ArmNN
 20.02
OutputLayer Class Reference

A layer user-provided data can be bound to (e.g. inputs, outputs). More...

#include <OutputLayer.hpp>

Inheritance diagram for OutputLayer:
BindableLayer Layer IConnectableLayer

Public Member Functions

virtual std::unique_ptr< IWorkloadCreateWorkload (const IWorkloadFactory &factory) const override
 Returns nullptr for Output type. More...
 
virtual void CreateTensorHandles (const TensorHandleFactoryRegistry &registry, const IWorkloadFactory &factory, const bool IsMemoryManaged=true) override
 Set the outputs to be appropriate sub tensors of the input if sub tensors are supported otherwise creates tensor handlers by default. More...
 
OutputLayerClone (Graph &graph) const override
 Creates a dynamically-allocated copy of this layer. More...
 
void ValidateTensorShapesFromInputs () override
 Check if the input tensor shape(s) will lead to a valid configuration of OutputLayer. More...
 
void Accept (ILayerVisitor &visitor) const override
 Apply a visitor to this layer. More...
 
- Public Member Functions inherited from BindableLayer
 BindableLayer (unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, const char *name, LayerBindingId id)
 
LayerBindingId GetBindingId () const
 
- Public Member Functions inherited from Layer
 Layer (unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, const char *name)
 
 Layer (unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, DataLayout layout, const char *name)
 
const std::string & GetNameStr () const
 
const OutputHandlerGetOutputHandler (unsigned int i=0) const
 
OutputHandlerGetOutputHandler (unsigned int i=0)
 
const std::vector< InputSlot > & GetInputSlots () const
 
const std::vector< OutputSlot > & GetOutputSlots () const
 
std::vector< InputSlot >::iterator BeginInputSlots ()
 
std::vector< InputSlot >::iterator EndInputSlots ()
 
std::vector< OutputSlot >::iterator BeginOutputSlots ()
 
std::vector< OutputSlot >::iterator EndOutputSlots ()
 
bool IsOutputUnconnected ()
 
void ResetPriority () const
 
LayerPriority GetPriority () const
 
LayerType GetType () const
 
DataType GetDataType () const
 
const BackendIdGetBackendId () const
 
void SetBackendId (const BackendId &id)
 
void VerifyLayerConnections (unsigned int expectedConnections, const CheckLocation &location) const
 
std::vector< TensorShapeInferOutputShapes (const std::vector< TensorShape > &inputShapes) const override
 Infer the shape of the output(s) based on the provided input shape(s) More...
 
virtual void SerializeLayerParameters (ParameterStringifyFunction &fn) const
 Helper to serialize the layer parameters to string. More...
 
virtual void ReleaseConstantData ()
 
template<typename Op >
void OperateOnConstantTensors (Op op)
 
const char * GetName () const override
 Returns the name of the layer. More...
 
unsigned int GetNumInputSlots () const override
 Returns the number of connectable input slots. More...
 
unsigned int GetNumOutputSlots () const override
 Returns the number of connectable output slots. More...
 
const InputSlotGetInputSlot (unsigned int index) const override
 Get a const input slot handle by slot index. More...
 
InputSlotGetInputSlot (unsigned int index) override
 Get the input slot handle by slot index. More...
 
const OutputSlotGetOutputSlot (unsigned int index=0) const override
 Get the const output slot handle by slot index. More...
 
OutputSlotGetOutputSlot (unsigned int index=0) override
 Get the output slot handle by slot index. More...
 
void SetGuid (LayerGuid guid)
 
LayerGuid GetGuid () const final
 Returns the unique id of the layer. More...
 
void AddRelatedLayerName (const std::string layerName)
 
const std::list< std::string > & GetRelatedLayerNames ()
 
virtual void Reparent (Graph &dest, std::list< Layer *>::const_iterator iterator)=0
 
void BackendSelectionHint (Optional< BackendId > backend) final
 Provide a hint for the optimizer as to which backend to prefer for this layer. More...
 
Optional< BackendIdGetBackendHint () const
 

Protected Member Functions

 OutputLayer (LayerBindingId id, const char *name)
 Constructor to create an OutputLayer. More...
 
 ~OutputLayer ()=default
 Default destructor. More...
 
- Protected Member Functions inherited from BindableLayer
 ~BindableLayer ()=default
 
- Protected Member Functions inherited from Layer
virtual ~Layer ()=default
 
template<typename QueueDescriptor >
void CollectQueueDescriptorInputs (QueueDescriptor &descriptor, WorkloadInfo &info) const
 
template<typename QueueDescriptor >
void CollectQueueDescriptorOutputs (QueueDescriptor &descriptor, WorkloadInfo &info) const
 
template<typename QueueDescriptor >
WorkloadInfo PrepInfoAndDesc (QueueDescriptor &descriptor) const
 Helper function to reduce duplication in *LayerCreateWorkload. More...
 
template<typename LayerType , typename ... Params>
LayerTypeCloneBase (Graph &graph, Params &&... params) const
 
virtual ConstantTensors GetConstantTensorsByRef ()
 
- Protected Member Functions inherited from IConnectableLayer
 ~IConnectableLayer ()
 Objects are not deletable via the handle. More...
 

Additional Inherited Members

- Protected Types inherited from Layer
using ConstantTensors = std::vector< std::reference_wrapper< std::unique_ptr< ScopedCpuTensorHandle > >>
 
- Protected Attributes inherited from Layer
std::vector< OutputHandlerm_OutputHandlers
 

Detailed Description

A layer user-provided data can be bound to (e.g. inputs, outputs).

Definition at line 13 of file OutputLayer.hpp.

Constructor & Destructor Documentation

◆ OutputLayer()

OutputLayer ( LayerBindingId  id,
const char *  name 
)
protected

Constructor to create an OutputLayer.

Parameters
idThe layer binding id number.
nameOptional name for the layer.

Definition at line 16 of file OutputLayer.cpp.

References armnn::Output.

Referenced by OutputLayer::CreateTensorHandles().

17  : BindableLayer(1, 0, LayerType::Output, name, id)
18 {
19 }
BindableLayer(unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, const char *name, LayerBindingId id)
Definition: Layer.hpp:396

◆ ~OutputLayer()

~OutputLayer ( )
protecteddefault

Default destructor.

Referenced by OutputLayer::CreateTensorHandles().

Member Function Documentation

◆ Accept()

void Accept ( ILayerVisitor visitor) const
overridevirtual

Apply a visitor to this layer.

Implements IConnectableLayer.

Definition at line 39 of file OutputLayer.cpp.

References BindableLayer::GetBindingId(), Layer::GetName(), and ILayerVisitor::VisitOutputLayer().

Referenced by OutputLayer::CreateTensorHandles().

40 {
41  visitor.VisitOutputLayer(this, GetBindingId(), GetName());
42 }
LayerBindingId GetBindingId() const
Definition: Layer.hpp:406
const char * GetName() const override
Returns the name of the layer.
Definition: Layer.hpp:305

◆ Clone()

OutputLayer * Clone ( Graph graph) const
overridevirtual

Creates a dynamically-allocated copy of this layer.

Parameters
[in]graphThe graph into which this layer is being cloned.

Implements Layer.

Definition at line 27 of file OutputLayer.cpp.

References BindableLayer::GetBindingId(), and Layer::GetName().

Referenced by OutputLayer::CreateTensorHandles().

28 {
29  return CloneBase<OutputLayer>(graph, GetBindingId(), GetName());
30 }
LayerBindingId GetBindingId() const
Definition: Layer.hpp:406
const char * GetName() const override
Returns the name of the layer.
Definition: Layer.hpp:305

◆ CreateTensorHandles()

virtual void CreateTensorHandles ( const TensorHandleFactoryRegistry registry,
const IWorkloadFactory factory,
const bool  IsMemoryManaged = true 
)
inlineoverridevirtual

Set the outputs to be appropriate sub tensors of the input if sub tensors are supported otherwise creates tensor handlers by default.

Ignores parameters for Output type.

Parameters
[in]registryContains all the registered tensor handle factories available for use.
[in]factoryThe workload factory which will create the workload.
[in]IsMemoryManagedDetermine whether or not to assign a memory manager during creation

Reimplemented from Layer.

Definition at line 27 of file OutputLayer.hpp.

References OutputLayer::Accept(), OutputLayer::Clone(), armnn::IgnoreUnused(), OutputLayer::OutputLayer(), OutputLayer::ValidateTensorShapesFromInputs(), and OutputLayer::~OutputLayer().

30  {
31  IgnoreUnused(registry, factory, IsMemoryManaged);
32  }
void IgnoreUnused(Ts &&...)

◆ CreateWorkload()

std::unique_ptr< IWorkload > CreateWorkload ( const IWorkloadFactory factory) const
overridevirtual

Returns nullptr for Output type.

Parameters
[in]graphThe graph where this layer can be found.
[in]factoryThe workload factory which will create the workload.
Returns
A pointer to the created workload, or nullptr if not created.

Implements Layer.

Definition at line 21 of file OutputLayer.cpp.

References armnn::IgnoreUnused().

22 {
23  IgnoreUnused(factory);
24  return nullptr;
25 }
void IgnoreUnused(Ts &&...)

◆ ValidateTensorShapesFromInputs()

void ValidateTensorShapesFromInputs ( )
overridevirtual

Check if the input tensor shape(s) will lead to a valid configuration of OutputLayer.

Implements Layer.

Definition at line 32 of file OutputLayer.cpp.

References InputSlot::GetConnection(), and Layer::GetInputSlot().

Referenced by OutputLayer::CreateTensorHandles().

33 {
34  // Just validates that the input is connected.
35  ConditionalThrow<LayerValidationException>(GetInputSlot(0).GetConnection() != nullptr,
36  "OutputLayer: Input slot must be connected.");
37 }
const IOutputSlot * GetConnection() const override
Definition: Layer.hpp:199
const InputSlot & GetInputSlot(unsigned int index) const override
Get a const input slot handle by slot index.
Definition: Layer.hpp:310

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