/sng4onnx

A simple tool that automatically generates and assigns an OP name to each OP in an old format ONNX file.

Primary LanguagePythonMIT LicenseMIT

sng4onnx

A simple tool that automatically generates and assigns an OP name to each OP in an old format ONNX file.
Simple op Name Generator for ONNX.

https://github.com/PINTO0309/simple-onnx-processing-tools

Downloads GitHub PyPI CodeQL

Key concept

  • Automatically generates and assigns an OP name to each OP in an old format ONNX file.

1. Setup

1-1. HostPC

### 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 sng4onnx

1-2. Docker

https://github.com/PINTO0309/simple-onnx-processing-tools#docker

2. CLI Usage

$ sng4onnx -h

usage:
  sng4onnx [-h]
  -if INPUT_ONNX_FILE_PATH
  -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.

  -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.

3. In-script Usage

>>> from sng4onnx import generate
>>> help(generate)

Help on function generate in module sng4onnx.onnx_opname_generator:

generate(
    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
    ----------
    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
    -------
    renamed_graph: onnx.ModelProto
        Renamed onnx ModelProto.

4. CLI Execution

$ sng4onnx \
--input_onnx_file_path emotion-ferplus-8.onnx \
--output_onnx_file_path emotion-ferplus-8_renamed.onnx

5. In-script Execution

from sng4onnx import generate

onnx_graph = generate(
  input_onnx_file_path="fusionnet_180x320.onnx",
  output_onnx_file_path="fusionnet_180x320_renamed.onnx",
)

6. Sample

https://github.com/onnx/models/blob/main/vision/classification/resnet/model/resnet18-v1-7.onnx

Before

image

After

image

7. Reference

  1. https://github.com/onnx/onnx/blob/main/docs/Operators.md
  2. https://docs.nvidia.com/deeplearning/tensorrt/onnx-graphsurgeon/docs/index.html
  3. https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon
  4. https://github.com/PINTO0309/simple-onnx-processing-tools
  5. https://github.com/PINTO0309/PINTO_model_zoo

8. Issues

https://github.com/PINTO0309/simple-onnx-processing-tools/issues