From April 2020, we are stocking Jetson Nano Developer Kit with version B01 carrier board. These are the changes that come with updated version B01:
J48, Power Select Header position changed, a jumper is included
J13, CSI Camera connector position changed
J49, New CSI camera connector added
J40, Button header removed
J44, Serial Port header removed
Compatible with production specification Jetson Nano module
NVIDIA Jetson Nano is an entry level embedded system-on-module (SOM) from the Jetson family, focusing on Artificial Intelligence (AI), Computer Vision and Deep Learning. It delivers 472 GFLOPs to support modern AI algorithms and can run multiple neural networks in parallel as well as handling several high-resolution sensors simultaneously. All of these while consuming just 5 to 10 Watts.
The developer kit aims to provide a low cost and easy way to use Jetson Nano for students, hobbyists, makers and developers. It comes with a non-production specification Jetson Nano SOM (the part that handles all the computation) and a reference carrier board (the part that handles input and output connectivity to the system).
The Jetson Nano is supported by JetPack SDK which is a unified software stack for all Jetson modules.
Micro SD card installed with JetPack SDK (32 GB and above recommended)
Monitor that supports HDMI or Display Port and the appropriate HDMI or DP cable
Software: JetPack SDK
The JetPack SDK provides a complete desktop Linux environment for Jetson Nano based on Ubuntu 18.04 with accelerated graphics, support for NVIDIA CUDA Toolkit 10.0, and libraries such as cuDNN 7.3 and TensorRT 5.The SDK also includes the ability to natively install popular open source Machine Learning (ML) frameworks such as TensorFlow, PyTorch, Caffe, Keras, and MXNet, along with frameworks for computer vision and robotics development like OpenCV and ROS.
Technical specifications for Jetson Nano Developer Kit:
