DepthToSpace permutes data from the depth dimension of the input blob into spatial dimensions. More...

Inheritance diagram for ngraph::op::v0::DepthToSpace:

Collaboration diagram for ngraph::op::v0::DepthToSpace:

Public Types
enum	DepthToSpaceMode { BLOCKS_FIRST, DEPTH_FIRST }

Public Member Functions
const NodeTypeInfo &	get_type_info () const override

	DepthToSpace (const Output< Node > &data, const DepthToSpaceMode &mode, std::size_t block_size=1)
	Constructs a DepthToSpace operation. More...

	DepthToSpace (const Output< Node > &data, const std::string &mode, std::size_t block_size=1)

bool	visit_attributes (AttributeVisitor &visitor) override

std::size_t	get_block_size () const

DepthToSpaceMode	get_mode () const

virtual OutputVector	decompose_op () const override

virtual std::shared_ptr< Node >	clone_with_new_inputs (const OutputVector &new_args) const override

Static Public Attributes
static constexpr NodeTypeInfo	type_info {"DepthToSpace", 0}

Protected Member Functions
DepthToSpaceMode	mode_from_string (const std::string &mode) const

Detailed Description

DepthToSpace permutes data from the depth dimension of the input blob into spatial dimensions.

Note: Values from the depth dimension (assuming NCHW layout) are moved in spatial blocks to the height and width dimensions.

Output node produces a tensor with shape: [N, C/(blocksize * blocksize), H * blocksize, W * blocksize]

Constructor & Destructor Documentation

ngraph::op::v0::DepthToSpace::DepthToSpace	(	const Output< Node > &	data,
		const DepthToSpaceMode &	mode,
		std::size_t	block_size = `1`
	)

Constructs a DepthToSpace operation.

Parameters

data	Node producing the input tensor
mode	Specifies how the input depth dimension is split to block coordinates
block_size	The size of the block of values to be moved

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