ArmNN
 24.08
FullyConnectedLayer Class Reference

This layer represents a fully connected operation. More...

#include <FullyConnectedLayer.hpp>

Inheritance diagram for FullyConnectedLayer:
[legend]
Collaboration diagram for FullyConnectedLayer:
[legend]

Public Member Functions

virtual std::unique_ptr< IWorkloadCreateWorkload (const IWorkloadFactory &factory) const override
 Makes a workload for the FullyConnected type. More...
 
FullyConnectedLayerClone (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 FullyConnectedLayer. More...
 
std::vector< TensorShapeInferOutputShapes (const std::vector< TensorShape > &inputShapes) const override
 By default returns inputShapes if the number of inputs are equal to number of outputs, otherwise infers the output shapes from given input shapes and layer properties. More...
 
void ExecuteStrategy (IStrategy &strategy) const override
 Apply a visitor to this layer. More...
 
void ReleaseConstantData () override
 This layer does not have any data stored, weights and bias are now stored in constant layers. More...
 
- Public Member Functions inherited from LayerWithParameters< FullyConnectedDescriptor >
const FullyConnectedDescriptorGetParameters () const override
 If the layer has a descriptor return it. More...
 
void SerializeLayerParameters (ParameterStringifyFunction &fn) const override
 Helper to serialize the layer parameters to string (currently used in DotSerializer and company). More...
 
- 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)
 
ShapeInferenceMethod GetShapeInferenceMethod () const
 
bool GetAllowExpandedDims () const
 
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 override
 Returns the armnn::LayerType of this layer. More...
 
DataType GetDataType () const
 
const BackendIdGetBackendId () const
 
void SetBackendId (const BackendId &id) override
 Set the backend of the IConnectableLayer. More...
 
virtual void CreateTensorHandles (const TensorHandleFactoryRegistry &registry, const IWorkloadFactory &factory, const bool IsMemoryManaged=true)
 
void VerifyLayerConnections (unsigned int expectedConnections, const CheckLocation &location) const
 
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
 
void SetShapeInferenceMethod (ShapeInferenceMethod shapeInferenceMethod)
 
void SetAllowExpandedDims (bool allowExpandedDims)
 
template<typename T >
std::shared_ptr< T > GetAdditionalInformation () const
 
void SetAdditionalInfoForObject (const AdditionalInfoObjectPtr &additionalInfo)
 
virtual const BaseDescriptorGetParameters () const override
 If the layer has a descriptor return it. More...
 

Protected Member Functions

 FullyConnectedLayer (const FullyConnectedDescriptor &param, const char *name)
 Constructor to create a FullyConnectedLayer. More...
 
 ~FullyConnectedLayer ()=default
 Default destructor. More...
 
ImmutableConstantTensors GetConstantTensorsByRef () const override
 Retrieve the handles to the constant values stored by the layer. More...
 
- Protected Member Functions inherited from LayerWithParameters< FullyConnectedDescriptor >
 LayerWithParameters (unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, const FullyConnectedDescriptor &param, const char *name)
 
 ~LayerWithParameters ()=default
 
WorkloadInfo PrepInfoAndDesc (QueueDescriptor &descriptor) const
 Helper function to reduce duplication in *Layer::CreateWorkload. More...
 
void ExecuteStrategy (IStrategy &strategy) const override
 Apply a visitor to this layer. More...
 
Layer::ImmutableConstantTensors GetConnectedConstantAsInputTensors () const
 
- 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
 
void ValidateAndCopyShape (const TensorShape &outputShape, const TensorShape &inferredShape, const ShapeInferenceMethod shapeInferenceMethod, const std::string &layerName, const unsigned int outputSlotIndex=0)
 
void VerifyShapeInferenceType (const TensorShape &outputShape, ShapeInferenceMethod shapeInferenceMethod)
 
template<typename QueueDescriptor >
WorkloadInfo PrepInfoAndDesc (QueueDescriptor &descriptor) const
 Helper function to reduce duplication in *Layer::CreateWorkload. More...
 
template<typename LayerType , typename ... Params>
LayerTypeCloneBase (Graph &graph, Params &&... params) const
 
virtual ConstantTensors GetConstantTensorsByRef () override final
 
void SetAdditionalInfo (QueueDescriptor &descriptor) const
 
- Protected Member Functions inherited from IConnectableLayer
 ~IConnectableLayer ()
 Objects are not deletable via the handle. More...
 

Additional Inherited Members

- Public Types inherited from LayerWithParameters< FullyConnectedDescriptor >
using DescriptorType = FullyConnectedDescriptor
 
- Public Types inherited from IConnectableLayer
using ConstantTensors = std::vector< std::reference_wrapper< std::shared_ptr< ConstTensorHandle > >>
 
using ImmutableConstantTensors = std::vector< std::reference_wrapper< const std::shared_ptr< ConstTensorHandle > >>
 
- Protected Attributes inherited from LayerWithParameters< FullyConnectedDescriptor >
FullyConnectedDescriptor m_Param
 The parameters for the layer (not including tensor-valued weights etc.). More...
 
- Protected Attributes inherited from Layer
AdditionalInfoObjectPtr m_AdditionalInfoObject
 
std::vector< OutputHandlerm_OutputHandlers
 
ShapeInferenceMethod m_ShapeInferenceMethod
 

Detailed Description

This layer represents a fully connected operation.

Definition at line 15 of file FullyConnectedLayer.hpp.

Constructor & Destructor Documentation

◆ FullyConnectedLayer()

FullyConnectedLayer ( const FullyConnectedDescriptor param,
const char *  name 
)
protected

Constructor to create a FullyConnectedLayer.

Parameters
[in]paramFullyConnectedDescriptor to configure the fully connected operation.
[in]nameOptional name for the layer.

Definition at line 17 of file FullyConnectedLayer.cpp.

18  : LayerWithParameters(param.GetNumInputs(), 1, LayerType::FullyConnected, param, name)
19 {
20 }

◆ ~FullyConnectedLayer()

~FullyConnectedLayer ( )
protecteddefault

Default destructor.

Member Function Documentation

◆ Clone()

FullyConnectedLayer * 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 29 of file FullyConnectedLayer.cpp.

30 {
31  auto layer = CloneBase<FullyConnectedLayer>(graph, m_Param, GetName());
32  return std::move(layer);
33 }

References Layer::GetName(), and LayerWithParameters< FullyConnectedDescriptor >::m_Param.

◆ CreateWorkload()

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

Makes a workload for the FullyConnected 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 22 of file FullyConnectedLayer.cpp.

23 {
24  FullyConnectedQueueDescriptor descriptor;
25  SetAdditionalInfo(descriptor);
26  return factory.CreateWorkload(LayerType::FullyConnected, descriptor, PrepInfoAndDesc(descriptor));
27 }

References IWorkloadFactory::CreateWorkload(), armnn::FullyConnected, LayerWithParameters< FullyConnectedDescriptor >::PrepInfoAndDesc(), and Layer::SetAdditionalInfo().

◆ ExecuteStrategy()

void ExecuteStrategy ( IStrategy strategy) const
overridevirtual

Apply a visitor to this layer.

Reimplemented from Layer.

Definition at line 84 of file FullyConnectedLayer.cpp.

85 {
86  strategy.ExecuteStrategy(this, GetParameters(), {}, GetName());
87 }

References IStrategy::ExecuteStrategy(), Layer::GetName(), and LayerWithParameters< FullyConnectedDescriptor >::GetParameters().

◆ GetConstantTensorsByRef()

Layer::ImmutableConstantTensors GetConstantTensorsByRef ( ) const
overrideprotectedvirtual

Retrieve the handles to the constant values stored by the layer.

Returns
A vector of the constant tensors stored by this layer.

Reimplemented from Layer.

Definition at line 78 of file FullyConnectedLayer.cpp.

79 {
81  return tensors;
82 }

References LayerWithParameters< FullyConnectedDescriptor >::GetConnectedConstantAsInputTensors().

◆ InferOutputShapes()

std::vector< TensorShape > InferOutputShapes ( const std::vector< TensorShape > &  inputShapes) const
overridevirtual

By default returns inputShapes if the number of inputs are equal to number of outputs, otherwise infers the output shapes from given input shapes and layer properties.

Parameters
[in]inputShapesThe input shapes layer has.
Returns
A vector to the inferred output shape.

Reimplemented from Layer.

Definition at line 35 of file FullyConnectedLayer.cpp.

36 {
37  if (inputShapes.size() != 2)
38  {
39  throw armnn::Exception("inputShapes' size is \"" + std::to_string(inputShapes.size()) +
40  "\" - should be \"2\".");
41  }
42 
43  const TensorShape& inputShape = inputShapes[0];
44  const TensorShape weightShape = inputShapes[1];
45 
46  // Output for FC is [1, w[1]].
47  unsigned int batches = inputShape[0];
48  unsigned int dimIdx = m_Param.m_TransposeWeightMatrix ? 0 : 1;
49 
50  return std::vector<TensorShape>({ TensorShape({batches, weightShape[dimIdx]})});
51 }

References LayerWithParameters< FullyConnectedDescriptor >::m_Param, and FullyConnectedDescriptor::m_TransposeWeightMatrix.

Referenced by FullyConnectedLayer::ValidateTensorShapesFromInputs().

◆ ReleaseConstantData()

void ReleaseConstantData ( )
inlineoverridevirtual

This layer does not have any data stored, weights and bias are now stored in constant layers.

We do not want to release the data in the constant layer, that is why we override with an empty function.

Reimplemented from Layer.

Definition at line 44 of file FullyConnectedLayer.hpp.

44 {}

◆ ValidateTensorShapesFromInputs()

void ValidateTensorShapesFromInputs ( )
overridevirtual

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

Parameters
[in]shapeInferenceMethodIndicates if output shape shall be overwritten or just validate.

Implements Layer.

Definition at line 53 of file FullyConnectedLayer.cpp.

