The NVIDIA Jetson Nano Developer Kit is a small yet powerful computer designed for makers, learners, and embedded developers. With its 128-core Maxwell GPU and quad-core ARM A57 CPU, it can run multiple neural networks in parallel for tasks such as image classification, object detection, segmentation, and speech processing, all while consuming only 5 watts of power.

Getting started is easy, simply insert a microSD card with the system image, boot the developer kit, and start using the NVIDIA JetPack SDK, which is compatible with NVIDIA’s world-leading AI platform. The Jetson Nano offers 4 GB of 64-bit LPDDR4 memory and has the ability to encode 4K video at 30fps and decode 4K video at 60fps. It also features Gigabit Ethernet, M.2 Key E connectivity, HDMI and DisplayPort, 4 USB 3.0 ports, and various other interfaces including GPIO, I2C, I2S, SPI, and UART. The device measures 69mm x 45mm and has a 260-pin edge connector.

Features:

128-core Maxwell GPU
Quad-core ARM A57 @ 1.43 GHz CPU
4 GB 64-bit LPDDR4 memory with 25.6 GB/s
Supports microSD (not included)
Video encoding: 4K @ 30, 4x 1080p @ 30, 9x 720p @ 30 (H.264/H.265)
Video decoding: 4K @ 60, 2x 4K @ 30, 8x 1080p @ 30, 18x 720p @ 30 (H.264/H.265)
2x MIPI CSI-2 DPHY lanes for camera connectivity
Gigabit Ethernet and M.2 Key E for connectivity
HDMI and display port for display
4x USB 3.0 and USB 2.0 Micro-B
Additional interfaces: GPIO, I2C, I2S, SPI, UART
Mechanical dimensions: 69 mm x 45 mm with 260-pin edge connector

Benefits:

Easy to use platform that runs on just 5 watts
Multiple neural networks can be run in parallel for various applications such as image classification, object detection, segmentation, and speech processing
Compatible with NVIDIA JetPack SDK, reducing complexity and effort for developers
System image can be easily loaded onto a microSD card and ready to use after booting the developer kit.