Functions
Node	ctc_greedy_decoder_seq_len (NodeInput data, NodeInput sequence_length, Optional[NodeInput] blank_index=None, bool merge_repeated=True, str classes_index_type="i32", str sequence_length_type="i32", Optional[str] name=None)
	Return a node which performs CTCGreedyDecoderSeqLen. More...

Node	gather_elements (NodeInput data, NodeInput indices, Optional[int] axis=0, Optional[str] name=None)
	Return a node which performs GatherElements. More...

Node	mvn (Node data, Node axes, bool normalize_variance, float eps, str eps_mode, Optional[str] name=None)
	Return a node which performs MeanVarianceNormalization (MVN). More...

Node	assign (NodeInput new_value, str variable_id, Optional[str] name=None)
	Return a node which produces the Assign operation. More...

Node	read_value (NodeInput init_value, str variable_id, Optional[str] name=None)
	Return a node which produces the Assign operation. More...

Function Documentation

◆ assign()

Node ngraph.opset6.ops.assign	(	NodeInput	new_value,
		str	variable_id,
		Optional[str]	name = `None`
	)

Return a node which produces the Assign operation.

@param new_value:    Node producing a value to be assigned to a variable.
@param variable_id:  Id of a variable to be updated.
@param name:         Optional name for output node.
@return Assign node

◆ ctc_greedy_decoder_seq_len()

Node ngraph.opset6.ops.ctc_greedy_decoder_seq_len	(	NodeInput	data,
		NodeInput	sequence_length,
		Optional[NodeInput]	blank_index = `None`,
		bool	merge_repeated = `True`,
		str	classes_index_type = `"i32"`,
		str	sequence_length_type = `"i32"`,
		Optional[str]	name = `None`
	)

Return a node which performs CTCGreedyDecoderSeqLen.

@param data:            The input 3D tensor. Shape: [batch_size, seq_length, num_classes]
@param sequence_length: Input 1D tensor with sequence length. Shape: [batch_size]
@param blank_index:     Scalar or 1D tensor with specifies the class index to use for the blank class.
                        Optional parameter. Default value is num_classes-1.
@return:                The new node which performs CTCGreedyDecoderSeqLen.

◆ gather_elements()

Node ngraph.opset6.ops.gather_elements	(	NodeInput	data,
		NodeInput	indices,
		Optional[int]	axis = `0`,
		Optional[str]	name = `None`
	)

Return a node which performs GatherElements.

@param data:       N-D tensor with data for gathering
@param indices:    N-D tensor with indices by which data is gathered
@param axis:       axis along which elements are gathered
@return:           The new node which performs GatherElements

◆ mvn()

Node ngraph.opset6.ops.mvn	(	Node	data,
		Node	axes,
		bool	normalize_variance,
		float	eps,
		str	eps_mode,
		Optional[str]	name = `None`
	)

Return a node which performs MeanVarianceNormalization (MVN).

@param data: The node with data tensor.
@param axes: The node with axes to reduce on.
@param normalize_variance: Denotes whether to perform variance normalization.
@param eps: The number added to the variance to avoid division by zero
           when normalizing the value. Scalar value.
@param eps_mode: how eps is applied (`inside_sqrt` or `outside_sqrt`)
@param name: Optional output node name.
@return The new node performing a MVN operation on input tensor.

◆ read_value()

Node ngraph.opset6.ops.read_value	(	NodeInput	init_value,
		str	variable_id,
		Optional[str]	name = `None`
	)