onnx_graphsurgeon.ir.node.Node Class Reference

Inheritance diagram for onnx_graphsurgeon.ir.node.Node:

Collaboration diagram for onnx_graphsurgeon.ir.node.Node:

Public Member Functions
def	__init__ (self, str op, str name=None, Dict[str, object] attrs=None, List["Tensor"] inputs=None, List["Tensor"] outputs=None)
def	i (self, tensor_idx=0, producer_idx=0)
def	o (self, consumer_idx=0, tensor_idx=0)
def	__setattr__ (self, name, value)
def	copy (self, List["Tensor"] inputs=None, List["Tensor"] outputs=None)
def	__str__ (self)
def	__repr__ (self)
def	__eq__ (self, other)

Public Attributes
	op
	name
	attrs
	inputs
	outputs

Constructor & Destructor Documentation

__init__()

def onnx_graphsurgeon.ir.node.Node.__init__	(		self,
		str	op,
		str	name = None,
		Dict[str, object]	attrs = None,
		List["Tensor"]	inputs = None,
		List["Tensor"]	outputs = None
	)

A node represents an operation in a graph, and consumes zero or more Tensors, and produces zero or more Tensors.

Args:
    op (str): The operation this node performs.

    name (str): The name of this node.
    attrs (Dict[str, object]): A dictionary that maps attribute names to their values.
    inputs (List[Tensor]): A list of zero or more input Tensors.
    outputs (List[Tensor]): A list of zero or more output Tensors.

Member Function Documentation

i()

def onnx_graphsurgeon.ir.node.Node.i	(		self,
			tensor_idx = 0,
			producer_idx = 0
	)

Convenience function to get a producer node of one of this node's input tensors.
Note that the parameters are swapped compared to the o() function; this is because tensors are likely to have only a single producer

For example:
::

    assert node.i() == node.inputs[0].inputs[0]
    assert node.i(1, 2) == node.inputs[1].inputs[2]

Args:
    tensor_idx (int): The index of the input tensor of this node. Defaults to 0.
    producer_idx (int): The index of the producer of the input tensor, if the tensor has multiple producers. Defaults to 0

Returns:
    Node: The specified producer (input) node.

o()

def onnx_graphsurgeon.ir.node.Node.o	(		self,
			consumer_idx = 0,
			tensor_idx = 0
	)

Convenience function to get a consumer node of one of this node's output tensors.

For example:
::

    assert node.o() == node.outputs[0].outputs[0]
    assert node.o(2, 1) == node.outputs[1].outputs[2]

Args:
    consumer_idx (int): The index of the consumer of the input tensor. Defaults to 0.
    tensor_idx (int): The index of the output tensor of this node, if the node has multiple outputs. Defaults to 0.

Returns:
    Node: The specified consumer (output) node

__setattr__()

def onnx_graphsurgeon.ir.node.Node.__setattr__	(		self,
			name,
			value
	)

copy()

def onnx_graphsurgeon.ir.node.Node.copy	(		self,
		List["Tensor"]	inputs = None,
		List["Tensor"]	outputs = None
	)

Makes a shallow copy of this node, overriding input and output information.

Note: Generally, you should only ever make a deep copy of a Graph.

__str__()

def onnx_graphsurgeon.ir.node.Node.__str__

(

self

)

Here is the caller graph for this function:

__repr__()

def onnx_graphsurgeon.ir.node.Node.__repr__

(

self

)

Here is the call graph for this function:

__eq__()

def onnx_graphsurgeon.ir.node.Node.__eq__	(		self,
			other
	)

Check whether two nodes are equal by comparing name, attributes, op, inputs, and outputs.

Member Data Documentation

op

onnx_graphsurgeon.ir.node.Node.op

name

onnx_graphsurgeon.ir.node.Node.name

attrs

onnx_graphsurgeon.ir.node.Node.attrs

inputs

onnx_graphsurgeon.ir.node.Node.inputs

outputs

onnx_graphsurgeon.ir.node.Node.outputs

---

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

• node.py