ArmNN
 24.08
QuantizedLstmLayer Class Reference

This layer represents a QuantizedLstm operation. More...

#include <QuantizedLstmLayer.hpp>

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

Public Member Functions

virtual std::unique_ptr< IWorkloadCreateWorkload (const IWorkloadFactory &factory) const override
 Makes a workload for the QuantizedLstm type. More...
 
QuantizedLstmLayerClone (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 QuantizedLstmLayer. 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...
 
- 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
 
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
 
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...
 

Public Attributes

QuantizedLstmParameters m_QuantizedLstmParameters
 

Protected Member Functions

 QuantizedLstmLayer (const char *name)
 Constructor to create a QuantizedLstmLayer. More...
 
 ~QuantizedLstmLayer ()=default
 Default destructor. More...
 
Layer::ImmutableConstantTensors GetConstantTensorsByRef () const override
 Retrieve the handles to the constant values stored by the layer. More...
 
- 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 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 Layer
AdditionalInfoObjectPtr m_AdditionalInfoObject
 
std::vector< OutputHandlerm_OutputHandlers
 
ShapeInferenceMethod m_ShapeInferenceMethod
 

Detailed Description

This layer represents a QuantizedLstm operation.

Definition at line 45 of file QuantizedLstmLayer.hpp.

Constructor & Destructor Documentation

◆ QuantizedLstmLayer()

QuantizedLstmLayer ( const char *  name)
protected

Constructor to create a QuantizedLstmLayer.

Parameters
[in]nameOptional name for the layer.

Definition at line 17 of file QuantizedLstmLayer.cpp.

18  : Layer(3, 2, LayerType::QuantizedLstm, name)
19 {
20 }

References armnn::QuantizedLstm.

◆ ~QuantizedLstmLayer()

~QuantizedLstmLayer ( )
protecteddefault

Default destructor.

Member Function Documentation

◆ Clone()

QuantizedLstmLayer * 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 47 of file QuantizedLstmLayer.cpp.

48 {
49  auto layer = CloneBase<QuantizedLstmLayer>(graph, GetName());
50 
51  layer->m_QuantizedLstmParameters.m_InputToInputWeights = m_QuantizedLstmParameters.m_InputToInputWeights ?
53  layer->m_QuantizedLstmParameters.m_InputToForgetWeights = m_QuantizedLstmParameters.m_InputToForgetWeights ?
55  layer->m_QuantizedLstmParameters.m_InputToCellWeights = m_QuantizedLstmParameters.m_InputToCellWeights ?
57  layer->m_QuantizedLstmParameters.m_InputToOutputWeights = m_QuantizedLstmParameters.m_InputToOutputWeights ?
59 
60  layer->m_QuantizedLstmParameters.m_RecurrentToInputWeights = m_QuantizedLstmParameters.m_RecurrentToInputWeights ?
62  layer->m_QuantizedLstmParameters.m_RecurrentToForgetWeights = m_QuantizedLstmParameters.m_RecurrentToForgetWeights
64  layer->m_QuantizedLstmParameters.m_RecurrentToCellWeights = m_QuantizedLstmParameters.m_RecurrentToCellWeights ?
66  layer->m_QuantizedLstmParameters.m_RecurrentToOutputWeights = m_QuantizedLstmParameters.m_RecurrentToOutputWeights
68 
69  layer->m_QuantizedLstmParameters.m_InputGateBias = m_QuantizedLstmParameters.m_InputGateBias ?
71  layer->m_QuantizedLstmParameters.m_ForgetGateBias = m_QuantizedLstmParameters.m_ForgetGateBias ?
73  layer->m_QuantizedLstmParameters.m_CellBias = m_QuantizedLstmParameters.m_CellBias ?
75  layer->m_QuantizedLstmParameters.m_OutputGateBias = m_QuantizedLstmParameters.m_OutputGateBias ?
77 
78  return std::move(layer);
79 }

References Layer::GetName(), QuantizedLstmParameters::m_CellBias, QuantizedLstmParameters::m_ForgetGateBias, QuantizedLstmParameters::m_InputGateBias, QuantizedLstmParameters::m_InputToCellWeights, QuantizedLstmParameters::m_InputToForgetWeights, QuantizedLstmParameters::m_InputToInputWeights, QuantizedLstmParameters::m_InputToOutputWeights, QuantizedLstmParameters::m_OutputGateBias, QuantizedLstmLayer::m_QuantizedLstmParameters, QuantizedLstmParameters::m_RecurrentToCellWeights, QuantizedLstmParameters::m_RecurrentToForgetWeights, QuantizedLstmParameters::m_RecurrentToInputWeights, and QuantizedLstmParameters::m_RecurrentToOutputWeights.

