NeonBatchNormalizationWorkload Class Reference

#include <NeonBatchNormalizationWorkload.hpp>

Inheritance diagram for NeonBatchNormalizationWorkload:

Public Member Functions
	NeonBatchNormalizationWorkload (const BatchNormalizationQueueDescriptor &descriptor, const WorkloadInfo &info)
virtual void	Execute () const override
Public Member Functions inherited from BaseWorkload< BatchNormalizationQueueDescriptor >
	BaseWorkload (const BatchNormalizationQueueDescriptor &descriptor, const WorkloadInfo &info)
void	PostAllocationConfigure () override
const BatchNormalizationQueueDescriptor &	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< BatchNormalizationQueueDescriptor >
const BatchNormalizationQueueDescriptor	m_Data
const profiling::ProfilingGuid	m_Guid

Detailed Description

Definition at line 26 of file NeonBatchNormalizationWorkload.hpp.

Constructor & Destructor Documentation

NeonBatchNormalizationWorkload()

NeonBatchNormalizationWorkload	(	const BatchNormalizationQueueDescriptor &	descriptor,
		const WorkloadInfo &	info
	)

Definition at line 50 of file NeonBatchNormalizationWorkload.cpp.

References BaseWorkload< BatchNormalizationQueueDescriptor >::m_Data, QueueDescriptor::m_Inputs, QueueDescriptor::m_Outputs, and QueueDescriptor::ValidateInputsOutputs().

    : BaseWorkload<BatchNormalizationQueueDescriptor>(descriptor, info)
{
    m_Data.ValidateInputsOutputs("NeonBatchNormalizationWorkload", 1, 1);

    arm_compute::ITensor& input = boost::polymorphic_downcast<IAclTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
    arm_compute::ITensor& output = boost::polymorphic_downcast<IAclTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();

    arm_compute::DataLayout aclDataLayout = ConvertDataLayout(m_Data.m_Parameters.m_DataLayout);
    input.info()->set_data_layout(aclDataLayout);
    output.info()->set_data_layout(aclDataLayout);

    m_Mean = std::make_unique<arm_compute::Tensor>();
    BuildArmComputeTensor(*m_Mean, m_Data.m_Mean->GetTensorInfo());

    m_Variance = std::make_unique<arm_compute::Tensor>();
    BuildArmComputeTensor(*m_Variance, m_Data.m_Variance->GetTensorInfo());

    m_Gamma = std::make_unique<arm_compute::Tensor>();
    BuildArmComputeTensor(*m_Gamma, m_Data.m_Gamma->GetTensorInfo());

    m_Beta = std::make_unique<arm_compute::Tensor>();
    BuildArmComputeTensor(*m_Beta, m_Data.m_Beta->GetTensorInfo());

    auto layer = std::make_unique<arm_compute::NEBatchNormalizationLayer>();
    layer->configure(&input,
                     &output,
                     m_Mean.get(),
                     m_Variance.get(),
                     m_Beta.get(),
                     m_Gamma.get(),
                     m_Data.m_Parameters.m_Eps);
    m_Layer.reset(layer.release());

    InitializeArmComputeTensorData(*m_Mean, m_Data.m_Mean);
    InitializeArmComputeTensorData(*m_Variance, m_Data.m_Variance);
    InitializeArmComputeTensorData(*m_Gamma, m_Data.m_Gamma);
    InitializeArmComputeTensorData(*m_Beta, m_Data.m_Beta);

    // Force Compute Library to perform the necessary copying and reshaping, after which
    // delete all the input tensors that will no longer be needed
    m_Layer->prepare();
    FreeUnusedTensors();
}

Member Function Documentation

Execute()

void Execute ( ) const

overridevirtual

Implements IWorkload.

Definition at line 96 of file NeonBatchNormalizationWorkload.cpp.

References ARMNN_SCOPED_PROFILING_EVENT_NEON.

{
    ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonBatchNormalizationWorkload_Execute");
    m_Layer->run();
}

---

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

• src/backends/neon/workloads/NeonBatchNormalizationWorkload.hpp
• src/backends/neon/workloads/NeonBatchNormalizationWorkload.cpp