Benchmarking Edge Computing

#artificialintelligence

The arrival of new hardware designed to run machine learning models at vastly increased speeds, and inside a relatively low power envelope, without needing a connection to the cloud, makes edge based computing that much more of an attractive proposition. Especially as alongside this new hardware we've seen the release of TensorFlow 2.0 as well as TensorFlow Lite for micro-controllers and new ultra-low powered hardware like the SparkFun Edge. The ecosystem around edge computing is starting to feel far more mature. Which means that biggest growth area in machine learning practice over the next year or two could well be around inferencing, rather than training. Time to run some benchmarking and find that out.


How AI Accelerators Are Changing The Face Of Edge Computing

#artificialintelligence

AI has become the key driver for the adoption of edge computing. Originally, the edge computing layer was meant to deliver local compute, storage, and processing capabilities to IoT deployments. Sensitive data that cannot be sent to the cloud for processing and analysis is handled by the edge. It also reduces the latency involved in the roundtrip to the cloud. Most of the business logic that runs in the cloud is moving to the edge to provide low-latency, faster response time.


Superfast Raspberry Pi rival: Odroid N2 promises blistering speed for only 2x price

ZDNet

Hardkernel failed to deliver the $100 Rockchip RK3399-based Odroid-N1 developer board last year due to component shortages. But it's now back with a successor, the Odroid-N2, which is cheaper and performs significantly better in benchmarking tests. The Odroid-N2 won't be as cheap as the $35 Raspberry Pi, but it's also intended for a different market that's willing to pay for some extra memory, more ports, and a faster processor. The 2GB DDR4 RAM model will cost $63 while a 4GB DDR4 RAM model costs $79. Notably, these figures are still well below the $100 price that Hardkernel had planned for the Rockchip-based Odroid-N1.


Google AI on Raspberry Pi: Now you get official TensorFlow support ZDNet

#artificialintelligence

Video: How to set up your Raspberry Pi 3 Model B . Besides putting a Raspberry Pi to work on a mini Mars rover, it's now going to be a lot easier to use Google's TensorFlow artificial-intelligence framework with the low-powered computer. Developers with Raspberry Pi have already been able to use TensorFlow in a variety of ways to add deep-learning models so that cheap or expensive hardware can do things like image classification. While TensorFlow can be used on Linux, Windows, Android, macOS, and iOS, it's hard to find cheaper hardware than the $35 Raspberry Pi. But as noted by Pete Warden, a software engineer and lead of the TensorFlow mobile and embedded team, running TensorFlow on Raspberry Pi "has involved a lot of work".


Google AI on Raspberry Pi: Now you get official TensorFlow support

ZDNet

Video: How to set up your Raspberry Pi 3 Model B . Besides putting a Raspberry Pi to work on a mini Mars rover, it's now going to be a lot easier to use Google's TensorFlow artificial-intelligence framework with the low-powered computer. Developers with Raspberry Pi have already been able to use TensorFlow in a variety of ways to add deep-learning models so that cheap or expensive hardware can do things like image classification. While TensorFlow can be used on Linux, Windows, Android, macOS, and iOS, it's hard to find cheaper hardware than the $35 Raspberry Pi. But as noted by Pete Warden, a software engineer and lead of the TensorFlow mobile and embedded team, running TensorFlow on Raspberry Pi "has involved a lot of work".