◆ CreateWorkload()

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

Makes a workload for the QuantizedLstm 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 QuantizedLstmLayer.cpp.

23 {
24  QuantizedLstmQueueDescriptor descriptor;
25 
26  // QuantizedLstmLayer parameters - there are no optional params
27  descriptor.m_InputToInputWeights = m_QuantizedLstmParameters.m_InputToInputWeights.get();
28  descriptor.m_InputToForgetWeights = m_QuantizedLstmParameters.m_InputToForgetWeights.get();
29  descriptor.m_InputToCellWeights = m_QuantizedLstmParameters.m_InputToCellWeights.get();
30  descriptor.m_InputToOutputWeights = m_QuantizedLstmParameters.m_InputToOutputWeights.get();
31 
32  descriptor.m_RecurrentToInputWeights = m_QuantizedLstmParameters.m_RecurrentToInputWeights.get();
33  descriptor.m_RecurrentToForgetWeights = m_QuantizedLstmParameters.m_RecurrentToForgetWeights.get();
34  descriptor.m_RecurrentToCellWeights = m_QuantizedLstmParameters.m_RecurrentToCellWeights.get();
35  descriptor.m_RecurrentToOutputWeights = m_QuantizedLstmParameters.m_RecurrentToOutputWeights.get();
36 
37  descriptor.m_InputGateBias = m_QuantizedLstmParameters.m_InputGateBias.get();
38  descriptor.m_ForgetGateBias = m_QuantizedLstmParameters.m_ForgetGateBias.get();
39  descriptor.m_CellBias = m_QuantizedLstmParameters.m_CellBias.get();
40  descriptor.m_OutputGateBias = m_QuantizedLstmParameters.m_OutputGateBias.get();
41 
42  SetAdditionalInfo(descriptor);
43 
44  return factory.CreateWorkload(LayerType::QuantizedLstm, descriptor, PrepInfoAndDesc(descriptor));
45 }

References IWorkloadFactory::CreateWorkload(), QuantizedLstmParameters::m_CellBias, QuantizedLstmQueueDescriptor::m_CellBias, QuantizedLstmParameters::m_ForgetGateBias, QuantizedLstmQueueDescriptor::m_ForgetGateBias, QuantizedLstmParameters::m_InputGateBias, QuantizedLstmQueueDescriptor::m_InputGateBias, QuantizedLstmParameters::m_InputToCellWeights, QuantizedLstmQueueDescriptor::m_InputToCellWeights, QuantizedLstmParameters::m_InputToForgetWeights, QuantizedLstmQueueDescriptor::m_InputToForgetWeights, QuantizedLstmParameters::m_InputToInputWeights, QuantizedLstmQueueDescriptor::m_InputToInputWeights, QuantizedLstmParameters::m_InputToOutputWeights, QuantizedLstmQueueDescriptor::m_InputToOutputWeights, QuantizedLstmParameters::m_OutputGateBias, QuantizedLstmQueueDescriptor::m_OutputGateBias, QuantizedLstmLayer::m_QuantizedLstmParameters, QuantizedLstmParameters::m_RecurrentToCellWeights, QuantizedLstmQueueDescriptor::m_RecurrentToCellWeights, QuantizedLstmParameters::m_RecurrentToForgetWeights, QuantizedLstmQueueDescriptor::m_RecurrentToForgetWeights, QuantizedLstmParameters::m_RecurrentToInputWeights, QuantizedLstmQueueDescriptor::m_RecurrentToInputWeights, QuantizedLstmParameters::m_RecurrentToOutputWeights, QuantizedLstmQueueDescriptor::m_RecurrentToOutputWeights, Layer::PrepInfoAndDesc(), armnn::QuantizedLstm, and Layer::SetAdditionalInfo().

