GithubHelp home page GithubHelp logo

nknytk / built-onnxruntime-for-raspberrypi-linux Goto Github PK

View Code? Open in Web Editor NEW
112.0 4.0 19.0 479.41 MB

Built python wheel files of https://github.com/microsoft/onnxruntime for raspberry pi 32bit linux.

Shell 100.00%

built-onnxruntime-for-raspberrypi-linux's Introduction

About this repository

ONNX Runtime is a cross-platform, high performance scoring engine for ML models. You can get Python bindings for Linux, Windows, Mac on x64 and arm64 platform from pypi. The project does not provide pre-built packages for Raspbery Pi Linux 32bit (ARM32v7) as of today. Instead it has an instruction on how to build ONNX Runtime from the source code.

Building package takes a lot of time. This repository provides pre-built Python ONNX Runtime Python wheel packages for Raspberry pi for convenience.

There is NO WARRANTY of any kind at all.

Files

wheels/

This directory has built packages.

  • wheels/bullseye/
    • Built python wheel packages for Raspberry Pi OS based on Debian Bullseye (Relase date: 2021-10-30~).
  • wheels/buster/
    • Built python wheel packages for Raspbian Buster and Raspberry Pi OS based on Debian Buster.
  • wheels/stretch/
    • Built python wheel packages for Raspbian Stretch.

See your raspberry pi's /etc/debian_version file to find your OS version.

value of /etc/debian_version Debian codename
11.x Bullseye
10.x Buster
9.x Stretch

Wheels are built on Raspberry Pi with this procedure since v1.6.0.
Building ONNX Runtime wheel for Raspberry Pi 32bit on Docker with Qemu stopped working since 2020 summer.

build.sh

A script to build ONNX Runtime wheels for armv7-linux on Docker with Qemu.
It builds wheels for Python 3.8, 3.9, 3.10 and 3.11.
You need docker to run it.

Usage:

$ sudo ./build.sh

Dockerfile-arm32v7.template

A Dockerfile template used in build.sh.

built-onnxruntime-for-raspberrypi-linux's People

Contributors

danielgoncalvesti avatar nknytk avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

built-onnxruntime-for-raspberrypi-linux's Issues

--use_openmp is not supported anymore.

Build fails because of --use_openmp argument which has been removed.

#0 1.449   --build_dir /code/onnxruntime/build/Linux --use_openmp --config MinSizeRel --arm --update --build                                                                                                                                  
#0 1.490 usage: 
#0 1.490         Default behavior is --update --build --test for native architecture builds.
#0 1.490         Default behavior is --update --build for cross-compiled builds.
#0 1.490 
#0 1.490         The Update phase will update git submodules, and run cmake to generate makefiles.
#0 1.490         The Build phase will build all projects.
#0 1.490         The Test phase will run all unit tests, and optionally the ONNX tests.
#0 1.490 
#0 1.490         Use the individual flags to only run the specified stages.
#0 1.490         
#0 1.491 build.py: error: unrecognized arguments: --use_openmp

microsoft/onnxruntime#14067

.whl not working

Hi,

I tried to install the provided .whl on my rpi 3 model B+ using the beow command:
pip install onnxruntime-1.4.0-cp38-cp38-linux_armv7l.whl
I got the below error: onnxruntime-1.4.0-cp38-cp38-linux_armv7l.whl is not a supported wheel on this platform.
My python version is 3.7.3 and pip version is pip 21.1.3

Can you suggest something what might be the issue?

Debian Bookworm support

Hi,

Do you have any plan to support Debian Bookworm (12) and so Python 3.11?

Thanks for your work.

pip3 install onnxruntime-1.2.0-cp37-cp37m-linux_armv7l.whl error on raspberry pi 4

pip3 install onnxruntime-1.2.0-cp37-cp37m-linux_armv7l.whl
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple
Processing ./onnxruntime-1.2.0-cp37-cp37m-linux_armv7l.whl
ERROR: Exception:
Traceback (most recent call last):
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/cli/base_command.py", line 188, in _main
status = self.run(options, args)
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/cli/req_command.py", line 185, in wrapper
return func(self, options, args)
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/commands/install.py", line 333, in run
reqs, check_supported_wheels=not options.target_dir
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/resolution/legacy/resolver.py", line 179, in resolve
discovered_reqs.extend(self._resolve_one(requirement_set, req))
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/resolution/legacy/resolver.py", line 362, in _resolve_one
abstract_dist = self._get_abstract_dist_for(req_to_install)
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/resolution/legacy/resolver.py", line 314, in _get_abstract_dist_for
abstract_dist = self.preparer.prepare_linked_requirement(req)
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/operations/prepare.py", line 469, in prepare_linked_requirement
hashes=hashes,
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/operations/prepare.py", line 264, in unpack_url
unpack_file(file.path, location, file.content_type)
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/utils/unpacking.py", line 252, in unpack_file
flatten=not filename.endswith('.whl')
File "/home/pi/.local/lib/python3.7/site-packages/pip/_internal/utils/unpacking.py", line 114, in unzip_file
zip = zipfile.ZipFile(zipfp, allowZip64=True)
File "/usr/lib/python3.7/zipfile.py", line 1222, in init
self._RealGetContents()
File "/usr/lib/python3.7/zipfile.py", line 1289, in _RealGetContents
raise BadZipFile("File is not a zip file")
zipfile.BadZipFile: File is not a zip file

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.