Embedding deep neural networks at the push of a button

CDNN2 enables localized, deep learning-based video analytics on camera devices in real time, significantly reducing data bandwidth and storage compared to running such analytics in the cloud, while lowering latency and increasing privacy. A key component within the CDNN2 framework is the offline CEVA Network Generator, which converts a pre-trained neural network to an equivalent embedded-friendly network in fixed-point math at the push of a button. CDNN2 deliverables include a hardware-based development kit which allows developers to not only run their network in simulation, but also to run it with ease on the CEVA development board in real-time. Improving on CEVA’s first generation neural network software framework (CDNN), CDNN2 adds support for TensorFlow, Google’s software library for machine learning, as well as offering improved capabilities and performance for the most…


Link to Full Article: Embedding deep neural networks at the push of a button