ConvParser Class Reference

Parser for ONNX Conv and QLinearConv nodes into LayerNode. More...

Inheritance diagram for ConvParser:

Collaboration diagram for ConvParser:

Public Member Functions
None	__init__ (self, int node_id, NodeProto node, dict[int, Any] nodes_outputs, list[dict[str, Any]] mapping_data, ModelProto onnx_model)
LayerNode	run (self)
	Run the parser and return the created LayerNode object. More...
dict[str, Any]	get_layer_node_user_format (self, list[int] kernel_shape, list[int] strides, list[int] dilations, int group_size, list[int] padding, list[int] ia_shape, list[int] oa_shape)
	Generate the necessary dictionary items required for the LayerNode creation. More...
def	generate_layer_node_for_conv (self)
Public Member Functions inherited from ONNXOperatorParser
None	__init__ (self, int node_id, NodeProto node, dict[int, Any] nodes_outputs, ModelProto onnx_model, *list[dict[str, Any]]|None mapping_data=None, Accelerator|None accelerator=None)
def	get_input_output_weight_data_type (self)
	Return the data type of the input, output and weight tensors of this node. More...
def	get_weight_name (self, NodeProto node)
	Return the name of the weight input of this node depending on its operator type. More...
list[int]	get_node_predecessors (self)
	Compute node input sources. More...
def	get_operand_source_user_format (self, list[int] predecessors)
	Set input source and indicate constant operands. More...
def	get_weight_precision (self)
	Return the weight precision for this node. More...
def	get_activation_precision (self)
	Return the activation precision for this node. More...
def	get_intermediate_output_precision (self)
	Return the intermediate output precision for this node. More...

Public Attributes
	mapping_data
	onnx_model
Public Attributes inherited from ONNXOperatorParser
	node_id
	node
	nodes_outputs
	onnx_model
	mapping_data
	accelerator

Additional Inherited Members
Static Public Attributes inherited from ONNXOperatorParser
string	CUSTOM_WEIGHT_SIZE_ATTR = "weight_size"
string	CUSTOM_ACT_SIZE_ATTR = "act_size"
string	CUSTOM_OUTPUT_SIZE_ATTR = "output_size"

Detailed Description

Parser for ONNX Conv and QLinearConv nodes into LayerNode.

Constructor & Destructor Documentation

__init__()

None __init__	(		self,
		int	node_id,
		NodeProto	node,
		dict[int, Any]	nodes_outputs,
		list[dict[str, Any]]	mapping_data,
		ModelProto	onnx_model
	)

Member Function Documentation

generate_layer_node_for_conv()

def generate_layer_node_for_conv

(

self

)

Here is the call graph for this function:

Here is the caller graph for this function:

get_layer_node_user_format()

dict[str, Any] get_layer_node_user_format	(		self,
		list[int]	kernel_shape,
		list[int]	strides,
		list[int]	dilations,
		int	group_size,
		list[int]	padding,
		list[int]	ia_shape,
		list[int]	oa_shape
	)

Generate the necessary dictionary items required for the LayerNode creation.

If there is no data for a given Layer Attribute, the Layer Attribute is not included in the returned dict.

Here is the call graph for this function:

Here is the caller graph for this function:

run()

LayerNode run

(

self

)

Run the parser and return the created LayerNode object.

Reimplemented from ONNXOperatorParser.

Here is the call graph for this function:

Here is the caller graph for this function:

Member Data Documentation

mapping_data

mapping_data

onnx_model

onnx_model

---

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

• /home/runner/work/zigzag/zigzag/zigzag/parser/onnx/conv_parser.py