ArmNN
 24.02
FakeQuantizationQueueDescriptor Struct Reference

#include <WorkloadData.hpp>

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

Public Member Functions

 FakeQuantizationQueueDescriptor ()
 
void Validate (const WorkloadInfo &workloadInfo) const
 
- Public Member Functions inherited from QueueDescriptorWithParameters< FakeQuantizationDescriptor >
virtual ~QueueDescriptorWithParameters ()=default
 
- Public Member Functions inherited from QueueDescriptor
virtual ~QueueDescriptor ()=default
 
void ValidateTensorNumDimensions (const TensorInfo &tensor, std::string const &descName, unsigned int numDimensions, std::string const &tensorName) const
 
void ValidateTensorNumDimNumElem (const TensorInfo &tensorInfo, unsigned int numDimension, unsigned int numElements, std::string const &tensorName) const
 
void ValidateInputsOutputs (const std::string &descName, unsigned int numExpectedIn, unsigned int numExpectedOut) const
 
template<typename T >
const T * GetAdditionalInformation () const
 

Public Attributes

const ConstTensorHandlem_Min
 
const ConstTensorHandlem_Max
 
- Public Attributes inherited from QueueDescriptorWithParameters< FakeQuantizationDescriptor >
FakeQuantizationDescriptor m_Parameters
 
- Public Attributes inherited from QueueDescriptor
std::vector< ITensorHandle * > m_Inputs
 
std::vector< ITensorHandle * > m_Outputs
 
void * m_AdditionalInfoObject
 
bool m_AllowExpandedDims = false
 

Additional Inherited Members

- Protected Member Functions inherited from QueueDescriptorWithParameters< FakeQuantizationDescriptor >
 QueueDescriptorWithParameters ()=default
 
 QueueDescriptorWithParameters (QueueDescriptorWithParameters const &)=default
 
QueueDescriptorWithParametersoperator= (QueueDescriptorWithParameters const &)=default
 
- Protected Member Functions inherited from QueueDescriptor
 QueueDescriptor ()
 
 QueueDescriptor (QueueDescriptor const &)=default
 
QueueDescriptoroperator= (QueueDescriptor const &)=default
 

Detailed Description

Definition at line 339 of file WorkloadData.hpp.

Constructor & Destructor Documentation

◆ FakeQuantizationQueueDescriptor()

Definition at line 341 of file WorkloadData.hpp.

342  : m_Min(nullptr)
343  , m_Max(nullptr)
344  {
345  }

Member Function Documentation

◆ Validate()

void Validate ( const WorkloadInfo workloadInfo) const

Definition at line 1683 of file WorkloadData.cpp.

1684 {
1685  const std::string descriptorName{"FakeQuantizationQueueDescriptor"};
1686 
1687  ValidateNumInputs(workloadInfo, descriptorName, 1);
1688  ValidateNumOutputs(workloadInfo, descriptorName, 1);
1689 
1690  const TensorInfo& inputTensorInfo = workloadInfo.m_InputTensorInfos[0];
1691  const TensorInfo& outputTensorInfo = workloadInfo.m_OutputTensorInfos[0];
1692 
1693  ValidateTensorNumDimensions(inputTensorInfo, descriptorName, 2, "input");
1694  ValidateTensorNumDimensions(outputTensorInfo, descriptorName, 2, "output");
1695 
1696  ValidateTensorShapesMatch(inputTensorInfo, outputTensorInfo, descriptorName, "input", "output");
1697 
1699  {
1700  throw InvalidArgumentException(descriptorName + ": min cannot be greater than max");
1701  }
1702 }

References WorkloadInfo::m_InputTensorInfos, FakeQuantizationDescriptor::m_Max, FakeQuantizationDescriptor::m_Min, WorkloadInfo::m_OutputTensorInfos, QueueDescriptorWithParameters< FakeQuantizationDescriptor >::m_Parameters, and QueueDescriptor::ValidateTensorNumDimensions().

Member Data Documentation

◆ m_Max

const ConstTensorHandle* m_Max

Definition at line 348 of file WorkloadData.hpp.

◆ m_Min

const ConstTensorHandle* m_Min

Definition at line 347 of file WorkloadData.hpp.


The documentation for this struct was generated from the following files:
armnn::TensorInfo
Definition: Tensor.hpp:152
armnn::FakeQuantizationDescriptor::m_Max
float m_Max
Maximum value.
Definition: Descriptors.hpp:921
armnn::WorkloadInfo::m_OutputTensorInfos
std::vector< TensorInfo > m_OutputTensorInfos
Definition: WorkloadInfo.hpp:19
armnn::QueueDescriptorWithParameters< FakeQuantizationDescriptor >::m_Parameters
FakeQuantizationDescriptor m_Parameters
Definition: WorkloadData.hpp:66
armnn::FakeQuantizationQueueDescriptor::m_Min
const ConstTensorHandle * m_Min
Definition: WorkloadData.hpp:347
armnn::InvalidArgumentException
Definition: Exceptions.hpp:80
armnn::WorkloadInfo::m_InputTensorInfos
std::vector< TensorInfo > m_InputTensorInfos
Definition: WorkloadInfo.hpp:18
armnn::QueueDescriptor::ValidateTensorNumDimensions
void ValidateTensorNumDimensions(const TensorInfo &tensor, std::string const &descName, unsigned int numDimensions, std::string const &tensorName) const
Definition: WorkloadData.cpp:397
armnn::FakeQuantizationDescriptor::m_Min
float m_Min
Minimum value.
Definition: Descriptors.hpp:919
armnn::FakeQuantizationQueueDescriptor::m_Max
const ConstTensorHandle * m_Max
Definition: WorkloadData.hpp:348