ngraph.opset2.ops Namespace Reference

Functions
Node	batch_to_space (NodeInput data, NodeInput block_shape, NodeInput crops_begin, NodeInput crops_end, Optional[str] name=None)
	Perform BatchToSpace operation on the input tensor. More...
Node	gelu (NodeInput node, Optional[str] name=None)
	Perform Gaussian Error Linear Unit operation element-wise on data from input node. More...
Node	mvn (Node data, bool across_channels=False, bool normalize_variance=False, float eps=1e-9, str name=None)
	Perform Mean Variance Normalization operation on data from input node. More...
Node	reorg_yolo (Node input, List[int] stride, Optional[str] name=None)
	Return a node which produces the ReorgYolo operation. More...
Node	roi_pooling (NodeInput input, NodeInput coords, TensorShape output_size, NumericData spatial_scale, str method, Optional[str] name=None)
	Return a node which produces an ROIPooling operation. More...
Node	space_to_batch (NodeInput data, NodeInput block_shape, NodeInput pads_begin, NodeInput pads_end, Optional[str] name=None)
	Perform SpaceToBatch operation on the input tensor. More...

Function Documentation

batch_to_space()

Node ngraph.opset2.ops.batch_to_space	(	NodeInput	data,
		NodeInput	block_shape,
		NodeInput	crops_begin,
		NodeInput	crops_end,
		Optional[str]	name = None
	)

Perform BatchToSpace operation on the input tensor.

BatchToSpace permutes data from the batch dimension of the data tensor into spatial dimensions.

Parameters

data	Node producing the data tensor.
block_shape	The sizes of the block of values to be moved.
crops_begin	Specifies the amount to crop from the beginning along each axis of data.
crops_end	Specifies the amount to crop from the end along each axis of data.
name	Optional output node name.

Returns

The new node performing a BatchToSpace operation.

gelu()

Node ngraph.opset2.ops.gelu	(	NodeInput	node,
		Optional[str]	name = None
	)

Perform Gaussian Error Linear Unit operation element-wise on data from input node.

Computes GELU function:

\[ f(x) = 0.5\cdot x\cdot(1 + erf( \dfrac{x}{\sqrt{2}}) \]

For more information refer to: Gaussian Error Linear Unit (GELU) <https://arxiv.org/pdf/1606.08415.pdf>_

Parameters

node	Input tensor. One of: input node, array or scalar.
name	Optional output node name.

Returns

The new node performing a GELU operation on its input data element-wise.

mvn()

Node ngraph.opset2.ops.mvn	(	Node	data,
		bool	across_channels = False,
		bool	normalize_variance = False,
		float	eps = 1e-9,
		str	name = None
	)

Perform Mean Variance Normalization operation on data from input node.

Computes MVN on the input tensor data (called X) using formula:

\[ Y = \dfrac{X-EX}{\sqrt{E(X-EX)^2}} \]

Parameters

data	The node with data tensor.
across_channels	Denotes if mean values are shared across channels.
normalize_variance	Denotes whether to perform variance normalization.
eps	The number added to the variance to avoid division by zero when normalizing the value. Scalar value.
name	Optional output node name.

Returns

The new node performing a MVN operation on input tensor.

reorg_yolo()

Node ngraph.opset2.ops.reorg_yolo	(	Node	input,
		List[int]	stride,
		Optional[str]	name = None
	)

Return a node which produces the ReorgYolo operation.

Parameters

input	Input data
stride	Stride to reorganize input by
name	Optional name for output node.

Returns

ReorgYolo node

roi_pooling()

Node ngraph.opset2.ops.roi_pooling	(	NodeInput	input,
		NodeInput	coords,
		TensorShape	output_size,
		NumericData	spatial_scale,
		str	method,
		Optional[str]	name = None
	)

Return a node which produces an ROIPooling operation.

Parameters

input	Input feature map {N, C, ...}
coords	Coordinates of bounding boxes
output_size	Height/Width of ROI output features (shape)
spatial_scale	Ratio of input feature map over input image size (float)
method	Method of pooling - string: "max" or "bilinear"

Returns

ROIPooling node

space_to_batch()

Node ngraph.opset2.ops.space_to_batch	(	NodeInput	data,
		NodeInput	block_shape,
		NodeInput	pads_begin,
		NodeInput	pads_end,
		Optional[str]	name = None
	)

Perform SpaceToBatch operation on the input tensor.

SpaceToBatch permutes data tensor blocks of spatial data into batch dimension. The operator returns a copy of the input tensor where values from spatial blocks dimensions are moved in the batch dimension

Parameters

data	Node producing the data tensor.
block_shape	The sizes of the block of values to be moved.
pads_begin	Specifies the padding for the beginning along each axis of data.
pads_end	Specifies the padding for the ending along each axis of data.
name	Optional output node name.

Returns

The new node performing a SpaceToBatch operation.