zigzag.parser.onnx.utils Namespace Reference

Classes
class	OnnxTensorCategory
	Internal representation of ONNX tensor category. More...
class	OnnxTensorType

Functions
ModelProto	parse_onnx_model_from_path (str onnx_model_path)
def	add_attribute (NodeProto node, str name, Any value)
def	add_branch_attribute (GraphProto graph, int branch=0)
GraphProto	unroll_branches (GraphProto graph)
def	is_dynamic (ModelProto model)
ModelProto	parse_dynamic_onnx_model (ModelProto model)
	Modifies the given onnx model if there's dynamic behavior in terms of an 'If' operator. More...
list[int]|int	get_attribute_ints_with_name (str name, Any attrs, list[int]|int|None default=None)
	Return the value of an attribute of given name from the given attributes If name does not exist in attrs, the default provided by the caller is used. More...
def	get_onnx_tensor_type (str name, ModelProto model)
def	get_node_input_output_dimension_shapes (NodeProto node, ModelProto model)

Variables
	logger = logging.getLogger(__name__)
string	BRANCH_ATTRIBUTE = "branch"

Function Documentation

add_attribute()

def zigzag.parser.onnx.utils.add_attribute	(	NodeProto	node,
		str	name,
		Any	value
	)

Here is the caller graph for this function:

add_branch_attribute()

def zigzag.parser.onnx.utils.add_branch_attribute	(	GraphProto	graph,
		int	branch = 0
	)

Here is the call graph for this function:

Here is the caller graph for this function:

get_attribute_ints_with_name()

list[int] | int zigzag.parser.onnx.utils.get_attribute_ints_with_name	(	str	name,
		Any	attrs,
		list[int] | int | None	default = None
	)

Return the value of an attribute of given name from the given attributes If name does not exist in attrs, the default provided by the caller is used.

If the caller doesn't supply a default, an error is thrown.

Here is the caller graph for this function:

get_node_input_output_dimension_shapes()

def zigzag.parser.onnx.utils.get_node_input_output_dimension_shapes	(	NodeProto	node,
		ModelProto	model
	)

Here is the call graph for this function:

Here is the caller graph for this function:

get_onnx_tensor_type()

def zigzag.parser.onnx.utils.get_onnx_tensor_type	(	str	name,
		ModelProto	model
	)

Here is the caller graph for this function:

is_dynamic()

def zigzag.parser.onnx.utils.is_dynamic

(

ModelProto

model

)

Here is the caller graph for this function:

parse_dynamic_onnx_model()

ModelProto zigzag.parser.onnx.utils.parse_dynamic_onnx_model

(

ModelProto

model

)

Modifies the given onnx model if there's dynamic behavior in terms of an 'If' operator.

All nodes are assigned a 'branch' attribute which specifies in which branch they live. The branch attribute starts from 0 and increases for each seen If operator. The nested graphs of the 'If' operators are then unrolled into a planar onnx model.

Here is the call graph for this function:

Here is the caller graph for this function:

parse_onnx_model_from_path()

ModelProto zigzag.parser.onnx.utils.parse_onnx_model_from_path

(

str

onnx_model_path

)

Here is the caller graph for this function:

unroll_branches()

GraphProto zigzag.parser.onnx.utils.unroll_branches

(

GraphProto

graph

)

Here is the caller graph for this function:

Variable Documentation

BRANCH_ATTRIBUTE

string BRANCH_ATTRIBUTE = "branch"

logger

logger = logging.getLogger(__name__)