Visit Xilinx at CVPR 2018 to learn about quantized neural networks on embedded devices.

The following showcases and demos will be featured throughout the show in the Xilinx booth # 501.

Robotics Kit
Robotic car controlled by Xilinx PYNQ board demonstrates CNN and OpenCV acceleration for automotive.

Quad-Camera Machine Learning
High-performance CNN recognition on four live cameras simultaneously with a single Xilinx device.

Heterogeneous Sensor Fusion
Computer vision hardware acceleration of stereo depth, optical flow and CNN.

Cloud Surveillance with ML Analytics
Enabling better cloud video analytics with integrated transcoding and Machine Learning Inference on Amazon EC2 F1 instances powered by Xilinx FPGAs.

PYNQ-TinyYOLO
A realtime, low-latency, low-power object detection system using PYNQ running on a Zynq® UltraScale+™ MPSoC. CNN is based on the Darknet reference network.

PYNQ-OpenCV Acceleration
A subset of Xilinx’s xfOpenCV libraries are exposed at the Python level using PYNQ. OpenCV components are accelerated in Programmable Logic.