Skip to main content

A very simple tool that forces a change in the opset of an ONNX graph. Simple Opset Changer for ONNX.

Project description

soc4onnx

A very simple tool that forces a change in the opset of an ONNX graph. Simple Opset Changer for ONNX.

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

Downloads GitHub PyPI CodeQL

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 soc4onnx

1-2. Docker

### docker pull
$ docker pull pinto0309/soc4onnx:latest

### docker build
$ docker build -t pinto0309/soc4onnx:latest .

### docker run
$ docker run --rm -it -v `pwd`:/workdir pinto0309/soc4onnx:latest
$ cd /workdir

2. CLI Usage

$ soc4onnx -h

usage:
    soc4onnx [-h]
    --input_onnx_file_path INPUT_ONNX_FILE_PATH
    --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
    --opset OPSET
    [--non_verbose]

optional arguments:
  -h, --help
        show this help message and exit

  --input_onnx_file_path INPUT_ONNX_FILE_PATH
        Input onnx file path.

  --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
        Output onnx file path.

  --opset OPSET
        opset number to be changed. e.g. --opset 11

  --non_verbose
        Do not show all information logs. Only error logs are displayed.

3. In-script Usage

$ python
>>> from soc4onnx import change
>>> help(change)
Help on function change in module soc4onnx.onnx_opset_change:

change(
  opset: int,
  input_onnx_file_path: Union[str, NoneType] = '',
  output_onnx_file_path: Union[str, NoneType] = '',
  onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
  non_verbose: Union[bool, NoneType] = False
) -> onnx.onnx_ml_pb2.ModelProto

    Parameters
    ----------
    opset: int
        opset number to be changed.
        e.g. --opset 11

    input_onnx_file_path: Optional[str]
        Input onnx file path.
        Either input_onnx_file_path or onnx_graph must be specified.

    output_onnx_file_path: Optional[str]
        Output onnx file path.
        If output_onnx_file_path is not specified, no .onnx file is output.

    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.

    non_verbose: Optional[bool]
        Do not show all information logs. Only error logs are displayed.
        Default: False

    Returns
    -------
    changed_graph: onnx.ModelProto
        opset changed onnx ModelProto

4. CLI Execution

$ soc4onnx \
--input_onnx_file_path NonMaxSuppression.onnx \
--output_onnx_file_path NonMaxSuppression_13.onnx \
--opset 13

5. In-script Execution

from soc4onnx import change

changed_graph = change(
    onnx_graph=graph,
    opset=13,
    non_verbose=True,
)

6. Sample

image

$ soc4onnx \
--input_onnx_file_path NonMaxSuppression.onnx \
--output_onnx_file_path NonMaxSuppression_13.onnx \
--opset 13

image

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

soc4onnx-1.0.0.tar.gz (4.8 kB view details)

Uploaded Source

Built Distribution

soc4onnx-1.0.0-py3-none-any.whl (5.7 kB view details)

Uploaded Python 3

File details

Details for the file soc4onnx-1.0.0.tar.gz.

File metadata

  • Download URL: soc4onnx-1.0.0.tar.gz
  • Upload date:
  • Size: 4.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.10.4

File hashes

Hashes for soc4onnx-1.0.0.tar.gz
Algorithm Hash digest
SHA256 2c5192af6fe2fe5aa0a7fa962d9db8b1d072176ae2a665e1ef951e0225f245c5
MD5 74564fc5ebf7b825f9e8129b65fcdf78
BLAKE2b-256 09b5d74c9791087282f25747a4ae8b311ecd88b3a469b8678e64de3c418c3d22

See more details on using hashes here.

File details

Details for the file soc4onnx-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: soc4onnx-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 5.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.10.4

File hashes

Hashes for soc4onnx-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c49c2c327c4997652f19a2660a690f621a7bb0143b9d64e0faf1f006cbf326e3
MD5 ff71bd75a594565b38839cfb4beaada2
BLAKE2b-256 fe04431c437b6fbfde5b90c7c3538d81e4412f5c885bd70cea2c0bc866b72465

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page