ngraph.opset4.ops Namespace Reference

Functions
Node	ctc_loss (NodeInput logits, NodeInput logit_length, NodeInput labels, NodeInput label_length, Optional[NodeInput] blank_index=None, bool preprocess_collapse_repeated=False, bool ctc_merge_repeated=True, bool unique=False, Optional[str] name=None)
	Return a node which performs CTCLoss. More...
Node	non_max_suppression (NodeInput boxes, NodeInput scores, Optional[NodeInput] max_output_boxes_per_class=None, Optional[NodeInput] iou_threshold=None, Optional[NodeInput] score_threshold=None, str box_encoding="corner", bool sort_result_descending=True, str output_type="i64", Optional[str] name=None)
	Return a node which performs NonMaxSuppression. More...
Node	softplus (NodeInput data, Optional[str] name=None)
	Apply SoftPlus operation on each element of input tensor. More...
Node	mish (NodeInput data, Optional[str] name=None)
	Return a node which performs Mish. More...
Node	hswish (NodeInput data, Optional[str] name=None)
	Return a node which performs HSwish (hard version of Swish). More...
Node	swish (NodeInput data, Optional[NodeInput] beta=None, Optional[str] name=None)
	Return a node which performing Swish activation function Swish(x, beta=1.0) = x * sigmoid(x * beta)). More...
Node	acosh (NodeInput node, Optional[str] name=None)
	Apply hyperbolic inverse cosine function on the input node element-wise. More...
Node	asinh (NodeInput node, Optional[str] name=None)
	Apply hyperbolic inverse sinus function on the input node element-wise. More...
Node	atanh (NodeInput node, Optional[str] name=None)
	Apply hyperbolic inverse tangent function on the input node element-wise. More...
Node	proposal (Node class_probs, Node bbox_deltas, NodeInput image_shape, dict attrs, Optional[str] name=None)
	Filter bounding boxes and outputs only those with the highest prediction confidence. More...
Node	reduce_l1 (NodeInput node, NodeInput reduction_axes, bool keep_dims=False, Optional[str] name=None)
	L1-reduction operation on input tensor, eliminating the specified reduction axes. More...
Node	reduce_l2 (NodeInput node, NodeInput reduction_axes, bool keep_dims=False, Optional[str] name=None)
	L2-reduction operation on input tensor, eliminating the specified reduction axes. More...
Node	lstm_cell (NodeInput X, NodeInput initial_hidden_state, NodeInput initial_cell_state, NodeInput W, NodeInput R, NodeInput B, int hidden_size, List[str] activations=None, List[float] activations_alpha=None, List[float] activations_beta=None, float clip=0.0, Optional[str] name=None)
	Return a node which performs LSTMCell operation. More...

Function Documentation

acosh()

Node ngraph.opset4.ops.acosh	(	NodeInput	node,
		Optional[str]	name = None
	)

Apply hyperbolic inverse cosine function on the input node element-wise.

Parameters

node	One of: input node, array or scalar.
name	Optional new name for output node.

Returns

New node with arccosh operation applied on it.

asinh()

Node ngraph.opset4.ops.asinh	(	NodeInput	node,
		Optional[str]	name = None
	)

Apply hyperbolic inverse sinus function on the input node element-wise.

Parameters

node	One of: input node, array or scalar.
name	Optional new name for output node.

Returns

New node with arcsinh operation applied on it.

atanh()

Node ngraph.opset4.ops.atanh	(	NodeInput	node,
		Optional[str]	name = None
	)

Apply hyperbolic inverse tangent function on the input node element-wise.

Parameters

node	One of: input node, array or scalar.
name	Optional new name for output node.

Returns

New node with arctanh operation applied on it.

ctc_loss()

Node ngraph.opset4.ops.ctc_loss	(	NodeInput	logits,
		NodeInput	logit_length,
		NodeInput	labels,
		NodeInput	label_length,
		Optional[NodeInput]	blank_index = None,
		bool	preprocess_collapse_repeated = False,
		bool	ctc_merge_repeated = True,
		bool	unique = False,
		Optional[str]	name = None
	)

Return a node which performs CTCLoss.

