ArmNN
 24.02
TransposeConvolution2dDescriptor Struct Reference

A TransposeConvolution2dDescriptor for the TransposeConvolution2dLayer. More...

#include <Descriptors.hpp>

Inheritance diagram for TransposeConvolution2dDescriptor:
[legend]
Collaboration diagram for TransposeConvolution2dDescriptor:
[legend]

Public Member Functions

 TransposeConvolution2dDescriptor ()
 
bool operator== (const TransposeConvolution2dDescriptor &rhs) const
 
- Public Member Functions inherited from BaseDescriptor
virtual bool IsNull () const
 
virtual ~BaseDescriptor ()=default
 

Public Attributes

uint32_t m_PadLeft
 Padding left value in the width dimension. More...
 
uint32_t m_PadRight
 Padding right value in the width dimension. More...
 
uint32_t m_PadTop
 Padding top value in the height dimension. More...
 
uint32_t m_PadBottom
 Padding bottom value in the height dimension. More...
 
uint32_t m_StrideX
 Stride value when proceeding through input for the width dimension. More...
 
uint32_t m_StrideY
 Stride value when proceeding through input for the height dimension. More...
 
bool m_BiasEnabled
 Enable/disable bias. More...
 
DataLayout m_DataLayout
 The data layout to be used (NCHW, NHWC). More...
 
bool m_OutputShapeEnabled
 Output shape if it has been specified. More...
 
std::vector< unsigned int > m_OutputShape
 

Detailed Description

Constructor & Destructor Documentation

◆ TransposeConvolution2dDescriptor()

Definition at line 1442 of file Descriptors.hpp.

1442  :
1443  m_PadLeft(0),
1444  m_PadRight(0),
1445  m_PadTop(0),
1446  m_PadBottom(0),
1447  m_StrideX(0),
1448  m_StrideY(0),
1449  m_BiasEnabled(false),
1451  m_OutputShapeEnabled(false)
1452  {}

References armnn::NCHW.

Member Function Documentation

◆ operator==()

bool operator== ( const TransposeConvolution2dDescriptor rhs) const
inline

Definition at line 1454 of file Descriptors.hpp.

1455  {
1456  return m_PadLeft == rhs.m_PadLeft &&
1457  m_PadRight == rhs.m_PadRight &&
1458  m_PadTop == rhs.m_PadTop &&
1459  m_PadBottom == rhs.m_PadBottom &&
1460  m_StrideX == rhs.m_StrideX &&
1461  m_StrideY == rhs.m_StrideY &&
1462  m_BiasEnabled == rhs.m_BiasEnabled &&
1463  m_DataLayout == rhs.m_DataLayout &&
1464  m_OutputShapeEnabled == rhs.m_OutputShapeEnabled &&
1465  m_OutputShape == rhs.m_OutputShape;
1466  }

References TransposeConvolution2dDescriptor::m_BiasEnabled, TransposeConvolution2dDescriptor::m_DataLayout, TransposeConvolution2dDescriptor::m_OutputShape, TransposeConvolution2dDescriptor::m_OutputShapeEnabled, TransposeConvolution2dDescriptor::m_PadBottom, TransposeConvolution2dDescriptor::m_PadLeft, TransposeConvolution2dDescriptor::m_PadRight, TransposeConvolution2dDescriptor::m_PadTop, TransposeConvolution2dDescriptor::m_StrideX, and TransposeConvolution2dDescriptor::m_StrideY.

Member Data Documentation

◆ m_BiasEnabled

◆ m_DataLayout

◆ m_OutputShape

std::vector<unsigned int> m_OutputShape

◆ m_OutputShapeEnabled

bool m_OutputShapeEnabled

Output shape if it has been specified.

Definition at line 1485 of file Descriptors.hpp.

Referenced by TransposeConvolution2dDescriptor::operator==(), and TransposeConvolution2dLayer::ValidateTensorShapesFromInputs().

◆ m_PadBottom

◆ m_PadLeft

◆ m_PadRight

◆ m_PadTop

◆ m_StrideX

◆ m_StrideY


The documentation for this struct was generated from the following file:
armnn::TransposeConvolution2dDescriptor::m_PadLeft
uint32_t m_PadLeft
Padding left value in the width dimension.
Definition: Descriptors.hpp:1469
armnn::TransposeConvolution2dDescriptor::m_StrideX
uint32_t m_StrideX
Stride value when proceeding through input for the width dimension.
Definition: Descriptors.hpp:1477
armnn::TransposeConvolution2dDescriptor::m_PadBottom
uint32_t m_PadBottom
Padding bottom value in the height dimension.
Definition: Descriptors.hpp:1475
armnn::TransposeConvolution2dDescriptor::m_StrideY
uint32_t m_StrideY
Stride value when proceeding through input for the height dimension.
Definition: Descriptors.hpp:1479
armnn::TransposeConvolution2dDescriptor::m_OutputShape
std::vector< unsigned int > m_OutputShape
Definition: Descriptors.hpp:1486
armnn::TransposeConvolution2dDescriptor::m_PadTop
uint32_t m_PadTop
Padding top value in the height dimension.
Definition: Descriptors.hpp:1473
armnn::TransposeConvolution2dDescriptor::m_PadRight
uint32_t m_PadRight
Padding right value in the width dimension.
Definition: Descriptors.hpp:1471
armnn::TransposeConvolution2dDescriptor::m_OutputShapeEnabled
bool m_OutputShapeEnabled
Output shape if it has been specified.
Definition: Descriptors.hpp:1485
armnn::TransposeConvolution2dDescriptor::m_BiasEnabled
bool m_BiasEnabled
Enable/disable bias.
Definition: Descriptors.hpp:1481
armnn::TransposeConvolution2dDescriptor::m_DataLayout
DataLayout m_DataLayout
The data layout to be used (NCHW, NHWC).
Definition: Descriptors.hpp:1483
armnn::DataLayout::NCHW
@ NCHW