The Embedded Learning Library (ELL) allows you to design and deploy intelligent machine-learned models onto resource constrained platforms and small single-board computers, like Raspberry Pi, Arduino, and micro:bit. The deployed models run locally, without requiring a network connection and without relying on servers in the cloud. ELL is an early preview of the embedded AI and machine learning technologies developed at Microsoft Research.
We've provided two sets of short tutorials to teach you about ELL:
-
The Try it on Azure folder contains a version of the tutorials that can be run entirely in the Azure Notebooks. This is good for learning the basics of the ELL library and evaluating whether ELL meets your needs, even if you don't have small devices at hand.
-
The Try it on a device folder contains the same tutorials, but with the goal of deploying the code to a small device, like a Raspberry Pi. To work properly, these tutorials must be downloaded to your laptop or desktop machine, in order to access your device. To download a tutorial, click the Download button at the top of the notebook and save the .ipynb file to your Jupyter startup folder. After the download completes, the notebook will show up in the Jupyter Dashboard. Open the downloaded notebook from the Dashboard and do the steps in your local Jupyter.