TinyML: Ultra-low power Machine Learning

• voice-controlled-robot

  3 145 0.0 Jupyter Notebook

  A voice-controlled robot using the ESP32 and TensorFlow Lite

  

This my voice controlled robot: https://github.com/atomic14/voice-controlled-robot

It does left, right, forward and backward. That was pretty much all I could fit in the model.

And here’s wake word detection: https://github.com/atomic14/diy-alexa

It does local wake word detection on device.

• diy-alexa

  4 478 3.4 Jupyter Notebook

  DIY Alexa

  

This my voice controlled robot: https://github.com/atomic14/voice-controlled-robot

It does left, right, forward and backward. That was pretty much all I could fit in the model.

And here’s wake word detection: https://github.com/atomic14/diy-alexa

It does local wake word detection on device.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• microflow-rs

  1 58 7.8 Rust

  A Rust TinyML compiler for neural network inference on embedded systems

I built a Rust TinyML compiler for my master thesis project: https://github.com/matteocarnelos/microflow-rs

It uses Rust procedural macros to evaluate the model at compile time and create a predict() function that performs inference on the given model. By doing so, I was able to strip down the binary way more than TensorFlow Lite for Microcontrollers and other engines. I even managed to run a speech command recognizer (TinyConv) on an 8-bit ATmega328 (Arduino Uno).

• esp-nn

  3 112 4.7 Assembly

  Optimised Neural Network functions for Espressif chipsets

  

There are a range of ML acceleration possible on existing chips. The basic 4-wide 8 bit integer SIMD extensions in NEON is available on basically all ARM Cortex M4F chips, which is already available 8+ years. It gives 4-5x speedup for neural networks.

The more recent ESP32-S3 has operations with up to 10x speedup, see https://github.com/espressif/esp-nn

Then there are RISCV chips with neural network co processors like Kendryte K210.

ARM has also defined a new set of extensions for NN acceleration, and reference designs for cores being ARM Cortex M85. Chips are becoming available this year.

• Arm-Helium-Technology

  1 6 5.7

  A reference book on M-Profile Vector Extensions (MVE) for Arm Cortex-M Processors

  

• SaaSHub

  www.saashub.com featured

  SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

  

Suggest a related project