Close
0%
0%

Object detector - MobileNet and YOLOv2 on MAixPy

Tutorial to train, evaluate (on PC), and test a YOLOv2 object detector on a MAix board running MicroPython

Similar projects worth following
This tutorial is about training (on PC) and deploying a YOLOv2 object detector on a MAix M1w Dock Suit running MicroPython. The MobileNet is used as a pre-trained model for the training.

Therefore, the original tutorial accomplishes the following points:
1. A quick introduction to YOLO(v2)
2. A quick introduction to MAix KPU
3. Training, evaluation, and testing of the object detector model (on Jupyter-Notebooks running on Docker)
4. Flashing the trained model on the MAix M1w Dock Suit running MicroPython (MAixPy)
5. Detecting a BRIO locomotive using the MAix M1w Dock Suit

Complete Tutorial: #MAixPy: Object detector - MobileNet and YOLOv2 on Sipeed MAix Dock

  • 1
    To compile the MAixPy firmware from scratch (on Ubuntu), clone the following repository:
    git clone https://github.com/sipeed/MaixPy
    cd MaixPy
    git submodule update --recursive --init
  • 2
    Install the requirements:
    sudo apt update
    sudo apt install python3 python3-pip build-essential cmake
    sudo pip3 install -r requirements.txt
  • 3
    Download and install the kendryte toolchain:
    wget http://dl.cdn.sipeed.com/kendryte-toolchain-ubuntu-amd64-8.2.0-20190409.tar.xz
    sudo tar -Jxvf kendryte-toolchain-ubuntu-amd64-8.2.0-20190409.tar.xz -C /opt

     The toolchain should be under /opt, otherwise you need to change the path inside config_defaults.mk.

View all 11 instructions

Enjoy this project?

Share

Discussions

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates