< Jetson
Revision as of 22:00, 16 December 2014 by Shervin.emami (talk | contribs) (Created a cuDNN page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

cuDNN is NVIDIA's GPU-accelerated library of primitives for deep neural networks and machine learning. It is integrated into higher-level machine learning frameworks such as UC Berkeley’s Caffe software, and is now available for Jetson TK1.

There is an overview of cuDNN for embedded on the Parallel ForAll Blog, and you can download it from its webpage.