Simple model Output OP Additional tools 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 soa4onnxhttps://github.com/PINTO0309/simple-onnx-processing-tools#docker
$ soa4onnx -h
usage:
soa4onnx [-h]
-if INPUT_ONNX_FILE_PATH
-on OUTPUT_OP_NAMES [OUTPUT_OP_NAMES ...]
-of OUTPUT_ONNX_FILE_PATH
[-d]
[-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.
-on OUTPUT_OP_NAMES [OUTPUT_OP_NAMES ...], \
--output_op_names OUTPUT_OP_NAMES [OUTPUT_OP_NAMES ...]
Output name to be added to the models output OP.
e.g.
--output_op_names "onnx::Gather_76" "onnx::Add_89"
-of OUTPUT_ONNX_FILE_PATH, --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
Output onnx file path.
-d, --do_not_type_check
Whether not to check that input and output tensors have data types defined.'
-n, --non_verbose
Do not show all information logs. Only error logs are displayed.
>>> from soa4onnx import outputs_add
>>> help(outputs_add)
Help on function outputs_add in module soa4onnx.onnx_model_output_adder:
outputs_add(
input_onnx_file_path: Union[str, NoneType] = '',
onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
output_op_names: Union[List[str], NoneType] = [],
output_onnx_file_path: Union[str, NoneType] = '',
do_not_type_check: Union[bool, NoneType] = False,
non_verbose: Union[bool, NoneType] = False
) -> onnx.onnx_ml_pb2.ModelProto
Parameters
----------
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_op_names: List[str]
Output name to be added to the models output OP.
If an output OP name other than one that already exists in the model is
specified, it is ignored.
e.g.
output_op_names = ["onnx::Gather_76", "onnx::Add_89"]
output_onnx_file_path: Optional[str]
Output onnx file path. If not specified, no ONNX file is output.
Default: ''
do_not_type_check: Optional[bool]
Whether not to check that input and output tensors have data types defined.
Default: False
non_verbose: Optional[bool]
Do not show all information logs. Only error logs are displayed.
Default: False
Returns
-------
outputops_added_graph: onnx.ModelProto
onnx.ModelProto with output OP added$ soa4onnx \
--input_onnx_file_path fusionnet_180x320.onnx \
--output_op_names "onnx::Gather_76" "onnx::Add_89" \
--output_onnx_file_path fusionnet_180x320_added.onnxfrom soa4onnx import outputs_add
onnx_graph = rename(
input_onnx_file_path="fusionnet_180x320.onnx",
output_op_names=["onnx::Gather_76", "onnx::Add_89"],
output_onnx_file_path="fusionnet_180x320_added.onnx",
)$ soa4onnx \
--input_onnx_file_path fusionnet_180x320.onnx \
--output_op_names "onnx::Gather_76" "onnx::Add_89" \
--output_onnx_file_path fusionnet_180x320_added.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