent_index=0)

const InputAbsDistMatrixType &	get_error_signals (int parent_index=0) const

El::Int	current_output_mini_batch_size () const override

El::Int	infer_mini_batch_size_from_parents_or_default_to_current () const override

OutputAbsDistMatrixType &	get_temp_grad ()

InputAbsDistMatrixType &	get_branch_tag_input (int tag)

std::vector< std::unique_ptr< InputAbsDistMatrixType > > &	get_branch_tag_input_vector ()

std::vector< std::unique_ptr< OutputAbsDistMatrixType > > &	get_all_activations ()

std::vector< std::unique_ptr< InputAbsDistMatrixType > > &	get_all_prev_activations ()

std::vector< std::unique_ptr< OutputAbsDistMatrixType > > &	get_all_prev_error_signals ()

std::vector< std::unique_ptr< InputAbsDistMatrixType > > &	get_all_error_signals ()

OutputAbsMatrixType &	get_local_activations (int child_index=0)

const OutputAbsMatrixType &	get_local_activations (int child_index=0) const

InputAbsMatrixType &	get_local_error_signals (int parent_index=0)

const InputAbsMatrixType &	get_local_error_signals (int parent_index=0) const

void	set_keep_error_signals (bool) override
	Set whether to keep or dynamically reallocate error signals. More...

El::mpi::Comm &	get_subgrid_comm ()

void	serialize (ArchiveT &ar)

Public Member Functions inherited from lbann::Layer
void	write_proto (lbann_data::Layer &proto) const
	Write layer to proto file. More...

lbann_comm *	get_comm () const

int	get_grid_tag () const noexcept
	Identifying tag for process grid. More...

void	set_grid_tag (int tag)
	Set process grid. More...

bool	runs_inplace () const
	If true, the layer will run in-place (the input and output activations point to the same tensor). Value is set during graph setup (in setup_pointers) based on layer traits and neighboring layers. More...

bool	distconv_enabled () const
	Indicate whether distconv is enabled. More...

	Layer ()

virtual	~Layer ()=default

virtual Layer *	copy () const =0
	Copy function. This function dynamically allocates memory for a layer instance and instantiates a copy. The caller is responsible for deallocating the instance. More...

void	set_name (const std::string name)
	Set the layer instance's name. Each layer in a model should have a unique, preferably human-readable, name. More...

void	set_model (model *m)
	Set the model that manages this layer. More...

std::string	get_name () const
	Get the layer instance's name. More...

model *	get_model () const noexcept
	Get a reference to the model that manages this layer. More...

virtual std::string	get_type () const =0
	Get the layer type's name. More...

virtual description	get_description () const
	Human-readable description. More...

virtual data_layout	get_data_layout () const =0
	Get data layout of the data tensors. We assume that the data layouts of the previous activations, activations, previous error signals, and error signals are the same. Each concrete layer that is templated on its data layout should override this function to return its template parameter. More...

virtual El::Device	get_device_allocation () const =0
	Get the device allocation for the data tensors. We assume that the decice allocation of the previous activations, activations, previous error signals, and error signals are the same. Each concrete layer that is templated on its device allocation should override this function to return its template parameter. More...

int	get_expected_num_parent_layers () const noexcept
	Get expected number of parent layers. A negative value indicates no limit. More...

int	get_expected_num_child_layers () const noexcept
	Get expected number of child layers. A negative value indicates no limit. More...

virtual int	get_backprop_requirements () const
	Returns the necessary tensors for computing backpropagation. More...

ParallelStrategy &	get_parallel_strategy () noexcept
	Get the parallel strategy for the layer. More...

ParallelStrategy const &	get_parallel_strategy () const noexcept
	Get the parallel strategy for the layer. More...

virtual bool	can_run_inplace () const
	If True, the computation can run in-place (feeding each input activations tensor as the corresponding output activations) More...

bool	using_gpus () const noexcept
	Whether the layer is using a GPU implementation. More...

void	back_prop ()
	Backward propagation step. Given the objective function gradients w.r.t. the output tensors, compute the gradients w.r.t. the input tensors and w.r.t. the weights. This is essentially an application of the chain rule. More...

bool	update ()
	Update step. Update the layer's internal members. Note that the optimization step for the weights happens elsewhere. More...

virtual void	setup (size_t max_mini_batch_size, const std::vector< El::Grid *> &grids)
	Setup layer members. More...

void	summarize_stats (lbann_summary &summarizer, int step)

void	reset_counters ()
	Reset layer stat counters. More...

void	set_communication_flag (SubGraphCommunication type)

SubGraphCommunication	get_communication_flag ()

void	set_num_spliting_groups (El::Int spliting_groups)

El::Int	get_num_spliting_groups () const

std::shared_ptr< El::Grid >	get_mygrid () const

void	reset_inter_subgrid_vc_comm (std::shared_ptr< El::mpi::Comm > mpi_comm)

void	set_subgraph_parallelism_execution ()

bool	subgraph_parallelism_execution () const noexcept

void	set_run_layer_in_subgraph ()

bool	get_run_layer_in_subgraph () const noexcept

const Layer &	get_parent_layer (size_t index=0) const

const Layer &	get_child_layer (size_t index=0) const

std::vector< const Layer * >	get_parent_layers () const

std::vector< const Layer * >	get_child_layers () const

size_t	find_parent_layer_index (const Layer &l) const

size_t	find_child_layer_index (const Layer &l) const

int	get_num_parents () const noexcept
	Get number of parent layers. More...

int	get_num_children () const noexcept
	Get number of child layers. More...

void	add_parent_layer (ViewingLayerPtr parent)
	Add a parent layer. More...

void	add_child_layer (ViewingLayerPtr child)
	Add a child layer. More...

void	replace_parent_layer (ViewingLayerPtr l, size_t index)

void	replace_child_layer (ViewingLayerPtr l, size_t index)

void	clear_parent_layers ()
	Remove pointers to parent layers. More...

void	clear_child_layers ()
	Remove pointers to child layers. More...

ViewingLayerPtr	get_parent_layer_pointer (size_t index) const

ViewingLayerPtr	get_child_layer_pointer (size_t index) const

virtual std::vector< ViewingLayerPtr >	get_layer_pointers ()
	List of pointers to other layers. More...

virtual void	set_layer_pointers (std::vector< ViewingLayerPtr > layers)
	Set list of pointers to other layers. More...

std::vector< ViewingWeightsPtr >	get_weights_pointers () const
	List of pointers to weights. More...

void	set_weights_pointers (std::vector< ViewingWeightsPtr > ptrs)
	Set list of pointers to weights. More...

void	replace_weights (Layer const &other_layer)
	Replace weights with another Layer's weights. More...

std::vector< int >	get_input_dims (size_t input_index=0) const
	Get input tensor dimensions. More...

int	get_input_size (size_t input_index=0) const
	Get input tensor size. More...

std::vector< int >	get_output_dims (size_t output_index=0) const
	Get output tensor dimensions. More...

int	get_output_size (size_t output_index=0) const
	Get output tensor size. More...

void	set_output_dims (std::vector< int > dims, size_t output_index=0)
	Set output tensor dimensions. More...

El::Int	infer_mini_batch_size_from_parents () const

void	set_hint_layer (ViewingLayerPtr l)
	Set hint layer. More...

const Layer *	get_hint_layer () const
	Get hint layer. More...

void	freeze ()

void	unfreeze ()

bool	is_frozen () const

template<typename ArchiveT >
void	serialize (ArchiveT &ar)

Static Public Member Functions
static abstract_evaluation_layer *	construct (lbann_comm *comm, data_layout layout, El::Device device)

Protected Member Functions
	abstract_evaluation_layer (lbann_comm *comm)

	abstract_evaluation_layer ()

void	setup_dims () override
	Setup tensor dimensions Called by the 'setup' function. If there are any input tensors, the base method sets all uninitialized output tensor dimensions equal to the first input tensor dimensions. More...

void	setup_data (size_t max_mini_batch_size) override
	Setup layer data. Called by the 'setup' function. Memory is allocated for distributed matrices. More...

void	fp_compute () override
	Apply layer operation. Called by the 'forward_prop' function. Given the input tensors, the output tensors are populated with computed values. More...

void	bp_compute () override
	Compute objective funciton gradients. Called by the 'back_prop' function. Given the input, output, and gradient w.r.t. output tensors, the gradient w.r.t. input tensors are populated with the computed values and the gradients w.r.t. the weights are sent to the appropriate optimizers. More...

Serialization
template<typename ArchiveT >
void	serialize (ArchiveT &ar)

Protected Member Functions inherited from lbann::data_type_layer< TensorDataType >
InputAbsDistMatrixType &	get_prev_activations (int parent_index=0)

const InputAbsDistMatrixType &	get_prev_activations (int parent_index=0) const

OutputAbsDistMatrixType &	get_prev_error_signals (int child_index=0)

const OutputAbsDistMatrixType &	get_prev_error_signals (int child_index=0) const

const InputAbsMatrixType &	get_local_prev_activations (int parent_index=0) const

const OutputAbsMatrixType &	get_local_prev_error_signals (int child_index=0) const

void	setup_matrices (const std::vector< El::Grid * > &grids) override

void	setup_data (size_t max_mini_batch_size) override

void	fp_setup_inputs () override

void	fp_setup_outputs () override

void	bp_setup_gradient_wrt_inputs () override

void	bp_compute () override

InputAbsDistMatrixType const &	weights_values (size_t idx) const
	Get the values matrix for a specific weights object. More...

