Train, Convert, Run MobileNet on Sipeed MaixPy and MaixDuino !
Today we introduce how to Train, Convert, Run MobileNet model on Sipeed Maix board, with easy use MaixPy and MaixDuino~
继续阅读“Train, Convert, Run MobileNet on Sipeed MaixPy and MaixDuino !”
MaixPy Run 20-classes object detection based on tiny-yolov2 in 30 lines~
Here is the demo run tiny-yolo v2 to do 20-class classifier
Firmware and kmodel: (the model is half-cooked)
maixpy_20class.zip (2.8 MB)
继续阅读“MaixPy Run 20-classes object detection based on tiny-yolov2 in 30 lines~”
MaixPy run face detection (tiny yolo v2)
MaixPy run face detect (tiny yolo v2)
Today we use MaixPy to run face detection, here is the frimware and model.
maixpy_yolo2.zip (1015.3 KB)
MaixPy display MNIST feature map
MaixPy display MNIST feature map
Today we will get middle layer result, which usually called feature map, and display them on lcd.
firmware and model download from here:
maixpy_fmap.zip (875.0 KB)
Run MNIST on MaixPy in 30 lines code
Run MNIST on MaixPy in 30 lines code
here is the preview version of MaixPy run Kmodel V3 MNIST demo.
mnist maixpy.zip (875.0 KB)
First Burn maixpy_kpu_preview.bin, then burn mnist.kfpkg (model)
Power on your Maix Board, and input following code, you will get MNIST run~
新的固件下载工具:kflash_gui,跨平台带界面
MaixPy有IDE啦~~
MaixPY 因为使用的 Micropython 非编译型语言,所以实际上不需要IDE或者工具链也能工作,但为了方便使用者取色、取阈值等操作,在 OpenMV IDE 的基础上,我们对MaixPy进行了适配, 感谢 OpenMV 做的大量工作
用 Jupyter Notebook 控制 MaixPy
MicroPython在测试程序的时候各种好用,不过通过串口测试REPL程序后,测试完的程序就永远地消失在命令行界面里了。
熟悉Python的各位大佬们都知道有一个神奇的软件叫Jupyter Notebook,可以直接在浏览器里写不限于Python语言的程序,并且可以随时选择运行程序的一部分。MicroPython也被大佬做成了Jupyter Notebook的Kernel,可以将程序留在电脑上自由编辑,随时通过串口在MicroPython上执行。
从MicroPython port出来的MaixPy也可以用这样的方法进行控制。这里简单整理一下本菜鸡在往Maix Go上搬Jupyter Notebook的时候踩过的坑QAQ
MaixPy 人脸追踪云台教程
本文介绍人脸追踪云台的组装和使用。(修改Maix内部算法可以改为追踪其它任何物体)
继续阅读“MaixPy 人脸追踪云台教程”