The Jetson Nano Developer Kit uses Ubuntu as the operating system.
NVIDIA Jetson Nano Developer Kit it's a 99 dollar computer built for those interested in Artificial Intelligence projects. It was developed for use with Ubuntu 18.04 and open source tools.
The Jetson Nano Developer Kit is aimed at embedded device designers, researchers, and hobbyists, allowing them to build their own kits. Can used to run applications for image classification, object detection, segmentation, and speech processing.
.
The NVIDIA Jetson Nano Development Kit consists of the Jetson chip (which can be purchased separately) pre-installed on a motherboard. The kit includes the power supply, the necessary power cables, and the software pre-installed on a MicroSD card.
The computer can be used in conjunction with the NVIDIA JetPack SDK that provides you a full desktop Linux environment based on Ubuntu 18.04 LTS, which also includes, graphics acceleration, compatibility with the NVIDIA CUDA toolkit and the cuDNN 7.3 and TensorRT 5 ″ libraries.
According to NVIDIA, developers will be able to easily install leading open source working solutions for machine learning (ML), like TensorFlow, Caffe and Keras. The same happens with frameworks for computer vision and robotics development like OpenCV and ROS.
Features
NVIDIA claims that the Jetson Nano provides 472 GFLOPS of computational performance from its 64-bit quad-core ARM CPU and an integrated 128-core NVIDIA GPU
The full list of its specifications is:
64-bit Quad-core ARM A57 CPU @ 1.43GHz
128-core NVIDIA Maxwell GPU @ 921MHz
RAM 4GB 64-bit LPDDR4 @ 1600MHz | 25.6 GB / s
VIDEO (encoded) 4Kp30 | (4x) 1080p30 | (2x) 1080p60
VIDEO (decoded) 4Kp60 | (2x) 4Kp30 | (8x) 1080p30 | (4x) 1080p60
CAMERA 1x MIPI CSI-2 DPHY lanes
NETWORK Gigabit Ethernet, M.2 Key E
VIDEO OUT HDMI 2.0 and eDP 1.4
Connectivity is an important requirement for this type of device. That is why it has 4 USB ports, as well as GPIO, I2C, I2S, SPI and UART.
However, you should not worry about energy consumption.
The Jetson Nano requires only 5W of power to run (up to 10W for intensive applications).
It is not a single board computer that can be used for a variety of uses like the Raspberry Pi or building gadgets like the Arduino. It has specific uses, but no one ever said that we cannot find applications for Artificial Intelligence in our home.
I don't know about you, but I already started the letter for Santa Claus.
For $ 99 USD? a great team!