◆ ExecuteStrategy()

void ExecuteStrategy ( IStrategy strategy) const
overridevirtual

Apply a visitor to this layer.

Reimplemented from Layer.

Definition at line 239 of file QuantizedLstmLayer.cpp.

240 {
241  std::vector<ConstTensor> constTensors;
242 
243  ManagedConstTensorHandle managedInputToInputWeights(m_QuantizedLstmParameters.m_InputToInputWeights);
244  ManagedConstTensorHandle managedInputToForgetWeights(m_QuantizedLstmParameters.m_InputToForgetWeights);
245  ManagedConstTensorHandle managedInputToCellWeights(m_QuantizedLstmParameters.m_InputToCellWeights);
246  ManagedConstTensorHandle managedInputToOutputWeights(m_QuantizedLstmParameters.m_InputToOutputWeights);
247 
248  ManagedConstTensorHandle managedRecurrentToInputWeights(m_QuantizedLstmParameters.m_RecurrentToInputWeights);
249  ManagedConstTensorHandle managedRecurrentToForgetWeights(m_QuantizedLstmParameters.m_RecurrentToForgetWeights);
250  ManagedConstTensorHandle managedRecurrentToCellWeights(m_QuantizedLstmParameters.m_RecurrentToCellWeights);
251  ManagedConstTensorHandle managedRecurrentToOutputWeights(m_QuantizedLstmParameters.m_RecurrentToOutputWeights);
252 
253  ManagedConstTensorHandle managedInputGateBias(m_QuantizedLstmParameters.m_InputGateBias);
254  ManagedConstTensorHandle managedForgetGateBias(m_QuantizedLstmParameters.m_ForgetGateBias);
255  ManagedConstTensorHandle managedCellBias(m_QuantizedLstmParameters.m_CellBias);
256  ManagedConstTensorHandle managedOutputGateBias(m_QuantizedLstmParameters.m_OutputGateBias);
257 
258  // InputToX weight tensors
260  {
261  constTensors.emplace_back(ConstTensor(managedInputToInputWeights.GetTensorInfo(),
262  managedInputToInputWeights.Map()));
263  }
264 
266  {
267  constTensors.emplace_back(ConstTensor(managedInputToForgetWeights.GetTensorInfo(),
268  managedInputToForgetWeights.Map()));
269  }
270 
272  {
273  constTensors.emplace_back(ConstTensor(managedInputToCellWeights.GetTensorInfo(),
274  managedInputToCellWeights.Map()));
275  }
276 
278  {
279  constTensors.emplace_back(ConstTensor(managedInputToOutputWeights.GetTensorInfo(),
280  managedInputToOutputWeights.Map()));
281  }
282 
283  // RecurrentToX weight tensors
285  {
286  constTensors.emplace_back(ConstTensor(
287  managedRecurrentToInputWeights.GetTensorInfo(),
288  managedRecurrentToInputWeights.Map()));
289  }
290 
292  {
293  constTensors.emplace_back(ConstTensor(
294  managedRecurrentToForgetWeights.GetTensorInfo(),
295  managedRecurrentToForgetWeights.Map()));
296  }
297 
299  {
300  constTensors.emplace_back(ConstTensor(
301  managedRecurrentToCellWeights.GetTensorInfo(),
302  managedRecurrentToCellWeights.Map()));
303  }
304 
306  {
307  constTensors.emplace_back(ConstTensor(
308  managedRecurrentToOutputWeights.GetTensorInfo(),
309  managedRecurrentToOutputWeights.Map()));
310  }
311 
312  // Bias tensors
314  {
315  constTensors.emplace_back(ConstTensor(managedInputGateBias.GetTensorInfo(),
316  managedInputGateBias.Map()));
317  }
318 
320  {
321  constTensors.emplace_back(ConstTensor(managedForgetGateBias.GetTensorInfo(),
322  managedForgetGateBias.Map()));
323  }
324 
325  if (m_QuantizedLstmParameters.m_CellBias != nullptr)
326  {
327  constTensors.emplace_back(ConstTensor(managedCellBias.GetTensorInfo(),
328  managedCellBias.Map()));
329  }
330 
332  {
333  constTensors.emplace_back(ConstTensor(managedOutputGateBias.GetTensorInfo(),
334  managedOutputGateBias.Map()));
335  }
336 
337 
338  strategy.ExecuteStrategy(this, BaseDescriptor(), constTensors, GetName());
339 }

