Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).
Role in this project:
ML Engineer Contributions:34 reviews, 17 commits, 62 PRs in 1 year 7 months
Contributions summary:Shlomi primarily contributed to optimizing and expanding the capabilities of the TensorFlow Lite Micro framework, particularly focusing on embedded machine learning model deployment. Their work involved modifying kernel implementations, including those for Flexbuffer and the Cast operator, to improve performance and memory usage. They also addressed build script improvements and added support for Xtensa architecture specific optimizations, demonstrating a strong understanding of low-power, resource-constrained environments.
embeddedmicrocontrollermlmodel
TensorFlow Lite for Microcontrollers
Contributions:132 pushes, 50 branches in 4 years 8 months
tensorflow-litelitetensorflowmicrocontrollers