Run image classification in a containerized environment with BalenaCloud

In just a few years, the Raspberry Pi has become one of the most popular Single Board Computers, allowing users to run an entire Operating System in a small form factor and for a very low price. Around the same time Docker was released to the public, bringing major evolutions to the design of web applications by introducing containers and microservices to a large developers’ community.


This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/run-image-classification-in-a-containerized-environment-with-balenacloud/
1 Like

Balena is a very interesting environment.
It is really a great idea to run edge impulse as a “balena” service on a raspberry pi !

I still need to get my head around it about when exactly the webassembly edge impulse is retrieved from edge impulse site onto the raspberry pi - all the rest was very clear !

1 Like

Thanks for the feedback @janvda!

The webassembly package is retrieved through the following script: https://github.com/edgeimpulse/balena-cam-tinyml/blob/master/edgeimpulse-inference/app/downloadWasm.sh.
It is defined as a prestart script in package.json before starting the node.js server.

1 Like