Parameters

logits	3-D tensor of logits.
logit_length	1-D tensor of lengths for each object from a batch.
labels	2-D tensor of labels for which likelihood is estimated using logits.
label_length	1-D tensor of length for each label sequence.
blank_index	Scalar used to mark a blank index.
preprocess_collapse_repeated	Flag for preprocessing labels before loss calculation.
ctc_merge_repeated	Flag for merging repeated characters in a potential alignment.
unique	Flag to find unique elements in a target.

Returns

The new node which performs CTCLoss

hswish()

Node ngraph.opset4.ops.hswish	(	NodeInput	data,
		Optional[str]	name = None
	)

Return a node which performs HSwish (hard version of Swish).

Parameters

data	Tensor with input data floating point type.

Returns

The new node which performs HSwish

lstm_cell()

Node ngraph.opset4.ops.lstm_cell	(	NodeInput	X,
		NodeInput	initial_hidden_state,
		NodeInput	initial_cell_state,
		NodeInput	W,
		NodeInput	R,
		NodeInput	B,
		int	hidden_size,
		List[str]	activations = None,
		List[float]	activations_alpha = None,
		List[float]	activations_beta = None,
		float	clip = 0.0,
		Optional[str]	name = None
	)

Return a node which performs LSTMCell operation.

Parameters

X	The input tensor with shape: [batch_size, input_size].
initial_hidden_state	The hidden state tensor with shape: [batch_size, hidden_size].
initial_cell_state	The cell state tensor with shape: [batch_size, hidden_size].
W	The weight tensor with shape: [4*hidden_size, input_size].
R	The recurrence weight tensor with shape: [4*hidden_size, hidden_size].
B	The bias tensor for gates with shape: [4*hidden_size].
hidden_size	Specifies hidden state size.
activations	The list of three activation functions for gates.
activations_alpha	The list of alpha parameters for activation functions.
activations_beta	The list of beta parameters for activation functions.
clip	Specifies bound values [-C, C] for tensor clipping performed before activations.
name	An optional name of the output node.

Returns

The new node represents LSTMCell. Node outputs count: 2.

mish()

Node ngraph.opset4.ops.mish	(	NodeInput	data,
		Optional[str]	name = None
	)

Return a node which performs Mish.

Parameters

data	Tensor with input data floating point type.

Returns

The new node which performs Mish

non_max_suppression()

Node ngraph.opset4.ops.non_max_suppression	(	NodeInput	boxes,
		NodeInput	scores,
		Optional[NodeInput]	max_output_boxes_per_class = None,
		Optional[NodeInput]	iou_threshold = None,
		Optional[NodeInput]	score_threshold = None,
		str	box_encoding = "corner",
		bool	sort_result_descending = True,
		str	output_type = "i64",
		Optional[str]	name = None
	)

Return a node which performs NonMaxSuppression.

Parameters

boxes	Tensor with box coordinates.
scores	Tensor with box scores.
max_output_boxes_per_class	Tensor Specifying maximum number of boxes to be selected per class.
iou_threshold	Tensor specifying intersection over union threshold
score_threshold	Tensor specifying minimum score to consider box for the processing.
box_encoding	Format of boxes data encoding.
sort_result_descending	Flag that specifies whenever it is necessary to sort selected boxes across batches or not.
output_type	Output element type.

Returns

The new node which performs NonMaxSuppression

proposal()

Node ngraph.opset4.ops.proposal	(	Node	class_probs,
		Node	bbox_deltas,
		NodeInput	image_shape,
		dict	attrs,
		Optional[str]	name = None
	)

Filter bounding boxes and outputs only those with the highest prediction confidence.

