While the price range of the Raspberry Pi has expanded (and increased) with the addition of variants with more memory, Nvidia is going in the opposite direction with the Jetson Nano by making it more affordable and accessible. Nvidia just announced a new 2GB variant of the Jetson Nano developer kit for the tempting price of $ 59. The board is essentially the same as the standard Jetson Nano, but has 2GB of RAM instead of 4GB. It uses the same processor, which means you get an integrated 128-core Maxwell GPU with a maximum of 921 MHz and a 64-bit quad-core Arm Cortex-A57 CPU with up to 1.43 GHz . Nvidia states the total performance of the processor at 472 GFLOPs. The board also includes Gigabit Ethernet, a video processor that can handle up to 4K 30fps encoding or 4K 60fps decoding, and support for PCIE and USB 3.0.
See also: Jetson Nano review
As with the first Jetson Nano, the video capabilities are impressive. While 4K 60fps decoding means you can use it to watch high definition video, the main point is that the board can handle multiple video streams (think automated machines with multiple cameras) for object detection, tracking, and obstacle avoidance. In addition to 4K at 60 fps, the Jetson Nano can decode eight video / camera feeds with 1080p and 30 frames per second! Once decoded, the streams can be processed simultaneously by the machine learning algorithms for object tracking and more.
To get around the $ 59 price point, there are a few other differences between the 4GB and 2GB variants of the Jetson Nano. Most noticeably, the 2GB version only has one USB 3.0 port (compared to four on the 4GB model) but adds two USB 2.0 ports. The DisplayPort socket has been removed from the card, but the HDMI connector remains. In addition, the development board is now supplied with power via USB-C and the Power Brick is not included in the scope of delivery.
Another Raspberry Pi Killer?
The Raspberry Pi has been updated since the original Jetson Nano was released in March 2019. The newer Raspberry Pi 4 has a 1.5 GHz 64-bit quad-core Arm Cortex-A72 processor, which is faster than the quad-core Cortex-A57 in the Nano. While the Raspberry Pi 4 has the edge in terms of CPU performance, the Nano is still the champion when it comes to GPU performance. And for AI, that GPU performance translates directly into machine learning performance.
Nvidia offers a uniform development environment (the Nvidia JetPack SDK) on all Jetson boards. You could start developing a project on the Jetson Nano. However, if you need more GPU power, upgrading to a more advanced Jetson board (like the Jetson Xavier NX) will have little or no downside from a software standpoint.
Official Raspberry Pi 4 prices are $ 55 for the 4 GB variant and $ 75 for the 8 GB variant. This is the equivalent of $ 59 for the 2GB Jetson Nano and $ 99 for the 4GB version. The bottom line is that the Pi 4 is a better choice when you need brutal CPU power. However, if you need machine learning, a faster GPU, and better video encoding / decoding, the Nano is a better choice.
Next: The best Raspberry Pi projects for everyone
Jetson Deep Learning Institute (DLI) courses
The new Jetson Nano 2 GB Developer Kit is great for students, educators, and enthusiasts to explore machine learning and robotics. It is intended to be an accessible platform for teaching, learning and developing AI and robotics applications. To that end, Nvidia has also announced the availability of free online training and certification programs that complement the existing open source projects, guides, and videos contributed by the Jetson developer community.
The Jetson DLI courses consist of a range of hands-on learning programs, turn-key video solutions, and project-based assessments for educators and learners. The Jetson AI Fundamentals course covers the basics of training / inference workflow, real-time computer vision, classification and regression networks, and object recognition and semantic segmentation.
The program includes two levels of certification: 1) The Jetson AI Specialist certification for students, makers, and hobbyists. 2) The Jetson AI Educator Certification for educators and instructors who wish to teach AI in their own classes or courses.
When and from where?
The Jetson Nano 2GB Developer Kit will be available through Nvidia’s sales channels later this month (October 2020) for $ 59. I should get my hands on a board very soon, so check out a full review here and on Gary Explains’ YouTube channel.