Machine vision firm runs AI deep learning on Nvidia platform | Electronics Weekly

"MVTec Software, a Munich-based machine vision specialist, says it it now possible to run deep learning functions on embedded boards with Nvidia Pascal architecture" continues Electronics Weekly.

HALCON's deep learning now on NVIDIA Jetson boards

The deep learning inference in the latest version of the firm’s Halcon machine vision software was successfully tested on Nvidia Jetson TX2 boards based on 64-bit Arm processors.

The deep learning inference, i.e., applying the trained CNN (convolutional neural network), almost reached the speed of a conventional laptop GPU (approx. 5 milliseconds), says MVTec...

Photo: Dr. Olaf Munkelt

Dr. Olaf Munkelt, managing director, MVTec Software, believes the rapidly growing market for embedded systems requires corresponding high-performing technologies.

“AI-based methods such as deep learning and CNNs, are becoming more and more important in highly automated industrial processes. We are specifically addressing these two market requirements by combining HALCON 17.12 with the NVIDIA Pascal architecture,” said Munkelt.
Read more...

Source: Electronics Weekly