RefInstanceNormalizationWorkload Class Reference

#include <RefInstanceNormalizationWorkload.hpp>

Inheritance diagram for RefInstanceNormalizationWorkload:

Public Member Functions
	RefInstanceNormalizationWorkload (const InstanceNormalizationQueueDescriptor &descriptor, const WorkloadInfo &info)
virtual void	Execute () const override
Public Member Functions inherited from BaseWorkload< InstanceNormalizationQueueDescriptor >
	BaseWorkload (const InstanceNormalizationQueueDescriptor &descriptor, const WorkloadInfo &info)
void	PostAllocationConfigure () override
const InstanceNormalizationQueueDescriptor &	GetData () const
profiling::ProfilingGuid	GetGuid () const final
Public Member Functions inherited from IWorkload
virtual	~IWorkload ()
virtual void	RegisterDebugCallback (const DebugCallbackFunction &)

Additional Inherited Members
Protected Attributes inherited from BaseWorkload< InstanceNormalizationQueueDescriptor >
const InstanceNormalizationQueueDescriptor	m_Data
const profiling::ProfilingGuid	m_Guid

Detailed Description

Definition at line 14 of file RefInstanceNormalizationWorkload.hpp.

Constructor & Destructor Documentation

RefInstanceNormalizationWorkload()

RefInstanceNormalizationWorkload ( const InstanceNormalizationQueueDescriptor &  descriptor, const WorkloadInfo &  info  )

explicit

Definition at line 16 of file RefInstanceNormalizationWorkload.cpp.

    : BaseWorkload<InstanceNormalizationQueueDescriptor>(descriptor, info) {}

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 21 of file RefInstanceNormalizationWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT, armnn::CpuRef, armnn::GetTensorInfo(), armnn::InstanceNorm(), BaseWorkload< InstanceNormalizationQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, and QueueDescriptor::m_Outputs.

{
    ARMNN_SCOPED_PROFILING_EVENT(Compute::CpuRef, "RefInstanceNormalizationWorkload_Execute");

    std::unique_ptr<Decoder<float>> inputDecoder  = MakeDecoder<float>(GetTensorInfo(m_Data.m_Inputs[0]),
                                                                       m_Data.m_Inputs[0]->Map());
    std::unique_ptr<Encoder<float>> outputEncoder = MakeEncoder<float>(GetTensorInfo(m_Data.m_Outputs[0]),
                                                                       m_Data.m_Outputs[0]->Map());

    InstanceNorm(m_Data, *inputDecoder, *outputEncoder);
}

---

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

• src/backends/reference/workloads/RefInstanceNormalizationWorkload.hpp
• src/backends/reference/workloads/RefInstanceNormalizationWorkload.cpp