Nvidia Jetson Nano Android
Android tv on the nvidia jetson development kit.
Nvidia jetson nano android. However new designs should take advantage of the jetson tx2 4gb a pin and cost compatible module with 2x the performance. Jetson nano is a fully featured gpu compatible with nvidia cuda libraries. See the jetson android announcement on the forum the instructions in this article relied on a repository that has since been removed and is here only for historical purposes. Looking to bring an ai enabled product to market.
Today we are bringing those benefits over to our open source jetson nano xavier nx platform. The jetson nano is a small powerful computer designed to power entry level edge ai applications and devices. Since this article was written nvidia has announced official support for android on jetson. A few years ago we wrote a blog note about choosing android for embedded applications where we described how various industrial and consumer facing systems can benefit from this os.
There are several commercial products that run android on the nvidia tk1 chip including nvidia s shield tablet. Nvidia has just announced a new 2gb variant of the jetson nano developer kit at the tempting price of 59. The jetson nano is nvidia s latest machine learning board in its jetson range. Having a cheap cuda equipped device we thought let s build a machine learning cluster.
The board is essentially the same as the standard jetson nano but has 2gb of ram rather. The nvidia jetson nano developer kit is a small ai computer for makers learners and developers. It costs just 99 for a full development board with a quad core cortex a57 cpu and a 128 cuda core maxwell gpu. Learn more about jetson tx1 on the nvidia developer zone.
Android on jetson a natural consequence. Project dedicated to running android tv builds on the nvidia jetson tk1 development kit. The jetson tx1 module is the first generation of jetson module designed for machine learning and ai at the edge and is used in many systems shipping today. Cuda is the de facto standard for modern machine learning computation.