Skip to content

MaixPy for Linux Python3, let's play with edge AI easier!

License

Notifications You must be signed in to change notification settings

Nyquest-unstable/MaixPy3

 
 

Repository files navigation

MaixPy3 Logo

MaixPy3 GitHub forks GitHub stars GitHub watchers

MIT PyPI version Python issue

MaixPy3 is a Python3 toolkit based on cpython, which simplifies the development of applications on Linux AI edge devices through Python programming.

Support Jupyter Environment

Install rpyc_ikernel kernel in jupyter notebook & lab to get an IDE that can remotely call Python code, videos, and image streaming.

Develop

Under linux x86_64, use python3 setup.py build to complete the linux package construction. If you need .whl pre-compiled package, please change build to bdist_wheel. For other platforms, take the version of maix_v83x as an example, match the Python3 + cross-compilation chain of the corresponding platform, and run python3.8 setup.py build maix_v83x to complete the construction of the target platform package.

Welcome to provide configurations of different platforms to MaixPy3/envs/ to adapt to the MaixPy3 environment.

Platform Status Config Progress Toolchain
linux_pc & RPi_2B working linux_desktop 60% develop.md & maixpy3_build.yml
maix_v83x working maix_v83x 90% v83x_linux_x86_python3.8_toolchain
maix_r329 working maix_r329 90% r329_linux_x86_python3.9_toolchain

Estimated Workload

  • 30% Python3.7↑ & toolchain environment adaptation Pillow spidev evdev gpiod pyserial zbarlight numpy pyaudio pyav *pybind11

  • 30% base library adaptation camera display image nn speech imlib

  • 30% AI application adaptation resnet yolo classifier FaceRecognize

  • 10% Peripheral library adapted to gpio spi i2c pwm event for special hardware

The development progress is in no particular order.

License

Copyright (c) Sipeed Corporation. All rights reserved.

Licensed under the MIT license.

About

MaixPy for Linux Python3, let's play with edge AI easier!

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 64.6%
  • C 16.2%
  • C++ 14.4%
  • Jupyter Notebook 4.6%
  • Makefile 0.2%