Parameters

class_probs	4D input floating point tensor with class prediction scores.
bbox_deltas	4D input floating point tensor with corrected predictions of bounding boxes
image_shape	The 1D input tensor with 3 or 4 elements describing image shape.
attrs	The dictionary containing key, value pairs for attributes.
name	Optional name for the output node. base_size The size of the anchor to which scale and ratio attributes are applied. Range of values: a positive unsigned integer number Default value: None Required: yes pre_nms_topn The number of bounding boxes before the NMS operation. Range of values: a positive unsigned integer number Default value: None Required: yes post_nms_topn The number of bounding boxes after the NMS operation. Range of values: a positive unsigned integer number Default value: None Required: yes nms_thresh The minimum value of the proposal to be taken into consideration. Range of values: a positive floating-point number Default value: None Required: yes feat_stride The step size to slide over boxes (in pixels). Range of values: a positive unsigned integer Default value: None Required: yes min_size The minimum size of box to be taken into consideration. Range of values: a positive unsigned integer number Default value: None Required: yes ratio The ratios for anchor generation. Range of values: a list of floating-point numbers Default value: None Required: yes scale The scales for anchor generation. Range of values: a list of floating-point numbers Default value: None Required: yes clip_before_nms The flag that specifies whether to perform clip bounding boxes before non-maximum suppression or not. Range of values: True or False Default value: True Required: no clip_after_nms The flag that specifies whether to perform clip bounding boxes after non-maximum suppression or not. Range of values: True or False Default value: False Required: no normalize The flag that specifies whether to perform normalization of output boxes to [0,1] interval or not. Range of values: True or False Default value: False Required: no box_size_scale Specifies the scale factor applied to logits of box sizes before decoding. Range of values: a positive floating-point number Default value: 1.0 Required: no box_coordinate_scale Specifies the scale factor applied to logits of box coordinates before decoding. Range of values: a positive floating-point number Default value: 1.0 Required: no framework Specifies how the box coordinates are calculated. Range of values: "" (empty string) - calculate box coordinates like in Caffe* tensorflow - calculate box coordinates like in the TensorFlow* Object Detection API models Default value: "" (empty string) Required: no Example of attribute dictionary: # just required ones attrs = { 'base_size': 85, 'pre_nms_topn': 10, 'post_nms_topn': 20, 'nms_thresh': 0.34, 'feat_stride': 16, 'min_size': 32, 'ratio': [0.1, 1.5, 2.0, 2.5], 'scale': [2, 3, 3, 4], } Optional attributes which are absent from dictionary will be set with corresponding default. @return Node representing Proposal operation.

reduce_l1()

Node ngraph.opset4.ops.reduce_l1	(	NodeInput	node,
		NodeInput	reduction_axes,
		bool	keep_dims = False,
		Optional[str]	name = None
	)

L1-reduction operation on input tensor, eliminating the specified reduction axes.

Parameters

node	The tensor we want to mean-reduce.
reduction_axes	The axes to eliminate through mean operation.
keep_dims	If set to True it holds axes that are used for reduction
name	Optional name for output node.

Returns

The new node performing mean-reduction operation.

reduce_l2()

Node ngraph.opset4.ops.reduce_l2	(	NodeInput	node,
		NodeInput	reduction_axes,
		bool	keep_dims = False,
		Optional[str]	name = None
	)

L2-reduction operation on input tensor, eliminating the specified reduction axes.

Parameters

node	The tensor we want to mean-reduce.
reduction_axes	The axes to eliminate through mean operation.
keep_dims	If set to True it holds axes that are used for reduction
name	Optional name for output node.

Returns

The new node performing mean-reduction operation.

softplus()

Node ngraph.opset4.ops.softplus	(	NodeInput	data,
		Optional[str]	name = None
	)

Apply SoftPlus operation on each element of input tensor.

Parameters

data	The tensor providing input data.

Returns

The new node with SoftPlus operation applied on each element.

swish()

Node ngraph.opset4.ops.swish	(	NodeInput	data,
		Optional[NodeInput]	beta = None,
		Optional[str]	name = None
	)

Return a node which performing Swish activation function Swish(x, beta=1.0) = x * sigmoid(x * beta)).

Parameters

data	Tensor with input data floating point type.

Returns

The new node which performs Swish