Getting Started with NVIDIA Jetson Nano Part 1: Setup – Maker.io Tutorial | DigiKey

The NVIDIA Jetson Nano is a single-board computer (SBC) based on the Tegra X1 processor. In this tutorial, we show you how to connect accessories to the Jetson Nano, set up Linux (Ubuntu), and install the necessary packages. The Nano is an affordable way to get started with Edge AI on an embedded system. It is capable of running NVIDIA’s CUDA language, which allows us to parallelize many machine learning tasks for faster execution. Frameworks that support CUDA, such as TensorFlow and PyTorch, work well on the Jetson Nano. Over the next few episodes, we’ll show you how to configure the Jetson Nano for machine learning development and run a few of the canned demos in the jetson-inference repository. Note that because the Nano is a small, (relatively) low-powered SBC, we would not advise using it to train large deep neural network models. Generally, you would want to train models on a larger computer, such as your desktop or cloud-based server, and then copy the model to the Nano. From there, you can use the Nano to perform predictions, classifications, etc. using the trained model.