opto.trace.nodes.Node#

class Node[source]#

A data node in a directed graph, this is a basic data structure of Trace.

Parameters:

• value (Any) – The value to be assigned to the node.

• name (str, optional) – The name of the node.

• trainable (bool, optional) – Whether the node is trainable or not. Defaults to False.

• description (str, optional) – String describing the node. Defaults to “[Node] This is a node in a computational graph.”

• constraint (Union[None, str], optional) – String describing constraints that the data should satisfy. Defaults to None.

• info (Union[None, Dict], optional) – Dictionary containing additional information about the node. Defaults to None.

trainable#

Whether the node is trainable or not.

Type:

bool

_feedback#

Dictionary of feedback from children nodes.

Type:

dict

_description#

String describing the node.

Type:

str

_constraint#

String describing all constraints that the data should satisfy.

Type:

str

_backwarded#

Whether the backward method has been called.

Type:

bool

_info#

Dictionary containing additional information about the node.

Type:

dict

_dependencies#

Dictionary of dependencies on parameters and expandable nodes.

Type:

dict

Notes

The Node class extends AbstractNode to represent a data node in a directed graph. It includes attributes and methods to handle feedback, constraints, and dependencies. The node can be marked as trainable and store feedback from children nodes. The feedback mechanism is analogous to gradients in machine learning and propagates information back through the graph. The feedback mechanism supports non-commutative aggregation, so feedback should be handled carefully to maintain correct operation order. The node can track dependencies on parameters and expandable nodes (nodes that depend on parameters not visible in the current graph level).

Initialize an instance of the Node class.

Parameters:

• value – The value to be assigned to the node.

• name – The name of the node (optional).

• trainable – A boolean indicating whether the node is trainable or not (optional).

• description – A string describing the node (optional).

• constraint – A string describing constraints on the node (optional).

• info – A dictionary containing additional information about the node (optional).

Attributes

children	Get the children of a node.
data	Retrieve the internal data of a node.
description	A textual description of the node.
expandable_dependencies	The depended expandable nodes.
feedback	The feedback from children nodes.
id	Get the identifier part of the node's name.
info	Additional information about the node.
is_leaf	Check if the node is a leaf node.
is_root	Check if the node is a root node.
level	Get the level of the node in the graph.
name	Get the name of the node.
parameter_dependencies	The depended parameters.
parents	Get the parents of a node.
py_name	Get the Python-friendly name of the node.
type	The type of the data stored in the node.

Methods

append(*args, **kwargs)
backward([feedback, propagator, ...])	Performs a backward pass in a computational graph.
call(fun, *args, **kwargs)	Call the function with the specified arguments and keyword arguments.
capitalize()
clone()	Create and return a duplicate of the current Node object.
detach()	Create and return a deep copy of the current instance of the Node class.
eq(other)	Check if the node is equal to another value.
format(*args, **kwargs)
getattr(key)	Get the attribute of the node with the specified key.
gt(other)	Compare if this node's level is greater than another node's level.
items()
join(seq)
keys()
len()	Return the length of the node.
lower()
lt(other)	Compare if this node's level is less than another node's level.
neq(other)	Check if the node is not equal to another value.
pop([_Node__index])
replace(old, new[, count])
split([sep, maxsplit])
strip([chars])
swapcase()
title()
upper()
values()
zero_feedback()	Zero out the feedback of the node.

__init__(value: Any, *, name: str | None = None, trainable: bool = False, description: str = '[Node] This is a node in a computational graph.', constraint: None | str = None, info: None | Dict = None) → None[source]#

Initialize an instance of the Node class.

Parameters:

• value – The value to be assigned to the node.

• name – The name of the node (optional).

• trainable – A boolean indicating whether the node is trainable or not (optional).

• description – A string describing the node (optional).

• constraint – A string describing constraints on the node (optional).

• info – A dictionary containing additional information about the node (optional).

__new__(**kwargs)#