module onnxrt.optim.graph_schema_helper
¶
Short summary¶
module mlprodict.onnxrt.optim.graph_schema_helper
Functions to help guessing the final graph structure.
Functions¶
function |
truncated documentation |
---|---|
Retrieves defined inputs in already declared variables bsed on their names. |
|
Gets types of predefined outputs when they cannot be inferred. Some part of it should be automated based on type … |
|
Converts proto values to Variables. |
Documentation¶
Functions to help guessing the final graph structure.
-
mlprodict.onnxrt.optim.graph_schema_helper.
_guess_type
(var)¶
-
mlprodict.onnxrt.optim.graph_schema_helper.
get_defined_inputs
(input_names, variables=None, dtype=None)¶ Retrieves defined inputs in already declared variables bsed on their names.
- Parameters
input_names – input names
variables – registered variables created by previous operators
dtype – float computational type
- Returns
typed inputs as
tuple(name, type)
-
mlprodict.onnxrt.optim.graph_schema_helper.
get_defined_outputs
(outputs, onnx_node, typed_inputs=None, variables=None, dtype=None)¶ Gets types of predefined outputs when they cannot be inferred. Some part of it should be automated based on type constraints.
- Parameters
outputs – requested outputs
onnx_node – ONNX node definition
typed_inputs – known typed inputs of the node as
tuple(name, type)
variables – registered variables created by previous operators
dtype – float computational type
- Returns
typed outputs as
tuple(name, type)
-
mlprodict.onnxrt.optim.graph_schema_helper.
proto2vars
(values)¶ Converts proto values to Variables.