Edge Impulse has launched Bring Your Own Model (BYOM) and a Python SDK, which allows AI teams to use their own bespoke ML models and optimize them for edge devices. Users can import their own models into Edge Impulse Studio, streamlining workflows and letting ML teams leverage Edge Impulse from their own development environments. Additionally, Edge Impulse’s new tools offer enterprises and their ML development teams valuable capabilities and promises to become a valuable part of all ML engineers’ toolkits. The BYOM launch also includes the release of the second version of the EON Compiler, which improves the overall efficiencies of models, enabling enterprises to save over 70% RAM and 40% ROM compared to TensorFlow Lite for Microcontrollers (TFLM).

source update: Edge Impulse Launches “Bring Your Own Model” for ML Engineers – Towards AI