SENSORO and Graphcore partner for safer, greener towns and cities
Il sito "il Centro Tirreno.it" utilizza cookie tecnici o assimiliati e cookie di profilazione di terze parti in forma aggregata a scopi pubblicitari e per rendere più agevole la navigazione, garantire la fruizione dei servizi, se vuoi saperne di più leggi l'informativa estesa, se decidi di continuare la navigazione consideriamo che accetti il loro uso.
30
Sab, Mag

Abbiamo 2493 visitatori e nessun utente online

SENSORO and Graphcore partner for safer, greener towns and cities

Immediapress
Typography
  • Smaller Small Medium Big Bigger
  • Default Helvetica Segoe Georgia Times

BEIJING, Dec. 21, 2021 /PRNewswire/ -- SENSORO - a worldwide leader in smart sensor and beacon technology - has chosen Graphcore systems to deliver the AI compute behind its latest environmental and safety monitoring systems. 

Graphcore IPUs will power a range of SENSORO solutions, designed to help towns and cities become safer,

greener places to live. 

Smart sensors are emerging as an essential tool in the management of modern, urban environments as they transition to more sustainable forms of energy and transportation, while also dealing with the effects of climate change. 

Fire, flood and fishing 

SENSORO will initially use Graphcore IPU compute for: 

Computing foundation 

SENSORO founder and CEO Tony Zhao welcomed our partnership, saying: "Graphcore's IPU system provides an efficient and easy-to-use computing platform for the urban ESG solution jointly created by both parties, and solves the computing power bottleneck that we have faced for a long time. We will be continuing to work with Graphcore, and using the IPU to deliver positive change in more aspects of people's lives." 

YOLO 

One of the main AI models used by SENSORO, running on Graphcore IPUs, is YOLO. 

YOLO (You Only Look Once) is a highly effective convolutional neural network for real-time object detection. Since the release of the first version in 2015, it has undergone a number of refinements to improve speed and accuracy. 

SENSORO found that the IPU's fine-grained and highly parallel compute capabilities lent themselves to the parallelisation required to get the most out of YOLO. 

When running inference on high resolution images (1920x1080px), SENSORO saw a 4X performance gain, compared to the GPU-based inference solution they had been using previously. 

Photo - https://mma.prnewswire.com/media/1714359/1st_photo.jpg  Photo - https://mma.prnewswire.com/media/1714316/SENSORO.jpg   

 

Author: RedWebsite: http://ilcentrotirreno.it/Email: Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo.