module onnxrt.optim._onnx_optimisation_common
¶
Short summary¶
module mlprodict.onnxrt.optim._onnx_optimisation_common
Common functions to reduce the number of nodes of an ONNX graphs.
Functions¶
function |
truncated documentation |
---|---|
Applies an optimisation function fct on a graph and not on the model. |
|
Applies an optimizing function on a subgraphs. |
|
Constructs a NodeProto. |
|
Renames an input and adds an Identity node to connect the dots. |
|
Renames an output and adds an Identity node to connect the dots. |
|
Renames an input from a node. |
|
Renames an output from a node. |
|
Documentation¶
Common functions to reduce the number of nodes of an ONNX graphs.
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_apply_optimisation_on_graph
(fct, onnx_model, recursive=True, debug_info=None, **kwargs)¶ Applies an optimisation function fct on a graph and not on the model.
- Parameters
fct – function to optimise like
onnx_remove_node_identity
onnx_model – onnx model
recursive – looks into subgraphs
debug_info – debug information (private)
kwargs – additional parameters
- Returns
new onnx _model
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_apply_remove_node_fct_node
(fct, node, recursive, debug_info)¶ Applies an optimizing function on a subgraphs.
- Parameters
node – onnx node
recursive – does it in subgraphs as well
- Returns
new node
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_copy_value_info_proto
(new_name, obj)¶
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_make_att_graph
(name, new_body)¶
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_make_node
(op_type, inputs, outputs, name=None, doc_string=None, domain=None, attributes=None)¶ Constructs a NodeProto.
- Parameters
op_type – (string): The name of the operator to construct
inputs – list of input names
outputs – list of output names
name – optional unique identifier for NodeProto
doc_string – optional documentation string for NodeProto
domain – optional domain for NodeProto. If it’s None, we will just use default domain (which is empty)
attributes – the attributes of the node. The acceptable values are documented in
make_attribute()
.
- Returns
node
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_rename_graph_input
(graph, old_name, new_name)¶ Renames an input and adds an Identity node to connect the dots.
- Parameters
graph – ONNX graph
- Returns
modified graph
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_rename_graph_output
(graph, old_name, new_name)¶ Renames an output and adds an Identity node to connect the dots.
- Parameters
graph – ONNX graph
- Returns
modified graph
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_rename_node_input
(onnx_node, old_name, new_name=None)¶ Renames an input from a node.
- Parameters
onnx_node – onnx_node
old_name – old name
new_name – new name or None if old_name is a dictionary
- Returns
new node
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_rename_node_output
(onnx_node, old_name, new_name)¶ Renames an output from a node.
- Parameters
onnx_node – onnx_node
old_name – old name
new_name – new name
- Returns
new node
-
mlprodict.onnxrt.optim._onnx_optimisation_common.
_replace
(name, old_name, new_name)¶