Inference embedded PC features vision processing units
AI is processed by the PC’s two Intel Movidius Myriad X VPUs to provide excellent inference performance per watt, 16 SHAVES cores for AI calculations and native FP16 support. The hardware is supported by Intel’s OpenVINO open source toolkit for end-to-end acceleration in a wide range of neural networks. OpenVINO allows CNN-based, pre-trained models to be easily deployed at the edge. Training models from Caffe or Tensorflow can also be implemented quickly and easily.
The ITG-100AI is powered by an Intel Atom x5-E3930 Apollo Lake SoC supported by 8GByte DDR3L memory. A 128GB SATA DOM is included for Linux or Windows 10 and the OpenVINO Toolkit, and the training model. Peripheral devices can be connected to the two LAN GbE, RS-232/422/485 and USB 3.0 interfaces. The ITG-100AI can be used in areas with a temperature range from – 20°C to +50°C.
More information
Related news
ICP Deutschland launches thin Mini-ITX Mainboard
Simultaneous power for mainboard and 24V peripherals
Rugged industrial PC is ideal for fleet management applications
Embedded board adds AMD power
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