References IStrategy::ExecuteStrategy(), Layer::GetName(), ManagedConstTensorHandle::GetTensorInfo(), QuantizedLstmParameters::m_CellBias, QuantizedLstmParameters::m_ForgetGateBias, QuantizedLstmParameters::m_InputGateBias, QuantizedLstmParameters::m_InputToCellWeights, QuantizedLstmParameters::m_InputToForgetWeights, QuantizedLstmParameters::m_InputToInputWeights, QuantizedLstmParameters::m_InputToOutputWeights, QuantizedLstmParameters::m_OutputGateBias, QuantizedLstmLayer::m_QuantizedLstmParameters, QuantizedLstmParameters::m_RecurrentToCellWeights, QuantizedLstmParameters::m_RecurrentToForgetWeights, QuantizedLstmParameters::m_RecurrentToInputWeights, QuantizedLstmParameters::m_RecurrentToOutputWeights, and ManagedConstTensorHandle::Map().

◆ 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 217 of file QuantizedLstmLayer.cpp.

References QuantizedLstmParameters::m_CellBias, QuantizedLstmParameters::m_ForgetGateBias, QuantizedLstmParameters::m_InputGateBias, QuantizedLstmParameters::m_InputToCellWeights, QuantizedLstmParameters::m_InputToForgetWeights, QuantizedLstmParameters::m_InputToInputWeights, QuantizedLstmParameters::m_InputToOutputWeights, QuantizedLstmParameters::m_OutputGateBias, QuantizedLstmLayer::m_QuantizedLstmParameters, QuantizedLstmParameters::m_RecurrentToCellWeights, QuantizedLstmParameters::m_RecurrentToForgetWeights, QuantizedLstmParameters::m_RecurrentToInputWeights, and QuantizedLstmParameters::m_RecurrentToOutputWeights.

◆ 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 81 of file QuantizedLstmLayer.cpp.

82 {
83  if (inputShapes.size() != 3)
84  {
85  throw armnn::Exception("inputShapes' size is \"" + std::to_string(inputShapes.size()) +
86  "\" - should be \"3\".");
87  }
88 
89  // Get input values for validation
90  unsigned int numBatches = inputShapes[0][0];
91  unsigned int outputSize = inputShapes[1][1];
92 
93  std::vector<TensorShape> outShapes;
94  outShapes.push_back(TensorShape({numBatches, outputSize})); // cellStateOut
95  outShapes.push_back(TensorShape({numBatches, outputSize})); // output
96 
97  return outShapes;
98 }

Referenced by QuantizedLstmLayer::ValidateTensorShapesFromInputs().

◆ ValidateTensorShapesFromInputs()

void ValidateTensorShapesFromInputs ( )
overridevirtual

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

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

Implements Layer.

Definition at line 100 of file QuantizedLstmLayer.cpp.

