ArmNN
 20.05
PadDescriptor Struct Reference

A PadDescriptor for the PadLayer. More...

#include <Descriptors.hpp>

Public Member Functions

 PadDescriptor ()
 
 PadDescriptor (const std::vector< std::pair< unsigned int, unsigned int >> &padList, const float &padValue=0)
 
bool operator== (const PadDescriptor &rhs) const
 

Public Attributes

std::vector< std::pair< unsigned int, unsigned int > > m_PadList
 Specifies the padding for input dimension. More...
 
float m_PadValue
 Optional value to use for padding, defaults to 0. More...
 

Detailed Description

A PadDescriptor for the PadLayer.

Definition at line 913 of file Descriptors.hpp.

Constructor & Destructor Documentation

◆ PadDescriptor() [1/2]

PadDescriptor ( )
inline

Definition at line 915 of file Descriptors.hpp.

915  : m_PadValue(0)
916  {}
float m_PadValue
Optional value to use for padding, defaults to 0.

◆ PadDescriptor() [2/2]

PadDescriptor ( const std::vector< std::pair< unsigned int, unsigned int >> &  padList,
const float &  padValue = 0 
)
inline

Definition at line 918 of file Descriptors.hpp.

919  : m_PadList(padList)
920  , m_PadValue(padValue)
921  {}
float m_PadValue
Optional value to use for padding, defaults to 0.
std::vector< std::pair< unsigned int, unsigned int > > m_PadList
Specifies the padding for input dimension.

Member Function Documentation

◆ operator==()

bool operator== ( const PadDescriptor rhs) const
inline

Definition at line 923 of file Descriptors.hpp.

References PadDescriptor::m_PadList, and PadDescriptor::m_PadValue.

924  {
925  return m_PadList == rhs.m_PadList && m_PadValue == rhs.m_PadValue;
926  }
float m_PadValue
Optional value to use for padding, defaults to 0.
std::vector< std::pair< unsigned int, unsigned int > > m_PadList
Specifies the padding for input dimension.

Member Data Documentation

◆ m_PadList

std::vector<std::pair<unsigned int, unsigned int> > m_PadList

Specifies the padding for input dimension.

First is the number of values to add before the tensor in the dimension. Second is the number of values to add after the tensor in the dimension. The number of pairs should match the number of dimensions in the input tensor.

Definition at line 932 of file Descriptors.hpp.

Referenced by PadLayer::Clone(), ClPadWorkload::ClPadWorkload(), PadLayer::CreateWorkload(), NeonPadWorkload::NeonPadWorkload(), PadDescriptor::operator==(), TfLiteParser::OutputShapeOfSqueeze(), Pad2dTestCommon(), Pad3dTestCommon(), Pad4dTestCommon(), StringifyLayerParameters< PadDescriptor >::Serialize(), and SerializerVisitor::VisitPadLayer().

◆ m_PadValue

float m_PadValue

The documentation for this struct was generated from the following file: