ONNC Bench requires Python 3.6 or above. Using virtual environment managers, such as Conda or VirtualEnv, is highly recommanded.

Install ONNC Bench by pip

You can install ONNC Bench by the popular pip from pypi. Simply type this:

pip install onnc-bench

To verify your installation, use pip show.

$ pip show onnc-bench

Name: onnc-bench
Version: 2.0.0
Summary: ONNC-bench is a Python wrapper of ONNC
Author: The Skymizer Team
Author-email: [email protected]
License: Apache License 2.0
Location: /usr/local/lib/python3.9/site-packages
Requires: sentry-sdk, click, wget, loguru, onnx, read-only-attributes, numpy, jinja2, requests

Now, you should be able to import ONNC Bench in a python shell

>>> from onnc.bench import __version__
>>> print(__version__)

Install Virtual Environment Managers

Simply follow below instructions to create a Conda/Miniconda environment for ONNC Bench

  1. If you do not have Conda, intall Miniconda(Installation Doc) first.

  2. Create a Conda environment:

    $ conda create -y python=3.7 --name onnc-bench
    ... (skiped)
    # To activate this environment, use
    #     $ conda activate onnc-bench
    # To deactivate an active environment, use
    #     $ conda deactivate
  3. Activate the environment:

    $ conda activate onnc-bench

After installation, every time you want to use ONNC Bench, you have to activate this environment with the same command.