This device – ” NVIDIA® Jetson Nano™ Developer Kit is a small, powerful computer that lets you run multiple neural networks in parallel for applications like image classification, object detection, segmentation, and speech processing. All in an easy-to-use platform that runs in as little as 5 watts. “ – source Nvidia.com
Tracking development using the Nvidia NanoAI – Click here for the reference page.
Useful links:
- Pytorch for Jetson nano
- Deep Learning Inference Benchmark – Jetson Nano
- Deep Learning inference benchmarking instructions
This works you through…
“The power of AI is now in the hands of makers, self-taught developers, and embedded technology enthusiasts everywhere with the NVIDIA Jetson Nano Developer Kit. This easy-to-use, powerful computer lets you run multiple neural networks in parallel for applications like image classification, object detection, segmentation, and speech processing. In this course, you’ll use Jupyter iPython notebooks on your own Jetson Nano to build a deep learning classification project with computer vision models. “ ..nvidia.com
Below is the development board l have: $99
Click here for Jetson Community Projects
Specs:
Related Information:
Summit Supercomputer – identified chemicals that could stop coronavirus from spreading, very important step toward a vaccine
200 Petaflops, 200 Quadrillion calculations per sec, faster than 1 million of the fastest laptops.
5.21.2020
Screenshots of a remote session from my Ubuntu workstation terminal into the nanoai.
Good resource link(s) discovered:
– Getting Started with the Jetson Nano – click here.
Image recognition with Pytorch on Jetson Nano
5.22.2020 – Work continued using the two links above, screenshot outputs below.
Currently using the great resource here at Jetson Zoo
I successfully installed tensorflow 1.15 on the Jetson Nano AI , l ended up having to use scp to get the files remotely into my nanoai.
Note – l am using a 256Gb Samsung evo MicroSD card on the Jetson Nano AI board – microSD cards are now very relatively cheap and this allows for a larger local dataset.
Click here for Jetson Nano Deep inference benchmarks – Nvidia
Pytorch