TinyML Applications with PyTorch

How to bring models developed with PyTorch on Microcontrollers like Arduino

on-device TinyML and embedded ML applications running on battery without internet connectivity are gaining ground primarily because of TinyML features including low power, low latency and enhanced privacy benefits. Deploying AI models on the tinyML devices like microcontrollers (aka MCUs) is a tough proposition. Complexities range from developing right model, choosing right framework, model conversion, to identifying the right MCU to fit the use case, etc.

The next video takes you step-by-step through how to develop a deep learning model with PyTorch. Rohit Sharma from AI Tech Systems (AITS), a leading firmware, software and services provider for low power IoT, Endpoint and tinyML devices, demonstrates how PyTorch can be used on Microcontrollers. Get an in-depth look at how to bring on-device AI applications to a multitude of verticals, including Industrial IoT, smart space and much more as AITS showcase a live demo using Arduino and STM32F07 boards.

You can download slides on bringing PyTorch Models to ARM Cortex M Processors here.

AITS Slides For ARM VTT.pdf

Here are a few examples of PyTorch Applications written in PyTorch

  1. Spoken Digit Recognition

  2. American Sign Language

  3. MNIST Digit Recognition

To stay up-to-date on other PyTorch app, sign up for Cainvas and search PyTorch.