Cue theme music..."Meet NVIDIA Jetson!" The latest addition the Jetson family, the NVIDIA® Jetson Nano™ Developer Kit (V3) delivers the performance to run modern AI workloads in a small form factor, power-efficient (consuming as little as 5 Watts), and low cost. Developers, learners, and makers can run AI frameworks and models for applications like image classification, object detection, segmentation, and speech processing. The developer kit can be powered by micro-USB and comes with extensive I/Os, ranging from GPIO to CSI. This makes it simple for developers to connect a diverse set of new sensors to enable a variety of AI applications. This version of the Jetson Nano Developer Kit comes equipped with two MIPI-CSI camera connectors which enables algorithms that perform stereo vision! We at SparkFun see this as more than enough potential to be yelling "Stop this crazy thing" to your friends & family!
Jetson Nano is also supported by NVIDIA JetPack™, which includes a board support package (BSP), Linux OS, NVIDIA CUDA®, cuDNN, and TensorRT™ software libraries for deep learning, computer vision, GPU computing, multimedia processing, and much more. The software is even available using an easy-to-flash SD card image, making it fast and easy to get started.
The same JetPack SDK is used across the entire NVIDIA Jetson family of products and is fully compatible with NVIDIA’s AI platform for training and deploying AI software. This proven software stack reduces complexity and overall effort for developers.
If a board needs code or communicates somehow, you're going to need to know how to program or interface with it. The programming skill is all about communication and code.
Skill Level: Experienced - You will require a firm understanding of programming, the programming toolchain, and may have to make decisions on programming software or language. You may need to decipher a proprietary or specialized communication protocol. A logic analyzer might be necessary.
See all skill levels
If it requires power, you need to know how much, what all the pins do, and how to hook it up. You may need to reference datasheets, schematics, and know the ins and outs of electronics.
Skill Level: Rookie - You may be required to know a bit more about the component, such as orientation, or how to hook it up, in addition to power requirements. You will need to understand polarized components.
See all skill levels
Based on 10 ratings:
1 of 3 found this helpful:
It is still ways away from being a developed solution. Too many bugs on the stock firmware. Remote desktop doesnt work. Supplied examples dont compile. Ubuntu crashes.
Quick and easy to set up.
Actually, the little computer is 'on its box', a curious way to keep one from shorting out the naked circuit board I am guessing. With a usb camera the Jetson Nano was quickly doing its best to label the scenes that I pointed the camera toward. This is done by feeding the images from the camera to a pre-computed neural network. Now, on to my project: Using machine learning to detect interesting signals in gigabytes of recorded underwater noise.
This is a great development board with lots of power for advanced AI and robotics. There is also lots of getting started materials and projects and if you are a Pi fanatic, this is easy as Pi.
This is my second Jetson Nano. The other one is a vA01 and this new one is a B02 (I think). These are great boards for learning and experimenting! I want to get a few more of these, plus the much more capable Jetson AGX Xavier.
0 of 2 found this helpful:
Honestly, I have never dealt with a company that has botched up a bill more times than this company. AND now they won't even return out calls or emails to get it figured out. Very VERY VERY disappointed with the service.
0 of 2 found this helpful:
I have wasted days, weeks trying to make the Jetson Nano usable. I have followed all recommended procedures on the nVidia website, bought its special memory card and power supply, fan and ethernet cable (because it has no wifi) but still.... it constantly freezes, crashes.. and ZERO support from a company who reported $3.08 billion income for the first quarter of 2020. I'm sure the hardware is as nice as they say, but the one-and-only operating system available for it is absolute garbage. It's not even capable of being a media center (if it could stay crash-free long enough to compile some).
So far it has been working great!
I installed it in the Geekworm N100 Metal Case with the Noctua 40mm fan. I did a lot of searching for a 22.5mm long screw to attach the fan even going so far as to get a 25mm long screw and shorten it using a Dremel. If you do get that case, it actually comes with 22.5mm long screws!
Perfect for my robot using stereo vision and object recognition. Looking forward to more community development in the future. Even got the FLiR Lepton working over GPIO with basically no changes from the RPi setup, fast and easy!
love that it has two camera connectors out of the box. works great, lots of fun to experiment with! just downloaded latest image from nvidia and "dd"'d to a micro sd card, voila, AI / ML workstation!