sipeed/MaixPy3

How to use MaixPy3 nn to test Yolov2 script

Q2Learn opened this issue · 3 comments

I have a problem with understanding how to use example models yolov2 with MaixPy3 nn on Sipeed MAIX-II Dock V831.

In the MaixPy3_scripts example applications presented here there is a yolov2 model with the .bin and .param files and an example script to test completed. Which is very cool.

So I want to load that example into sipeed v831 board for object detection. So I transfer over the files to my board via the microSD card and moved it to /home/res and I change the directories and permissions in the file and try and run it but I am getting an error when running it:

ImportError: cannot import name 'decoder' from 'maix.nn' (/usr/lib/python3.8/site-packages/maix/nn.pyc)

In the readme for ../MaixPy3_scripts/ it says (google translated):

"When using the scripts in scripts, please install some resource files in basic first. The resource files that scripts depend on are concentrated in basic/res, and they should be copied to v831 before running!"

But I can't find basic/res to install the resource files and cant find a tutorial or help anywhere on how to get that going. Any help will be appreciated in finding a location or a tutorial or just some help in setting it up. My goal is to get an example yolov2 running object detection so that I can see how it performs and eventually try and build my own yolov2 model and maybe even train new algorithms like YoloR or yoloRET for Edge AI.

I will be glad for your feedback!

More information is still being compiled. You can continue to follow us. In 2022, many internal development results will be released.

Some content has been built into the latest M2 Docker image

Thanks @junhuanchen that worked. I updated to the latest firmware and transferred over the example application script at https://github.com/sipeed/MaixPy3_scripts for nn_face and I was able to test it.

Thank you for your help.