git clone https://github.com/sipeed/MaixPy
cd MaixPy
git submodule update --recursive --init

sudo apt update
sudo apt install python3 python3-pip build-essential cmake
sudo pip3 install -r requirements.txt

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.

cd MaixPy/projects/maixpy_k210_minimum
python3 project.py menuconfig
python3 project.py build
python3 project.py flash -B dan -b 1500000 -p /dev/ttyUSB0 -t

git clone https://github.com/sipeed/kflash.py.git

kflash.py doesn't have the option to flash a file with an address offset, so you'll need to make a .kfpkg file. A .kfpkg package is just a .zip file with a custom extension that contains the following files:

• flash-list.json: json file describing the files included in the package
• *.kmodel: – the model that will be flashed

The file flash-list.json looks like this:

{
  "version": "0.1.0",
  "files": [
    {
      "address": 0x00300000,
      "bin": "m.kmodel",
      "sha256Prefix": false
    }
  ]
}

You can find an example of the .kfpkg file inside the repo: lemariva/uPyMaixYoloV2. 

Download the example and replace the m.kmodel inside with your weights.kmodel file (rename it before). 

./kflash.py -p /dev/ttyUSB0 -b 2000000 model.kfpkg

The repository lemariva/uPyMaixYoloV2 includes an example to run the object detector on the Sipeed M1w Dock suit (includes Wi-Fi).

git clone https://github.com/lemariva/uPyMaixYoloV2

and Open the Folder using VSCode. You can connect to the board using the PyMakr extension. I wrote a tutorial for the ESP/WiPy boards but the extension can be also used with the MAix. However, you can only run files but you cannot upload them.

Before you run the file, configure your Wi-Fi credentials:

# wlan access
ssid_ = ""
wpa2_pass = ""

or remove the lines between # wlan access and ## Sensor, if you don't want to connect the board to Wi-Fi.

you can use uPyLoader. First, clone the repository:

git clone https://github.com/BetaRavener/uPyLoader.git

and install the following dependencies:

pip3 install PyQt5

Then:

1. Start the application: main.py
2. Select the serial port and click on the Connect button to connect the board.
3. The first time you run the software, you need to initialize it:
   • Go to File->Init transfer files to complete the initialization. This creates two files on the board, __upload.py and __download.py.
4. Select the file that you want to upload (e.g. boot.py), and click on the Transfer button.