Performs transposed convolution. Also supports built-in Relu activation available by setting it in arguments. More...

#include <deconvolution.hpp>

Inheritance diagram for cldnn::deconvolution:

Collaboration diagram for cldnn::deconvolution:

[legend]

Public Types
typedef cldnn_deconvolution_desc	dto

Public Member Functions
	deconvolution (const primitive_id &id, const primitive_id &input, const std::vector< primitive_id > &weights, const std::vector< primitive_id > &bias, tensor stride={ 1, 1, 1, 1 }, tensor input_offset={ 0, 0, 0, 0 }, bool with_activation=false, float activation_slp=0.0f, const padding &output_padding=padding())
	Constructs deconvolution primitive. More...

	deconvolution (const primitive_id &id, const primitive_id &input, const std::vector< primitive_id > &weights, tensor stride={ 1, 1, 1, 1 }, tensor input_offset={ 0, 0, 0, 0 }, bool with_activation=false, float activation_slp=0.0f, const padding &output_padding=padding())
	Constructs deconvolution primitive (w/o bias). More...

	deconvolution (const primitive_id &id, const primitive_id &input, const std::vector< primitive_id > &weights, const std::vector< primitive_id > &bias, tensor stride, tensor input_offset, bool with_activation, float activation_slp, tensor output_size, const padding &output_padding=padding())
	Constructs deconvolution primitive (computes input paddings to match output size). More...

	deconvolution (const primitive_id &id, const primitive_id &input, const std::vector< primitive_id > &weights, tensor stride, tensor input_offset, bool with_activation, float activation_slp, tensor output_size, const padding &output_padding=padding())
	Constructs deconvolution primitive (w/o bias, computes input paddings to match output size). More...

	deconvolution (const dto *dto)
	Constructs a copy from C API cldnn_deconvolution_desc.

int32_t	split () const
	On how many cards split the computation to.

Public Member Functions inherited from cldnn::primitive_base< deconvolution, cldnn_deconvolution_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 ()

static deconvolution	create_with_output_size (const primitive_id &id, const primitive_id &input, const std::vector< primitive_id > &weights, const std::vector< primitive_id > &bias, tensor output_size, tensor stride={ 1, 1, 1, 1 }, tensor input_offset={ 0, 0, 0, 0 }, bool with_activation=false, float activation_slp=0.0f, const padding &output_padding=padding())
	Constructs deconvolution primitive (computes input paddings to match output size). More...

static deconvolution	create_with_output_size (const primitive_id &id, const primitive_id &input, const std::vector< primitive_id > &weights, tensor output_size, tensor stride={ 1, 1, 1, 1 }, tensor input_offset={ 0, 0, 0, 0 }, bool with_activation=false, float activation_slp=0.0f, const padding &output_padding=padding())
	Constructs deconvolution primitive (w/o bias; computes input paddings to match output size). More...

Public Attributes
fixed_size_vector_ref	weights
	List of primitive ids containing weights data.

fixed_size_vector_ref	bias
	List of primitive ids containing bias data.

tensor	input_offset
	Defines a shift, relative to (0,0) position of the input buffer, where (0,0) point of the deconvolution window should start calculations.

tensor	stride
	Defines shift in input buffer between adjacent calculations of output values.

bool	with_activation
	Enables Relu activation.

float	activation_negative_slope
	Relu activation slope.

bool	with_output_size
	Indicates that the primitive has user-defined output size (non-zero value).

tensor	output_size
	User-defined output data size of the primitive (w/o padding).

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
std::vector< std::reference_wrapper< const primitive_id > >	get_dependencies () const override

void	update_dto (dto &dto) const override

Protected Member Functions inherited from cldnn::primitive_base< deconvolution, cldnn_deconvolution_desc >
	primitive_base (const primitive_id &id, const std::vector< primitive_id > &input, const padding &output_padding=padding())

	primitive_base (const cldnn_deconvolution_desc *dto)

Protected Attributes
primitive_id_arr	_weights

primitive_id_arr	_bias

Protected Attributes inherited from cldnn::primitive
primitive_id_arr	_input

Detailed Description

Performs transposed convolution. Also supports built-in Relu activation available by setting it in arguments.

Deconvolution is similar to convolution layer with the weights flipped on the axis and stride and input padding parameters used in opposite sense as in convolution.

Definition at line 34 of file deconvolution.hpp.

Constructor & Destructor Documentation

◆ deconvolution() [1/4]

cldnn::deconvolution::deconvolution	(	const primitive_id &	id,
		const primitive_id &	input,
		const std::vector< primitive_id > &	weights,
		const std::vector< primitive_id > &	bias,
		tensor	stride = `{ 1, 1, 1, 1 }`,
		tensor	input_offset = `{ 0,0,0,0 }`,
		bool	with_activation = `false`,
		float	activation_slp = `0.0f`,
		const padding &	output_padding = `padding()`
	)

inline

Constructs deconvolution primitive.

Parameters

id	This primitive id.
input	Input primitive id.
weights	List of primitive ids containing weights data.
bias	List of primitive ids containing bias data. Provide empty vector if using next parameters without bias.
input_offset	Input padding/offset.
stride	Defines shift in input buffer between adjacent calculations of output values.
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.

