A very simple tool to swap connections between output and input variables in an ONNX graph. Simple Variable Switch for ONNX.
https://github.com/PINTO0309/simple-onnx-processing-tools
### option
$ echo export PATH="~/.local/bin:$PATH" >> ~/.bashrc \
&& source ~/.bashrc
### run
$ pip install -U onnx \
&& python3 -m pip install -U onnx_graphsurgeon --index-url https://pypi.ngc.nvidia.com \
&& pip install -U svs4onnxhttps://github.com/PINTO0309/simple-onnx-processing-tools#docker
$ svs4onnx -h
usage:
svs4onnx [-h]
-if INPUT_ONNX_FILE_PATH
-fovn FROM_OUTPUT_VARIABLE_NAME
-tivn TO_INPUT_VARIABLE_NAME
-of OUTPUT_ONNX_FILE_PATH
[-n]
optional arguments:
-h, --help
show this help message and exit.
-if INPUT_ONNX_FILE_PATH, --input_onnx_file_path INPUT_ONNX_FILE_PATH
Input onnx file path.
-fovn FROM_OUTPUT_VARIABLE_NAME, --from_output_variable_name FROM_OUTPUT_VARIABLE_NAME
Output variable name of the connection change source.
e.g.
--from_output_variable_name "output1"
-tivn TO_INPUT_VARIABLE_NAME, --to_input_variable_name TO_INPUT_VARIABLE_NAME
Input variable name of connection change destination.
e.g.
--to_input_variable_name "input1"
-of OUTPUT_ONNX_FILE_PATH, --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
Output onnx file path.
-n, --non_verbose
Do not show all information logs. Only error logs are displayed.
>>> from svs4onnx import variable_switch
>>> help(variable_switch)
Help on function variable_switch in module svs4onnx.onnx_model_variable_switch:
variable_switch(
from_output_variable_name: str,
to_input_variable_name: str,
input_onnx_file_path: Union[str, NoneType] = '',
onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
output_onnx_file_path: Union[str, NoneType] = '',
non_verbose: Union[bool, NoneType] = False,
) -> onnx.onnx_ml_pb2.ModelProto
Parameters
----------
from_output_variable_name: str
Output variable name of the connection change source.
e.g.
output_op_names = "output1"
to_input_variable_name: str
Input variable name of connection change destination.
e.g.
output_op_names = "input1"
input_onnx_file_path: Optional[str]
Input onnx file path.
Either input_onnx_file_path or onnx_graph must be specified.
Default: ''
onnx_graph: Optional[onnx.ModelProto]
onnx.ModelProto.
Either input_onnx_file_path or onnx_graph must be specified.
onnx_graph If specified, ignore input_onnx_file_path and process onnx_graph.
output_onnx_file_path: Optional[str]
Output onnx file path. If not specified, no ONNX file is output.
Default: ''
non_verbose: Optional[bool]
Do not show all information logs. Only error logs are displayed.
Default: False
Returns
-------
variable_switched_graph: onnx.ModelProto
onnx.ModelProto with variable switched$ svs4onnx \
--input_onnx_file_path movenet_multipose_lightning_192x256_nopost_tmp1.onnx \
--from_output_variable_name "cast1_output" \
--to_input_variable_name "StatefulPartitionedCall/strided_slice_21" \
--output_onnx_file_path movenet_multipose_lightning_192x256_nopost_tmp2.onnxfrom svs4onnx import variable_switch
onnx_graph = variable_switch(
from_output_variable_name="cast1_output",
to_input_variable_name="StatefulPartitionedCall/strided_slice_21",
input_onnx_file_path="movenet_multipose_lightning_192x256_nopost_tmp1.onnx",
output_onnx_file_path="movenet_multipose_lightning_192x256_nopost_tmp2.onnx",
)$ svs4onnx \
--input_onnx_file_path movenet_multipose_lightning_192x256_nopost_tmp1.onnx \
--from_output_variable_name "cast1_output" \
--to_input_variable_name "StatefulPartitionedCall/strided_slice_21" \
--output_onnx_file_path movenet_multipose_lightning_192x256_nopost_tmp2.onnx
- https://github.com/onnx/onnx/blob/main/docs/Operators.md
- https://docs.nvidia.com/deeplearning/tensorrt/onnx-graphsurgeon/docs/index.html
- https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon
- https://github.com/PINTO0309/simple-onnx-processing-tools
- https://github.com/PINTO0309/PINTO_model_zoo
https://github.com/PINTO0309/simple-onnx-processing-tools/issues