TensorFlow Lite for Microcontrollers (TF Dev Summit '20)
TensorFlow Lite for Microcontrollers or TFLite Micro is designed to run machine learning models on microcontrollers and other embedded devices. The key advantages are low energy consumption, small size, network connectivity is not required, privacy by running inference on-device and a large scale impact as billions of microcontrollers are embedded within hardware every year.
In this video, we demostrate running a tiny ~250KB binary image classification model which detects if a person is present in the image captured by the SparkFunEdge microcontroller (https://goo.gle/3auscnH). If the microcontroller detects a person, the green LED lights up; otherwise the orange LED lights up. Every time it runs an inference, the blue LED toggles.
Meghna Natraj – Software Engineer
Pete Warden – Staff Software Engineer
Jason Mayes – Senior Developer Advocate
Here are some resources to get started:
Website → https://goo.gle/2yiYyUl
Github → https://goo.gle/2UsBkDW
Examples (generate a sine wave, person detection, simple audio recognition, magic wand) → https://goo.gle/3dGu3rq
TinyML Book → https://goo.gle/2JqBZPI
Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20
Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow
event: TensorFlow Dev Summit 2020; re_ty: Publish; product: TensorFlow – TensorFlow Lite; fullname: Jason Mayes, Pete Warden;