Definition at line 47 of file deconvolution.hpp.

◆ deconvolution() [2/4]

cldnn::deconvolution::deconvolution	(	const primitive_id &	id,
		const primitive_id &	input,
		const std::vector< primitive_id > &	weights,
		tensor	stride = `{ 1, 1, 1, 1 }`,
		tensor	input_offset = `{ 0,0,0,0 }`,
		bool	with_activation = `false`,
		float	activation_slp = `0.0f`,
		const padding &	output_padding = `padding()`
	)

inline

Constructs deconvolution primitive (w/o bias).

Parameters

id	This primitive id.
input	Input primitive id.
weights	List of primitive ids containing weights data.
input_offset	Input padding/offset.
stride	Defines shift in input buffer between adjacent calculations of output values.
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.

Definition at line 79 of file deconvolution.hpp.

◆ deconvolution() [3/4]

cldnn::deconvolution::deconvolution	(	const primitive_id &	id,
		const primitive_id &	input,
		const std::vector< primitive_id > &	weights,
		const std::vector< primitive_id > &	bias,
		tensor	stride,
		tensor	input_offset,
		bool	with_activation,
		float	activation_slp,
		tensor	output_size,
		const padding &	output_padding = `padding()`
	)

inline

Constructs deconvolution primitive (computes input paddings to match output size).

Parameters

id	This primitive id.
input	Input primitive id.
weights	List of primitive ids containing weights data.
bias	List of primitive ids containing bias data. Provide empty vector if using next parameters without bias.
input_offset	Input padding/offset.
stride	Defines shift in input buffer between adjacent calculations of output values.
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.
output_size	User-defined output data size of the primitive (w/o padding).

Definition at line 112 of file deconvolution.hpp.

◆ deconvolution() [4/4]

cldnn::deconvolution::deconvolution	(	const primitive_id &	id,
		const primitive_id &	input,
		const std::vector< primitive_id > &	weights,
		tensor	stride,
		tensor	input_offset,
		bool	with_activation,
		float	activation_slp,
		tensor	output_size,
		const padding &	output_padding = `padding()`
	)

inline

Constructs deconvolution primitive (w/o bias, computes input paddings to match output size).

Parameters

id	This primitive id.
input	Input primitive id.
weights	List of primitive ids containing weights data.
input_offset	Input padding/offset.
stride	Defines shift in input buffer between adjacent calculations of output values.
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.
output_size	User-defined output data size of the primitive (w/o padding).

Definition at line 147 of file deconvolution.hpp.

Member Function Documentation

◆ create_with_output_size() [1/2]

static deconvolution cldnn::deconvolution::create_with_output_size	(	const primitive_id &	id,
		const primitive_id &	input,
		const std::vector< primitive_id > &	weights,
		const std::vector< primitive_id > &	bias,
		tensor	output_size,
		tensor	stride = `{ 1, 1, 1, 1 }`,
		tensor	input_offset = `{ 0,0,0,0 }`,
		bool	with_activation = `false`,
		float	activation_slp = `0.0f`,
		const padding &	output_padding = `padding()`
	)

inlinestatic

Constructs deconvolution primitive (computes input paddings to match output size).

Parameters

id	This primitive id.
input	Input primitive id.
weights	List of primitive ids containing weights data.
bias	List of primitive ids containing bias data. Provide empty vector if using next parameters without bias.
input_offset	Input padding/offset.
stride	Defines shift in input buffer between adjacent calculations of output values.
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.
output_size	User-defined output data size of the primitive (w/o padding).

Returns: Deconvolution primitive with specified settings.

Definition at line 201 of file deconvolution.hpp.

◆ create_with_output_size() [2/2]

static deconvolution cldnn::deconvolution::create_with_output_size	(	const primitive_id &	id,
		const primitive_id &	input,
		const std::vector< primitive_id > &	weights,
		tensor	output_size,
		tensor	stride = `{ 1, 1, 1, 1 }`,
		tensor	input_offset = `{ 0,0,0,0 }`,
		bool	with_activation = `false`,
		float	activation_slp = `0.0f`,
		const padding &	output_padding = `padding()`
	)

inlinestatic

Constructs deconvolution primitive (w/o bias; computes input paddings to match output size).

Parameters

id	This primitive id.
input	Input primitive id.
weights	List of primitive ids containing weights data.
input_offset	Input padding/offset.
stride	Defines shift in input buffer between adjacent calculations of output values.
with_activation	Enables Relu activation.
activation_slp	Relu activation slope.
output_size	User-defined output data size of the primitive (w/o padding).

Returns: Deconvolution primitive with specified settings.

Definition at line 228 of file deconvolution.hpp.

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

C:/ML/OpenSource/clDNN/api/CPP/deconvolution.hpp

Public Types

Public Member Functions

Static Public Member Functions

Public Attributes

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ deconvolution() [1/4]

◆ deconvolution() [2/4]

◆ deconvolution() [3/4]

◆ deconvolution() [4/4]

Member Function Documentation

◆ create_with_output_size() [1/2]

◆ create_with_output_size() [2/2]