weights &	master_weights (size_t idx)
	Get a specific master weights object. More...

weights const &	master_weights (size_t idx) const

	data_type_layer (data_type_layer &&other)=default
	Protected lifecycle functions. More...

	data_type_layer (data_type_layer const &other)

data_type_layer &	operator= (data_type_layer &&other)=default

data_type_layer &	operator= (data_type_layer const &other)

Protected Member Functions inherited from lbann::Layer
void	setup_grid ()
	Setup process grid. More...

virtual void	setup_pointers ()
	Setup layer pointers. Called by the 'setup' function. Pointers to parent/child layers are assumed to be already initialized. More...

virtual void	setup_gpu ()
	Setup GPU objects. Called by the 'setup' function if the layer is on GPUs. More...

virtual bool	update_compute ()
	Perform the computation for the update step. Returns false if the layer must reset for a new training epoch. More...

	Layer (Layer &&other)=default

	Layer (Layer const &other)

Layer &	operator= (Layer &&other)=default

Layer &	operator= (Layer const &other)

void	add_weights (ViewingWeightsPtr w)

size_t	num_weights () const noexcept

bool	has_weights () const noexcept

bool	has_weights (size_t idx) const noexcept

void	set_num_weights (size_t n)

void	set_weights (size_t idx, ViewingWeightsPtr w)

weights const &	get_weights (size_t idx) const

weights &	get_weights (size_t idx)

void	add_as_gradient_source ()

void	remove_as_gradient_source ()

Private Attributes
EvalType	m_scale = 0

CPUMatType	m_value

Al::request	m_allreduce_req

Friends
class	cereal::access

Additional Inherited Members
Protected Attributes inherited from lbann::Layer
int	m_expected_num_parent_layers = 1

int	m_expected_num_child_layers = 1
	Expected number of child layers. A negative value indicates no limit. More...

model *	m_model = nullptr
	Reference to model managing this layer. More...

bool	m_frozen
	Avoid back prop if frozen. More...

EvalType	m_fp_time
	Time spent in forward propagation. More...

EvalType	m_fp_compute_time
	Time spent in the forward propagation computation. More...

EvalType	m_bp_time
	Time spent in backward propagation. More...

EvalType	m_bp_compute_time
	Time spent in the backward propagation computation. More...

EvalType	m_update_time
	Time spent in updates. More...

std::string	m_name
	Layer instance's name. Each layer in a model should have a unique, preferably human-readable, name. More...

bool	m_runs_inplace = false
	If true, the layer will run in-place (the input and output activations point to the same tensor). Value is set during graph setup (in setup_pointers) based on layer traits and neighboring layers. More...

int	m_grid_tag = -1
	Identifying tag for process grid. More...

SubGraphCommunication	subgraph_communication_method = PT2PT

bool	m_subgraph_parallelism_execution = false

bool	run_layer_in_subgraph = false

std::unique_ptr< std::set< int > >	m_subgrid_ranks

El::Int	m_num_spliting_groups = 1

std::shared_ptr< El::mpi::Comm >	m_interSubGridVCComm

Detailed Description

template<typename TensorDataType>
class lbann::abstract_evaluation_layer< TensorDataType >

Interface with objective function and metrics.

Definition at line 36 of file evaluation.hpp.

Member Typedef Documentation

◆ CPUMatType

template<typename TensorDataType >

using lbann::abstract_evaluation_layer< TensorDataType >::CPUMatType = El::Matrix<EvalDataType, El::Device::CPU>

Definition at line 44 of file evaluation.hpp.

◆ EvalDataType

template<typename TensorDataType >

using lbann::abstract_evaluation_layer< TensorDataType >::EvalDataType = TensorDataType

Definition at line 42 of file evaluation.hpp.

Constructor & Destructor Documentation

◆ abstract_evaluation_layer() [1/2]

template<typename TensorDataType >

lbann::abstract_evaluation_layer< TensorDataType >::abstract_evaluation_layer ( lbann_comm * comm )

protected

◆ abstract_evaluation_layer() [2/2]

template<typename TensorDataType >

lbann::abstract_evaluation_layer< TensorDataType >::abstract_evaluation_layer ( )

inlineprotected

Definition at line 71 of file evaluation.hpp.

