Getting Started with NVIDIA Jetson Nano Part 2: Image Classification | Digi-Key Electronics

The NVIDIA Jetson Nano is a single-board computer (SBC) based on the Tegra X1 processor. In this tutorial, we show you how to use the jetson-inference tools to train an existing deep neural network to recognize different objects.
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.
To start, we demonstrate the built-in demo of identifying a dog in real time using a webcam. From there, we move to training our own deep neural network.
For most use cases, you would want to train networks using a larger, more powerful computer, like a desktop or server. However, we can use transfer learning to train an existing network to perform similar tasks, including identifying images. We’ll use the Jetson capture tool to create a basic training set of images and use them to train a model. We can then use that model to identify images from a webcam.
Product Links:
NVIDIA Jetson Nano - www.digikey.co...
5V, 4A Power Supply - www.digikey.co...
32 GB microSD Card - www.digikey.co...
Raspberry Pi Camera Module V2 - www.digikey.co...
Related Videos:
Getting Started with NVIDIA Jetson Nano Part 1: Setup - • Getting Started with N...
Intro to Edge AI: Machine Learning + IoT - • Intro to Edge AI: Mach...
Learn more:
Maker.io - www.digikey.co...
Digi-Key’s Blog - TheCircuit www.digikey.co...
Connect with Digi-Key on Facebook / digikey.electronics
And follow us on Twitter / digikey

[@typhoon9945]

Great content!! I'm really interested in the Jetson.

[@saultes]

This is a great video, we want more on AI and ANN on the nano!

[@sunil76jos]

I am getting a segmentation fault at time 12:12 after following the video, after saving checkpoint. Any clue?

[@johnmoore4248]

Hello Shawn, I would like a program to know distinguish my family members and others from camera feed. How can i do that? I am new to AI so I don't have knowledge. Could you tell me is it possible to do in nano? I think i need to retrain as in this video but by doing so it will only be shown as person rather than like (mom, dad). I am really appreciated if you could answer these questions. Have a great day. Cheers

[@ShawnHymel]

What you are looking to do is called "facial recognition." There are other libraries out there that make the process of training and filling a facial recognition database much easier than what's shown in these videos. I recommend taking a look at this article to get started: medium.com/@ageitgey/build-a-hardware-based-face-recognition-system-for-150-with-the-nvidia-jetson-nano-and-python-a25cb8c891fd

[@oumardiop1]

anybody having a problem with the pytorch module not being installed when running the train.py file?

[@EfrainMcshell]

this cool is kid.......

[@oumardiop1]

very kid