Timezone: »

 
Oral
TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems
Robert David · Jared Duke · Advait Jain · Vijay Janapa Reddi · Nat Jeffries · Jian Li · Nick Kreeger · Ian Nappier · Meghna Natraj · Tiezhen Wang · Pete Warden · Rocky Rhodes · Rocky Rhodes

Tue Apr 06 03:20 PM -- 03:40 PM (PDT) @
in Session 4: Training (I) »

We introduce TensorFlow (TF) Micro, an open-source machine learning inference framework for running deep-learning models on embedded systems. TF Micro tackles the efficiency requirements imposed by embedded system resource constraints and the fragmentation challenges that make cross-platform interoperability nearly impossible. The framework adopts a unique interpreter-based approach that provides flexibility while overcoming the challenges. This paper explains the design decisions behind TF Micro and describes its implementation. We present an evaluation to demonstrate its low resource requirement and minimal run-time performance overhead.

Author Information

Robert David (Google)
Jared Duke (Google)
Advait Jain (Google)
Vijay Janapa Reddi (Harvard University)
Nat Jeffries (Google)
Jian Li (Google Inc.)
Nick Kreeger (Google)
Ian Nappier (Google)
Meghna Natraj (Google)
Tiezhen Wang (Google)
Pete Warden (Google)
Rocky Rhodes (Google)
Rocky Rhodes (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors