Nvidia’s $99 Jetson Nano Developer Package brings GPU-supercharged AI smarts to maker initiatives

Machine studying is coming to the lots, and people hordes of DIY drones and robots are about to get a complete lot smarter. On Monday at Nvidia’s GTC convention, the corporate plans to disclose the $99 Jetson Nano Developer Package. The equipment is an enlargement of the corporate’s “Jetson” embedded graphics platform, and it goals to infuse your wildest maker initiatives with AI that the Raspberry Pi may solely dream of. It’ll be out there instantly on-line, by distributors, and at GTC itself.

The Jetson Nano Developer Package is a standalone model of the brand new Jetson Nano AI laptop additionally introduced at present. As you’d anticipate from an Nvidia product, the GPU’s the key sauce—a 128-core beast that looms giant on the maker board. Based mostly on the “Maxwell” GPU structure that powered the corporate’s GeForce GTX 900-series graphics playing cards, it’s able to 472 GFLOPS of FP16 efficiency, HEVC video encoding at both 4K30 or 3x 1080p30 decision, and HEVC decoding at 4K60 or 8x 1080p30—which means it might monitor a number of high-definition video inputs without delay and course of the pictures it sees in actual time. It is a highly effective GPU handy to makers. It’s tamed by a large black heatsink sitting atop the module.

Brad Chacos/IDG

Click on to enlarge

Nvidia fleshed out the board with a 1.43GHz quad-core ARM A57 processor, 4GB of 64-bit LPDDR4 reminiscence, and gigabit ethernet. Storage is dealt with through a bring-your-own SD card, identical to with the Raspberry Pi. Additionally just like the Raspberry Pi, the Jetson Nano Developer Package is loaded with {hardware} connections designed to reveal the board’s smarts to the world. Nvidia outfitted the board with three USB 2.Zero ports, a USB 3.Zero port, a MIPI-CSI digicam connector, HDMI 2.0, DisplayPort 1.2, and I2S audio out, together with enlargement choices for a Wi-Fi card, a fan, and a UART header.  

You’ll additionally discover a 40-pin GPIO header. Nvidia says the Jetson Nano Developer equipment will help the Blinka library and thus many Adafruit peripherals. Directions explaining how you can configure the header to work with different add-on {hardware} might be discovered within the Jetson GPIO Python library.

jetson nano dev kit Nvidia

As with many different maker boards, the Jetson Nano Developer equipment doesn’t ship with an influence provide, so that you’ll have to deliver your individual customary 5V/2A-3.5A micro-USB energy charger. Should you plan on operating notably intense benchmarks or workloads, Nvidia recommends utilizing a 5V/4A DC energy provide as an alternative. The board might be configured to function in both 5W or 10W mode relying on the depth of your duties.  

After all, {hardware} is just half of the equation. That fancy GPU can’t do a lot with out software program to inform it what to do.

Jetson helps Linux4Tegra, an working system derived from Ubuntu 18.04. It additionally helps widespread deep studying software program frameworks like TensorFlow, PyTorch, Caffe, Keras, and MxNet throughout all kinds of fashions. The board’s hefty {hardware} assist it run a variety of AI frameworks and neural networks a lot quicker than competing options, in accordance with Nvidia, together with a Raspberry Pi outfitted with Intel’s Compute Stick.

jetson ai Nvidia

The Jetson Nano Developer Package additionally helps Jetpack, Nvidia’s repeatedly up to date software program improvement equipment that runs throughout your entire Jetson embedded merchandise portfolio. Nvidia has been creating Jetpack for over three years at this level. The corporate additionally created a pair of tutorials dubbed “Hey AI World” and “Two Days to a Demo” that designate totally different inferencing and coaching approaches for makers who aren’t used to deep studying.

Lastly, Nvidia developed an open-source “JetBot” AI project that shows off the Jetson Nano’s capabilities. Here’s how the reviewer’s guide describes the project:

“Through the ​J​etBot project makers and learners can get the hands-on experience needed to create innovative and fun AI projects with Nvidia Jetson Nano.  The project achieves this by taking the user from the basics of motor control and camera image acquisition to high level tasks like data collection and AI training, where you teach JetBot to follow objects, avoid collisions and more.”

1 jetson nano pressgraphic 2000x1200 Nvidia

The JetBot project for Nvidia’s Jetson Nano Dev Kit.

Sounds pretty nifty! Nvidia sent Haveaheartsavealife a review unit to try out JetBot and the inferencing tutorials, but it arrived too late for us to test it before the announcement. We’re hoping to have a more extensive follow-up some point soon. If you’re interested in dabbling in deep learning projects, the Jetson Nano Developer Kit goes on sale today. Curious makers should visit the Jetson developer site for all the info you need to get started with Nvidia’s tiny, affordable AI board.

To comment on this article and other Haveaheartsavealife content, visit our Facebook page or our Twitter feed.

Leave a Reply

Your email address will not be published. Required fields are marked *