Repository files navigation

中文

Let's Sipeed up, Maximize AI's power!

MaixPy, makes AIOT easier!

Maixpy is designed to make AIOT programming easier, based on theMicropython syntax, running on a very powerful embedded AIOT chipK210.

There are many things you can do with MaixPy, please refer tohere

K210 brief:

• Image Recognition with hardware AI acceleration
• Dual core with FPU
• 8MB(6MB+2MB) RAM
• 16MB external Flash
• Max 800MHz CPU freq (see the dev board in detail, usually 400MHz)
• Microphone array(8 mics)
• Hardware AES SHA256
• FPIOA (Periphrals can map to any pins)
• Peripherals: I2C, SPI, I2S, WDT, TIMER, RTC, UART, GPIO etc.

Find I2C devices:

frommachineimportI2Ci2c=I2C(I2C.I2C0,freq=100000,scl=28,sda=29)devices=i2c.scan()print(devices)

Take picture:

importsensorimportimageimportlcdlcd.init()sensor.reset()sensor.set_pixformat(sensor.RGB565)sensor.set_framesize(sensor.QVGA)sensor.run(1)whileTrue:img=sensor.snapshot()lcd.display(img)

Use AI model to recognize object:

importKPUaskpuimportsensorsensor.reset()sensor.set_pixformat(sensor.RGB565)sensor.set_framesize(sensor.QVGA)sensor.set_windowing((224,224))model=kpu.load("/sd/mobilenet.kmodel")# load modelwhile(True):img=sensor.snapshot()# take picture by cameraout=kpu.forward(task,img)[:]# inference, get one-hot outputprint(max(out))# print max probability object ID

please read doc before run it

SeeReleases page

Get latest commit firmware:master firmware

Custom your firmware, seebuild or useonline custom tool

Doc refer tomaixpy.sipeed.com

MaixPy_scripts

Seebuild doc

The historic version seehistoric branch (No longer maintained, just keep commit history)

Go tomaixhub.com to use online compilation to customize the functions you need

Find more models onMaixhub.com

SeeLICENSE file

In addition to the source code of theMaixPy project, sinceMaixPy exists as a component, it can be configured to not participate in compilation, so this repository can also be developed asC SDK. For the usage details, seeBuilding Documentation, which can be started by compiling and downloadingprojects/hello_world.

The compilation process is briefly as follows:

wget http://dl.cdn.sipeed.com/kendryte-toolchain-ubuntu-amd64-8.2.0-20190409.tar.xzsudo tar -Jxvf kendryte-toolchain-ubuntu-amd64-8.2.0-20190409.tar.xz -C /optcd projects/hello_worldpython3 project.py menuconfigpython3 project.py buildpython3 project.py flash -B dan -b 1500000 -p /dev/ttyUSB0 -t