clDNN
Public Member Functions | Static Public Member Functions | Friends | List of all members
cldnn::padding Struct Reference
C++ API » Memory description and management

Represents data padding information. More...

#include <layout.hpp>

Public Member Functions

float filling_value () const
 Filling value for padding area.
 
tensor lower_size () const
 Gets lower padding sizes. For spatials, it means size of left (X) and top (Y) padding. More...
 
tensor upper_size () const
 Gets upper padding sizes. For spatials, it means size of right (X) and bottom (Y) padding. More...
 
 padding (const std::vector< tensor::value_type > &lower_sizes, const std::vector< tensor::value_type > &upper_sizes, float filling_value=0.0f)
 
 padding (const std::vector< tensor::value_type > &sizes, float filling_value=0.0f)
 Constrcuts symmetric padding. More...
 
 padding ()
 Constructs "zero-sized" padding.
 
 padding (const cldnn_padding &other)
 Copy construction.
 
 operator cldnn_padding () const
 Implicit conversion to C API cldnn_padding.
 
 operator bool () const
 Returns true if padding size is not zero.
 

Static Public Member Functions

static padding max (padding const &lhs, padding const &rhs, float filling_value=0.0f)
 

Friends

bool operator== (const padding &lhs, const padding &rhs)
 
bool operator!= (const padding &lhs, const padding &rhs)
 
bool operator< (const padding &lhs, const padding &rhs)
 

Detailed Description

Represents data padding information.

Definition at line 125 of file layout.hpp.

Constructor & Destructor Documentation

◆ padding() [1/2]

cldnn::padding::padding ( const std::vector< tensor::value_type > &  lower_sizes,
const std::vector< tensor::value_type > &  upper_sizes,
float  filling_value = 0.0f 
)
inline
Parameters
lower_sizesTop-left padding sizes. See tensor::tensor(const std::vector<value_type>&, value_type) for details.
upper_sizesBottom-right padding sizes. See tensor::tensor(const std::vector<value_type>&, value_type) for details.
filling_valueFilling value for padding area.

Definition at line 142 of file layout.hpp.

◆ padding() [2/2]

cldnn::padding::padding ( const std::vector< tensor::value_type > &  sizes,
float  filling_value = 0.0f 
)
inline

Constrcuts symmetric padding.

Parameters
sizesTop-left and bottom-right padding sizes. See tensor::tensor(const std::vector<value_type>&, value_type) for details.
filling_valueFilling value for padding area.

Definition at line 149 of file layout.hpp.

Member Function Documentation

◆ lower_size()

tensor cldnn::padding::lower_size ( ) const
inline

Gets lower padding sizes. For spatials, it means size of left (X) and top (Y) padding.

Returns
Tensor with padding for top/left/lower bounds of data.

Definition at line 132 of file layout.hpp.

◆ upper_size()

tensor cldnn::padding::upper_size ( ) const
inline

Gets upper padding sizes. For spatials, it means size of right (X) and bottom (Y) padding.

Returns
Tensor with padding for bottom/right/upper bounds of data.

Definition at line 136 of file layout.hpp.

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