101 {
103 
104  const TensorShape& outputShape = GetOutputSlot(0).GetTensorInfo().GetShape();
105 
107 
108  auto inferredShapes = InferOutputShapes(
109  {
110  GetInputSlot(0).GetTensorInfo().GetShape(), // input
111  GetInputSlot(1).GetTensorInfo().GetShape(), // previousCellStateIn
112  GetInputSlot(2).GetTensorInfo().GetShape() // previousOutputIn
113  });
114 
115  if (inferredShapes.size() != 2)
116  {
117  throw armnn::LayerValidationException("inferredShapes has "
118  + std::to_string(inferredShapes.size()) +
119  " element(s) - should only have 2.");
120  }
121 
122  // Check weights and bias for nullptr
124  {
125  throw armnn::LayerValidationException("QuantizedLstmLayer: "
126  "m_QuantizedLstmParameters.m_InputToInputWeights "
127  "should not be null.");
128  }
129 
131  {
132  throw armnn::LayerValidationException("QuantizedLstmLayer: "
133  "m_QuantizedLstmParameters.m_InputToForgetWeights "
134  "should not be null.");
135  }
136 
138  {
139  throw armnn::LayerValidationException("QuantizedLstmLayer: "
140  "m_QuantizedLstmParameters.m_InputToCellWeights "
141  "should not be null.");
142  }
143 
145  {
146  throw armnn::LayerValidationException("QuantizedLstmLayer: "
147  "m_QuantizedLstmParameters.m_InputToOutputWeights "
148  "should not be null.");
149  }
150 
152  {
153  throw armnn::LayerValidationException("QuantizedLstmLayer: "
154  "m_QuantizedLstmParameters.m_RecurrentToInputWeights "
155  "should not be null.");
156  }
157 
159  {
160  throw armnn::LayerValidationException("QuantizedLstmLayer: "
161  "m_QuantizedLstmParameters.m_RecurrentToForgetWeights "
162  "should not be null.");
163  }
164 
166  {
167  throw armnn::LayerValidationException("QuantizedLstmLayer: "
168  "m_QuantizedLstmParameters.m_RecurrentToCellWeights "
169  "should not be null.");
170  }
171 
173  {
174  throw armnn::LayerValidationException("QuantizedLstmLayer: "
175  "m_QuantizedLstmParameters.m_RecurrentToOutputWeights "
176  "should not be null.");
177  }
178 
180  {
181  throw armnn::LayerValidationException("QuantizedLstmLayer: "
182  "m_QuantizedLstmParameters.m_InputGateBias "
183  "should not be null.");
184  }
185 
187  {
188  throw armnn::LayerValidationException("QuantizedLstmLayer: "
189  "m_QuantizedLstmParameters.m_ForgetGateBias "
190  "should not be null.");
191  }
192 
194  {
195  throw armnn::LayerValidationException("QuantizedLstmLayer: "
196  "m_QuantizedLstmParameters.m_CellBias "
197  "should not be null.");
198  }
199 
201  {
202  throw armnn::LayerValidationException("QuantizedLstmLayer: "
203  "m_QuantizedLstmParameters.m_OutputGateBias "
204  "should not be null.");
205  }
206 
207  // Check output TensorShape(s) match inferred shape
208  ValidateAndCopyShape(outputShape, inferredShapes[0], m_ShapeInferenceMethod, "QuantizedLstmLayer");
209 
211  inferredShapes[1],
213  "QuantizedLstmLayer",
214  1);
215 }

References CHECK_LOCATION, Layer::GetInputSlot(), Layer::GetOutputSlot(), TensorInfo::GetShape(), armnn::GetTensorInfo(), InputSlot::GetTensorInfo(), OutputSlot::GetTensorInfo(), QuantizedLstmLayer::InferOutputShapes(), QuantizedLstmParameters::m_CellBias, QuantizedLstmParameters::m_ForgetGateBias, QuantizedLstmParameters::m_InputGateBias, QuantizedLstmParameters::m_InputToCellWeights, QuantizedLstmParameters::m_InputToForgetWeights, QuantizedLstmParameters::m_InputToInputWeights, QuantizedLstmParameters::m_InputToOutputWeights, QuantizedLstmParameters::m_OutputGateBias, QuantizedLstmLayer::m_QuantizedLstmParameters, QuantizedLstmParameters::m_RecurrentToCellWeights, QuantizedLstmParameters::m_RecurrentToForgetWeights, QuantizedLstmParameters::m_RecurrentToInputWeights, QuantizedLstmParameters::m_RecurrentToOutputWeights, Layer::m_ShapeInferenceMethod, Layer::ValidateAndCopyShape(), Layer::VerifyLayerConnections(), and Layer::VerifyShapeInferenceType().

