Python SDK simplifies edge AI development
Edge Impulse has launched a Python software development kit (SDK) with ‘bring your own model’ support and benchmarking for machine learning (ML) and edge AI to embedded devices.
The Python SDK was developed by the ML team at Edge Impulse based on internal tools. This is a toolbox of essential functions for anyone deploying models to the edge and supports a new set of capabilities that the company calls Bring Your Own Model (BYOM).
One key feature of the SDK is the ability to profile a deep learning model for inference on embedded hardware. It can take almost any model and show how it performs on a wide range of embedded processors.
- Edge Impulse teams for in-memory AI
- Edge Impulse, Renesas team for ML applications
- Alif, Bosch, Edge Impulse team for AI sensors
“We launched Edge Impulse to help developers and companies embed data-driven machine learning algorithms into physical devices, bridging the gap between technology and real life,” said Daniel Situnayake, head of machine learning at Edge Impulse.
“We started our journey by building tools for embedded engineers, enabling them to work with ML while staying focused on their craft. But over four years, we’ve noticed our product has been more than a tool for embedded engineers. It’s become wildly popular with ML experts, too.”
“Today, we’re launching a whole new way to use Edge Impulse. Built with ML experts in mind, it’s designed to help practitioners feel incredibly productive with edge AI: to take their existing skills and workflows and apply them to an entirely new domain — hardware — while working confidently next to embedded engineers.
- Edge Impulse raises $15m for TinyML
- Nordic, Edge Impulse team for embedded AI
- Edge AI tool targets PSoC microcontrollers
The SDK is designed to help simplify common tasks that fit into an embedded edge AI workflow. All of the Bring Your Own Model functionality is also available via the web interface, and can be used with all the current Edge Impulse tools for interactive computing and scripting to make sure a model can fit into the limited resources of an embedded design.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