54 {
55  const TensorShape& outputShape = GetOutputSlot(0).GetTensorInfo().GetShape();
56 
58 
59  std::vector<TensorShape> inferredShapes = InferOutputShapes(
62 
63  if (inferredShapes.size() != 1)
64  {
65  throw armnn::LayerValidationException("inferredShapes has "
66  + std::to_string(inferredShapes.size()) +
67  " elements - should only have 1.");
68  }
69 
70  if (inferredShapes[0].GetDimensionality() != Dimensionality::Specified)
71  {
72  throw armnn::LayerValidationException("inferredShapes' dimensionality has not been specified.");
73  }
74 
75  ValidateAndCopyShape(outputShape, inferredShapes[0], m_ShapeInferenceMethod, "FullyConnectedLayer");
76 }

References Layer::GetInputSlot(), Layer::GetOutputSlot(), TensorInfo::GetShape(), InputSlot::GetTensorInfo(), OutputSlot::GetTensorInfo(), FullyConnectedLayer::InferOutputShapes(), Layer::m_ShapeInferenceMethod, armnn::Specified, Layer::ValidateAndCopyShape(), and Layer::VerifyShapeInferenceType().


The documentation for this class was generated from the following files:
armnn::OutputSlot::GetTensorInfo
const TensorInfo & GetTensorInfo() const override
Definition: Layer.cpp:100
armnn::FullyConnectedDescriptor::m_TransposeWeightMatrix
bool m_TransposeWeightMatrix
Enable/disable transpose weight matrix.
Definition: Descriptors.hpp:528
armnn::Layer::ValidateAndCopyShape
void ValidateAndCopyShape(const TensorShape &outputShape, const TensorShape &inferredShape, const ShapeInferenceMethod shapeInferenceMethod, const std::string &layerName, const unsigned int outputSlotIndex=0)
Definition: Layer.cpp:457
armnn::Layer::GetOutputSlot
const OutputSlot & GetOutputSlot(unsigned int index=0) const override
Get the const output slot handle by slot index.
Definition: Layer.hpp:339
armnn::Layer::GetInputSlot
const InputSlot & GetInputSlot(unsigned int index) const override
Get a const input slot handle by slot index.
Definition: Layer.hpp:337
armnn::LayerWithParameters< FullyConnectedDescriptor >::GetParameters
const FullyConnectedDescriptor & GetParameters() const override
Definition: LayerWithParameters.hpp:19
armnn::Layer::GetName
const char * GetName() const override
Returns the name of the layer.
Definition: Layer.hpp:332
armnn::IConnectableLayer::ImmutableConstantTensors
std::vector< std::reference_wrapper< const std::shared_ptr< ConstTensorHandle > >> ImmutableConstantTensors
Definition: INetwork.hpp:141
armnn::InputSlot::GetTensorInfo
const TensorInfo & GetTensorInfo() const override
Gets the TensorInfo for this InputSlot.
Definition: Layer.cpp:614
armnn::LayerWithParameters< FullyConnectedDescriptor >::GetConnectedConstantAsInputTensors
Layer::ImmutableConstantTensors GetConnectedConstantAsInputTensors() const
Definition: LayerWithParameters.hpp:59
armnn::LayerWithParameters< FullyConnectedDescriptor >::m_Param
FullyConnectedDescriptor m_Param
The parameters for the layer (not including tensor-valued weights etc.).
Definition: LayerWithParameters.hpp:52
armnn::LayerWithParameters< FullyConnectedDescriptor >::PrepInfoAndDesc
WorkloadInfo PrepInfoAndDesc(QueueDescriptor &descriptor) const
Helper function to reduce duplication in *Layer::CreateWorkload.
Definition: LayerWithParameters.hpp:44
armnn::LayerValidationException
Definition: Exceptions.hpp:105
armnn::Layer::VerifyShapeInferenceType
void VerifyShapeInferenceType(const TensorShape &outputShape, ShapeInferenceMethod shapeInferenceMethod)
Definition: Layer.cpp:526
armnn::Layer::SetAdditionalInfo
void SetAdditionalInfo(QueueDescriptor &descriptor) const
Definition: Layer.cpp:303
armnn::Exception
Base class for all ArmNN exceptions so that users can filter to just those.
Definition: Exceptions.hpp:46
armnn::LayerType::FullyConnected
@ FullyConnected
armnn::Dimensionality::Specified
@ Specified
armnn::TensorInfo::GetShape
const TensorShape & GetShape() const
Definition: Tensor.hpp:193
armnn::LayerWithParameters< FullyConnectedDescriptor >::LayerWithParameters
LayerWithParameters(unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, const FullyConnectedDescriptor &param, const char *name)
Definition: LayerWithParameters.hpp:30
armnn::Layer::m_ShapeInferenceMethod
ShapeInferenceMethod m_ShapeInferenceMethod
Definition: Layer.hpp:441
armnn::FullyConnectedLayer::InferOutputShapes
std::vector< TensorShape > InferOutputShapes(const std::vector< TensorShape > &inputShapes) const override
By default returns inputShapes if the number of inputs are equal to number of outputs,...
Definition: FullyConnectedLayer.cpp:35