Open source NVIDIA Jetson Nano emulator for A.I. newbies

If you are new to A.I., exploring what’s what, and thinking of investing in an NVIDIA Jetson Nano single board computer, you might want to take a look at the open source Jetson AI-Computer Emulator first. It’s an application-level emulator of the Jetson hardware that has been created by machine-learning software engineer Tea Vui Huang.

The emulator mimics aspects of NVIDIA’s JetPack SDK, which offloads work to CUDA cores in a GPU to speed up execution. It’s suited to tasks such as image recognition, object detection, and image segmentation, though users are only allowed to use pre-selected images. Install the emulator package on your PC along with the Anaconda Python environment, import the emulator directly into your Python scripts, and off you go.

You get the same Jetson Python interfaces, including the Inference and Utilities API. When you want to progress to the next stage, buy a Jetson Nano and get access Nvidia’s libraries, which use the onboard Nano hardware to accelerate operations such as inference and decision making by trained neural networks, so you can see how it works with Nvidia’s CUDA-based acceleration

“It’s something that I wish I had when I was just getting interested in AI. It returns the data in a format that is exactly what a Jetson Nano would give, and you learn that nothing is 100 per cent concrete in machine learning. It’s all guesswork and prediction.

For example, users can see that models give outputs in terms of a bounding box and a percentage. It’s not totally confident that it’s just detected, say, a bicycle. That’s what AI is like in real-life too. It shows people the realistic boundaries of AI.

Imagine something like a self-driving car: it uses an object detection model to detect other cards, road signs, so on; if an object it’s looking at is obstructed by something like a tree it becomes less confident in identifying that object.

Tea Vui Huang

The first generation Jetson Nano is $99 with 4GB of RAM with a Maxwell GPU with 128 CUDA cores to run AI workloads, and four Arm Cortex-A57 CPU cores at 1.43GHz. A newer $59 version has 2GB of RAM.

Source: The Register