Deep-Learning AI on Low-Power Microcontrollers: MNIST Handwriting Recognition Using TensorFlow Lite Micro on Arm Cortex-M Devices

Raphael Mun

16 Apr 2020CPOL10 min read

17.6K

In this article we’re going to build a fully functional MNIST handwriting recognition app using TensorFlow Lite to run our AI inference on a low-power STMicroelectronics microcontroller using an Arm Cortex M7-based processor

This article looks at: Training a TensorFlow model with MNIST, converting your model to TensorFlow Lite, creating the embedded app, generate sample MNIST data for embedding, and testing the MNIST images.

This article is in the Product Showcase section for our sponsors at CodeProject. These articles are intended to provide you with information on products and services that we consider useful and of value to developers.

Views

Daily Counts

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Written By

Raphael Mun

United States

Raphael Mun is a tech entrepreneur and educator who has been developing software professionally for over 20 years. He currently runs Lemmino, Inc and teaches and entertains through his Instafluff livestreams on Twitch building open source projects with his community.

Deep-Learning AI on Low-Power Microcontrollers: MNIST Handwriting Recognition Using TensorFlow Lite Micro on Arm Cortex-M Devices

Views

License

Comments and Discussions