Member Data Documentation

◆ m_QuantizedLstmParameters


The documentation for this class was generated from the following files:
armnn::QuantizedLstmParameters::m_InputToInputWeights
std::shared_ptr< ConstTensorHandle > m_InputToInputWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, inputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:17
armnn::QuantizedLstmParameters::m_CellBias
std::shared_ptr< ConstTensorHandle > m_CellBias
A unique pointer to represent 1D bias tensor with dimensions [outputSize] (int32).
Definition: QuantizedLstmLayer.hpp:39
armnn::OutputSlot::GetTensorInfo
const TensorInfo & GetTensorInfo() const override
Definition: Layer.cpp:100
armnn::QuantizedLstmParameters::m_OutputGateBias
std::shared_ptr< ConstTensorHandle > m_OutputGateBias
A unique pointer to represent 1D bias tensor with dimensions [outputSize] (int32).
Definition: QuantizedLstmLayer.hpp:41
CHECK_LOCATION
#define CHECK_LOCATION()
Definition: Exceptions.hpp:203
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::LayerType::QuantizedLstm
@ QuantizedLstm
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::Layer::Layer
Layer(unsigned int numInputSlots, unsigned int numOutputSlots, LayerType type, const char *name)
Definition: Layer.cpp:260
armnn::Layer::GetName
const char * GetName() const override
Returns the name of the layer.
Definition: Layer.hpp:332
armnn::QuantizedLstmParameters::m_RecurrentToOutputWeights
std::shared_ptr< ConstTensorHandle > m_RecurrentToOutputWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, outputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:32
armnn::QuantizedLstmParameters::m_InputToForgetWeights
std::shared_ptr< ConstTensorHandle > m_InputToForgetWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, inputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:19
armnn::InputSlot::GetTensorInfo
const TensorInfo & GetTensorInfo() const override
Gets the TensorInfo for this InputSlot.
Definition: Layer.cpp:614
armnn::QuantizedLstmParameters::m_InputToCellWeights
std::shared_ptr< ConstTensorHandle > m_InputToCellWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, inputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:21
armnn::QuantizedLstmParameters::m_ForgetGateBias
std::shared_ptr< ConstTensorHandle > m_ForgetGateBias
A unique pointer to represent 1D bias tensor with dimensions [outputSize] (int32).
Definition: QuantizedLstmLayer.hpp:37
armnn::Layer::PrepInfoAndDesc
WorkloadInfo PrepInfoAndDesc(QueueDescriptor &descriptor) const
Helper function to reduce duplication in *Layer::CreateWorkload.
Definition: Layer.hpp:409
armnn::QuantizedLstmParameters::m_InputToOutputWeights
std::shared_ptr< ConstTensorHandle > m_InputToOutputWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, inputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:23
armnn::LayerValidationException
Definition: Exceptions.hpp:105
armnn::Layer::VerifyShapeInferenceType
void VerifyShapeInferenceType(const TensorShape &outputShape, ShapeInferenceMethod shapeInferenceMethod)
Definition: Layer.cpp:526
armnn::GetTensorInfo
const TensorInfo & GetTensorInfo(const ITensorHandle *tensorHandle)
float32 helpers
Definition: RefWorkloadUtils.hpp:33
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::QuantizedLstmLayer::m_QuantizedLstmParameters
QuantizedLstmParameters m_QuantizedLstmParameters
Definition: QuantizedLstmLayer.hpp:49
armnn::QuantizedLstmLayer::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: QuantizedLstmLayer.cpp:81
armnn::TensorInfo::GetShape
const TensorShape & GetShape() const
Definition: Tensor.hpp:193
armnn::QuantizedLstmParameters::m_RecurrentToCellWeights
std::shared_ptr< ConstTensorHandle > m_RecurrentToCellWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, outputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:30
armnn::Layer::VerifyLayerConnections
void VerifyLayerConnections(unsigned int expectedConnections, const CheckLocation &location) const
Definition: Layer.cpp:410
armnn::QuantizedLstmParameters::m_InputGateBias
std::shared_ptr< ConstTensorHandle > m_InputGateBias
A unique pointer to represent 1D bias tensor with dimensions [outputSize] (int32).
Definition: QuantizedLstmLayer.hpp:35
armnn::Layer::m_ShapeInferenceMethod
ShapeInferenceMethod m_ShapeInferenceMethod
Definition: Layer.hpp:441
armnn::QuantizedLstmParameters::m_RecurrentToInputWeights
std::shared_ptr< ConstTensorHandle > m_RecurrentToInputWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, outputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:26
armnn::QuantizedLstmParameters::m_RecurrentToForgetWeights
std::shared_ptr< ConstTensorHandle > m_RecurrentToForgetWeights
A unique pointer to represent 2D weights tensor with dimensions [outputSize, outputSize] (QAsymm8).
Definition: QuantizedLstmLayer.hpp:28