AI (artificial intelligence) is taking the world of IoT by storm. While many aspects of AI are computing- and resource-intensive, others rely on small and swift devices that can quickly deliver results. Innodisk’s new AI accelerator cards provide exponential performance gains for AI inference on the edge.
They use Intel’s third-generation Movidius Myriad X Vision Processing Unit (VPU), which is designed for deep neural network inference. As such, the VPU enhances all vision inference applications such as facial recognition, vehicle registration plate recognition and many other machine vision applications. The results enable an up to a 30-fold boost in performance depending on the edge device’s CPU.
Embedded devices typically found on the edge are ill-equipped for image recognition. The CPU is normally chosen for its low power consumption and thermal efficiency, making it particularly unsuited for AI inference. Much like a video card takes the load off the CPU for graphics rendering in PCs, the VPU assists edge devices in picking out objects and patterns in images and videos. Innodisk’s new AI accelerator cards achieve all this while leaving a small thermal footprint and maintaining low power consumption.
Innodisk’s AI accelerator cards have no minimum order quantity and come in two form factors: mPCIe with one Myriad X (EMPA-I101); and M.2 2280 with two Myriad X (EGPA-I201) inside. Windows and Linux are supported and deep learning frameworks such as Caffe, TensorFlow, Apache MXNet, and Open Neural Network Exchange (ONNX) are also supported through the Intel OpenVINO™ toolkit.
Cabinets for industrial applications Vepac Electronics
Enclosures, Racks, Cabinets & Panel Products
Verotec’s VERAK cabinets addresses the most stringent enclosure requirements providing both IP65 environmental protection and EMC screening.
Read more...Vertiv expands rack PDU portfolio
Computer/Embedded Technology
Vertiv has announced its new Vertiv PowerIT rack power distribution units designed to address the rising power needs of data-intensive workloads, including AI and high-performance computing.
Read more...Rugged PoE switch built for industrial demands Conical Technologies
Computer/Embedded Technology
The rugged Planet IGS-5225-8P4S-12V comes in a compact, rugged, and highly efficient design, making it the switch of choice for engineers working in harsh environments.
Read more...High-performance networking for demanding environments Electronic Products Design
Computer/Embedded Technology
The Raptor-Epsilon Ethernet switch system is a ruggedised networking solution engineered to deliver advanced switching capabilities, superior reliability, and energy-efficient operation in the most demanding environments.
Read more...SIGLENT launches new 8 GHz DSO Vepac Electronics
Test & Measurement
SIGLENT has unveiled the enhanced SDS7000A/AP models, building on the success of its SDS7000A high-resolution digital oscilloscope series.
Read more...Rugged, I/O-rich NVIDIA Jetson solutions Electronic Products Design
Computer/Embedded Technology
Developed for the NVIDIA Jetson AGX Orin, the Osbourne carrier and development kit is a compact and rugged platform designed to support a wide range of embedded AI and edge computing applications.
Read more...Mission-critical RF transceiver Vepac Electronics
Telecoms, Datacoms, Wireless, IoT
The Iris SQN9506 from Sequans Communications is a wide-band RF transceiver that operates from 220 MHz to 7,125 GHz.
Read more...New generation of SBCs
Computer/Embedded Technology
HardKernel’s new generation of ODROID H4-series SBCs are more powerful; offering higher performance and richer interfaces than previous generations.
Read more...Smallest 13th gen Intel SBC Vepac Electronics
Computer/Embedded Technology
At just 86 x 55 mm, the de next-RAP8 continues AAEON’s run of producing record-breaking single-board computers with embedded Intel technology.
While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.
printer friendly version