Question: openvino support for Nvidia Jetson Xavier ?

[moyu026]

I wonder know if openvino supports for Nvidia Jetson Xavier. I try to pip install openvino-dev, it always fails and has a same error:

• Collecting scikit-learn~=0.24.1 (from openvino-dev[paddle])
• Using cached scikit-learn-0.24.2.tar.gz (7.5 MB)
• Installing build dependencies ... done
• Getting requirements to build wheel ... done
• Preparing metadata (pyproject.toml) ... error
• error: subprocess-exited-with-error
• × Preparing metadata (pyproject.toml) did not run successfully.
• │ exit code: 1
• ╰─> [847 lines of output]

•   <string>:17: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
  

•   Partial import of sklearn during the build process.
  

•   <string>:116: DeprecationWarning:
  

•     `numpy.distutils` is deprecated since NumPy 1.23.0, as a result
  

•     of the deprecation of `distutils` itself. It will be removed for
  

•     Python >= 3.12. For older Python versions it will remain present.
  

•     It is recommended to use `setuptools < 60.0` for those Python versions.
  

•     For more details, see:
  

•       https://numpy.org/devdocs/reference/distutils_status_migration.html
  

•   INFO: C compiler: gcc -pthread -B /home/nvidia/anaconda3/envs/openvino/compiler_compat -Wsign-compare -DNDEBUG -fwrapv -O3 -Wall -fPIC -O3 -isystem /home/nvidia/anaconda3/envs/openvino/include -fPIC -O3 -isystem /home/nvidia/anaconda3/envs/openvino/include -fPIC
  

•   INFO: compile options: '-c'
  

•   INFO: gcc: test_program.c
  

•   INFO: gcc -pthread -B /home/nvidia/anaconda3/envs/openvino/compiler_compat objects/test_program.o -o test_program
  

•   INFO: C compiler: gcc -pthread -B /home/nvidia/anaconda3/envs/openvino/compiler_compat -Wsign-compare -DNDEBUG -fwrapv -O3 -Wall -fPIC -O3 -isystem /home/nvidia/anaconda3/envs/openvino/include -fPIC -O3 -isystem /home/nvidia/anaconda3/envs/openvino/include -fPIC
  

[ilya-lavrenov]

Hi @moyu026
We don't currently provide prebuilt OpenVINO wheel package for Linux aarch64 platform.
You can use archives where Python API is also available https://docs.openvino.ai/2023.0/openvino_docs_install_guides_installing_openvino_from_archive_linux.html#step-1-download-and-install-the-openvino-core-components

Alternatively, you can try installing OpenVINO Python API via conda:

conda install -c "conda-forge/label/openvino_dev" openvino

This command will install OpenVINO pre-release package (because in official 2023.0 release python API is not available in conda-forge yet; but it will be since 2023.1)

[avitial]

Closing this, I hope previous responses were sufficient to help you proceed. Feel free to reopen and ask additional questions related to this topic.

[ilya-lavrenov]

We have released OpenVINO 2023.1.0 and published wheel packages for arm64 Linux https://pypi.org/project/openvino/#files
Please, try:

python3 -m pip install openvino