The OpenVINO™ toolkit offers software developers a single toolkit to accelerate their solutions across multiple hardware platforms including FPGAs. Intel® FPGAs offer fast to market, scalable, and customizable solutions.
OpenVINO™ toolkit with the Deep Learning Deployment Toolkit (DLDT) enables you to go from Caffe* or TensorFlow* to hardware with no FPGA experience.
We have developed Intel® FPGA Deep Learning Acceleration Suite (Intel® FPGA DL Acceleration Suite) to scale to a wide array of networks.
The unique architecture of FPGAs provides the flexibility needed to support custom primitives.
This video demonstrates how an Intel® FPGA Programmable Acceleration Card (Intel® FPGA PAC) and OpenVINO™ toolkit can be used to accelerate vision inference where people are detected, identified, and tracked across multiple camera feeds. The design also contains a cryptographic block inside the Intel® FPGA that allows the user to encrypt the trained model before use to protect intellectual property.