Here is the call graph for this function:

Here is the caller graph for this function:

Member Function Documentation

◆ bp_compute()

template<typename TensorDataType >

void lbann::abstract_evaluation_layer< TensorDataType >::bp_compute ( )

overrideprotectedvirtual

Compute objective funciton gradients. Called by the 'back_prop' function. Given the input, output, and gradient w.r.t. output tensors, the gradient w.r.t. input tensors are populated with the computed values and the gradients w.r.t. the weights are sent to the appropriate optimizers.

Reimplemented from lbann::Layer.

Here is the caller graph for this function:

◆ construct()

template<typename TensorDataType >

static abstract_evaluation_layer* lbann::abstract_evaluation_layer< TensorDataType >::construct	(	lbann_comm *	comm,
		data_layout	layout,
		El::Device	device
	)

static

Construct an evaluation layer. The caller is responsible for deallocating the layer.

Here is the caller graph for this function:

◆ fp_compute()

template<typename TensorDataType >

void lbann::abstract_evaluation_layer< TensorDataType >::fp_compute ( )

overrideprotectedvirtual

Apply layer operation. Called by the 'forward_prop' function. Given the input tensors, the output tensors are populated with computed values.

Implements lbann::Layer.

Here is the caller graph for this function:

◆ get_scale()

template<typename TensorDataType >

EvalType lbann::abstract_evaluation_layer< TensorDataType >::get_scale ( ) const

inline

Get scaling factor.

Definition at line 48 of file evaluation.hpp.

◆ get_value()

template<typename TensorDataType >

EvalType lbann::abstract_evaluation_layer< TensorDataType >::get_value ( bool scaled = true )

Get evaluated value.

Here is the caller graph for this function:

◆ serialize()

template<typename TensorDataType >

template<typename ArchiveT >

void lbann::abstract_evaluation_layer< TensorDataType >::serialize ( ArchiveT & ar )

protected

Here is the caller graph for this function:

◆ set_scale()

template<typename TensorDataType >

void lbann::abstract_evaluation_layer< TensorDataType >::set_scale ( EvalType scale )

inline

Set scaling factor.

Definition at line 50 of file evaluation.hpp.

Here is the call graph for this function:

◆ setup_data()

template<typename TensorDataType >

void lbann::abstract_evaluation_layer< TensorDataType >::setup_data ( size_t max_mini_batch_size )

overrideprotectedvirtual

Setup layer data. Called by the 'setup' function. Memory is allocated for distributed matrices.

Reimplemented from lbann::Layer.

Here is the caller graph for this function:

◆ setup_dims()

template<typename TensorDataType >

void lbann::abstract_evaluation_layer< TensorDataType >::setup_dims ( )

overrideprotectedvirtual

Setup tensor dimensions Called by the 'setup' function. If there are any input tensors, the base method sets all uninitialized output tensor dimensions equal to the first input tensor dimensions.

Reimplemented from lbann::Layer.

Here is the caller graph for this function:

Friends And Related Function Documentation

◆ cereal::access

template<typename TensorDataType >

friend class cereal::access

friend

Definition at line 70 of file evaluation.hpp.

Member Data Documentation

◆ m_allreduce_req

template<typename TensorDataType >

Al::request lbann::abstract_evaluation_layer< TensorDataType >::m_allreduce_req

private

Non-blocking allreduce request.

Definition at line 86 of file evaluation.hpp.

◆ m_scale

template<typename TensorDataType >

EvalType lbann::abstract_evaluation_layer< TensorDataType >::m_scale = 0

private

Scaling factor to apply to evaluated value.

Definition at line 80 of file evaluation.hpp.

◆ m_value

template<typename TensorDataType >

CPUMatType lbann::abstract_evaluation_layer< TensorDataType >::m_value

private

Evaluated value. The value may be stored in pinned memory.

Definition at line 84 of file evaluation.hpp.

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

evaluation.hpp

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Private Attributes

Friends

Additional Inherited Members

Detailed Description

template<typename TensorDataType> class lbann::abstract_evaluation_layer< TensorDataType >

Member Typedef Documentation

◆ CPUMatType

◆ EvalDataType

Constructor & Destructor Documentation

◆ abstract_evaluation_layer() [1/2]

◆ abstract_evaluation_layer() [2/2]

Member Function Documentation

◆ bp_compute()

◆ construct()

◆ fp_compute()

◆ get_scale()

◆ get_value()

◆ serialize()

◆ set_scale()

◆ setup_data()

◆ setup_dims()

Friends And Related Function Documentation

◆ cereal::access

Member Data Documentation

◆ m_allreduce_req

◆ m_scale

◆ m_value

template<typename TensorDataType>
class lbann::abstract_evaluation_layer< TensorDataType >