ArmNN
 24.02
ConvertFp32ToFp16QueueDescriptor Struct Reference

#include <WorkloadData.hpp>

Inheritance diagram for ConvertFp32ToFp16QueueDescriptor:
[legend]
Collaboration diagram for ConvertFp32ToFp16QueueDescriptor:
[legend]

Public Member Functions

void Validate (const WorkloadInfo &workloadInfo) const
 
- 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
 

Additional Inherited Members

- Public Attributes inherited from QueueDescriptor
std::vector< ITensorHandle * > m_Inputs
 
std::vector< ITensorHandle * > m_Outputs
 
void * m_AdditionalInfoObject
 
bool m_AllowExpandedDims = false
 
- Protected Member Functions inherited from QueueDescriptor
 QueueDescriptor ()
 
 QueueDescriptor (QueueDescriptor const &)=default
 
QueueDescriptoroperator= (QueueDescriptor const &)=default
 

Detailed Description

Definition at line 457 of file WorkloadData.hpp.

Member Function Documentation

◆ Validate()

void Validate ( const WorkloadInfo workloadInfo) const

Definition at line 2281 of file WorkloadData.cpp.

2282 {
2283  const std::string descriptorName{"ConvertFp32ToFp16QueueDescriptor"};
2284 
2285  ValidateNumInputs(workloadInfo, descriptorName, 1);
2286  ValidateNumOutputs(workloadInfo, descriptorName, 1);
2287 
2288  const TensorInfo& inputTensorInfo = workloadInfo.m_InputTensorInfos[0];
2289  const TensorInfo& outputTensorInfo = workloadInfo.m_OutputTensorInfos[0];
2290 
2291  if (inputTensorInfo.GetDataType() != DataType::Float32)
2292  {
2293  throw InvalidArgumentException(descriptorName + ": Input tensor type must be Float32.");
2294  }
2295 
2296  if (outputTensorInfo.GetDataType() != DataType::Float16)
2297  {
2298  throw InvalidArgumentException(descriptorName + ": Output tensor type must be Float16.");
2299  }
2300 
2301  ValidateTensorShapesMatch(inputTensorInfo, outputTensorInfo, descriptorName, "input", "output");
2302 }

References armnn::Float16, armnn::Float32, TensorInfo::GetDataType(), WorkloadInfo::m_InputTensorInfos, and WorkloadInfo::m_OutputTensorInfos.


The documentation for this struct was generated from the following files:
armnn::TensorInfo
Definition: Tensor.hpp:152
armnn::DataType::Float32
@ Float32
armnn::DataType::Float16
@ Float16
armnn::WorkloadInfo::m_OutputTensorInfos
std::vector< TensorInfo > m_OutputTensorInfos
Definition: WorkloadInfo.hpp:19
armnn::InvalidArgumentException
Definition: Exceptions.hpp:80
armnn::TensorInfo::GetDataType
DataType GetDataType() const
Definition: Tensor.hpp:200
armnn::WorkloadInfo::m_InputTensorInfos
std::vector< TensorInfo > m_InputTensorInfos
Definition: WorkloadInfo.hpp:18