Suggested development box to run & debug edge-impulse-linux and OpenCV

What would be an ideal development box to run & debug a Python program that can test an edge-impulse-linux trained model (.eim) along with OpenCV before deploying it to a Raspberry Pi 4 device? I currently have a Windows 10 development box with WSL2 > Ubuntu 20.04. But I am having issues using an edge-impulse-linux .eim model on my Python program. So may I ask again, any suggestions on setting up an ideal development box to run & debug edge-impulse-linux (before deploying the program to a production device like Rasbperry Pi 4)? :slight_smile:

Hi @rgvgreatcoder,

Could you share more details about the issues you have with your Python program?

One idea for your development box would be to use an existing set of pictures/videos and check inferencing results before deploying to the Rasp Pi 4. Using the Python SDK, it is easy to use files as an input instead of a camera, see for instance: Is there are way to do classification for Video

Aurelien

Hi @rgvgreatcoder I guess I answered your question on YouTube as well, but a Linux VM will be fine here as long as you can forward your webcam (some built-in webcams have trouble with that).

A question tho, if you run this under WSL2 what do you see? I would imagine it’d work.

Guys,

I am going to answer what I already did on another case. Sorry for duplicating my answer but it makes sense.

I wanted to share that running edge impulse in Ubuntu 20.04 inside WSL2 in a Windows 10 machine works! That is, I was able to run both: edge impulse CLI and edge impulse library in my Python code, in my Ubuntu 20.04 that runs in WSL2 in my Windows 10 machine!

Using the Windows Terminal to open up Ubuntu, I ran the following:

pip3 install edge_impulse_linux # To use in the Python code
npm install edge-impulse-linux -g # To install the CLI

Then I used Visual Studio Code with the “Remote - WSL” plug in, I was basically running VSCode inside Ubuntu machine. So in there, I created the my new Python project.

To use the edge impulse model (.eim file) on my Python code, I ran the following command to download it (as you mentioned above):

edge-impulse-linux-runner --download mymodel.eim --force-target runner-linux-x86_64

I had no issues after that. Thank you all for your support! … :smiley: