cldnn::upsampling Struct Reference

Performs nearest neighbor/bilinear upsampling Also supports built-in Relu activation available by setting it in arguments. More...

#include <upsampling.hpp>

Inheritance diagram for cldnn::upsampling:

Collaboration diagram for cldnn::upsampling:

Public Types
typedef cldnn_upsampling_desc	dto

Public Member Functions
	upsampling (const primitive_id &id, const primitive_id &input, uint32_t scale, uint32_t num_filter, upsampling_sample_type sample_type, bool with_activation=false, float activation_slp=0.0f, const padding &output_padding=padding())
	Constructs upsampling primitive. More...
	upsampling (const dto *dto)
	Constructs a copy from C API cldnn_upsampling_desc.
Public Member Functions inherited from cldnn::primitive_base< upsampling, cldnn_upsampling_desc >
const cldnn_primitive_desc *	get_dto () const override
	Returns pointer to a C API primitive descriptor casted to cldnn_primitive_desc.
Public Member Functions inherited from cldnn::primitive
	primitive (const primitive_type_id &type, const primitive_id &id, const std::vector< primitive_id > &input, const padding &output_padding=padding())
	primitive (const cldnn_primitive_desc *dto)
	Constructs a copy from basic C API cldnn_primitive_desc.
std::vector< std::reference_wrapper< primitive_id > >	dependecies ()
	Returns references to all primitive ids on which this primitive depends - inputs, weights, biases, etc.
std::vector< primitive_id >	dependecies () const
	Returns copy of all primitive ids on which this primitive depends - inputs, weights, biases, etc.
	operator primitive_id () const
	Implicit conversion to primiitive id.

Static Public Member Functions
static primitive_type_id	type_id ()

Public Attributes
uint32_t	scale
uint32_t	num_filter
upsampling_sample_type	sample_type
bool	with_activation
	Enables Relu activation.
float	activation_negative_slope
	Relu activation slope.
Public Attributes inherited from cldnn::primitive
const primitive_type_id	type
	Primitive's type id.
const primitive_id	id
	Primitive's id.
fixed_size_vector_ref	input
	List of ids of input primitives.
padding	output_padding
	Requested output padding.

Protected Member Functions
void	update_dto (dto &dto) const override
Protected Member Functions inherited from cldnn::primitive_base< upsampling, cldnn_upsampling_desc >
	primitive_base (const primitive_id &id, const std::vector< primitive_id > &input, const padding &output_padding=padding())
	primitive_base (const cldnn_upsampling_desc *dto)
Protected Member Functions inherited from cldnn::primitive
virtual std::vector< std::reference_wrapper< const primitive_id > >	get_dependencies () const

Additional Inherited Members
Protected Attributes inherited from cldnn::primitive
primitive_id_arr	_input

Detailed Description

Performs nearest neighbor/bilinear upsampling Also supports built-in Relu activation available by setting it in arguments.

Definition at line 42 of file upsampling.hpp.

Constructor & Destructor Documentation

upsampling()

cldnn::upsampling::upsampling ( const primitive_id &  id, const primitive_id &  input, uint32_t  scale, uint32_t  num_filter, upsampling_sample_type  sample_type, bool  with_activation = false, float  activation_slp = 0.0f, const padding &  output_padding = padding()  )

inline

Constructs upsampling primitive.

Parameters

id	This primitive id.
input	Input primitive id.
scale	Upsampling scale.
num_filter	Input filter. Only used by bilinear sample_type.
sample_type	Upsampling method (nearest neighbor/bilinear).
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.

Definition at line 54 of file upsampling.hpp.

Member Data Documentation

num_filter

uint32_t cldnn::upsampling::num_filter

Parameters

num_filter

Input filter. Only used by bilinear sample_type.

Definition at line 87 of file upsampling.hpp.

sample_type

upsampling_sample_type cldnn::upsampling::sample_type

Parameters

sample_type

Upsampling method (nearest neighbor/bilinear).

Definition at line 89 of file upsampling.hpp.

scale

uint32_t cldnn::upsampling::scale

Parameters

scale

Upsampling scale.

Definition at line 85 of file upsampling.hpp.

---

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

• C:/ML/OpenSource/clDNN/api/CPP/upsampling.hpp