2014 Caffe Convolutional Architecture for Fast Feature Embedding.pdf

Caffe: Convolutional Architecture for Fast Feature Embedding ? Yangqing Jia ?, Evan Shelhamer ?, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell UC Berkeley EECS, Berkeley, CA 94702 {jiayq,shelhamer,jdonahue,sergeyk,jonlong,rbg,sguada,trevor}***@ ABSTRACT Ca?e provides multimedia scientists and practitioners with a clean and modi?able framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general- purpose convolutional works and other deep mod- els e?ciently modity architectures. Ca?e ?ts indus- try and -scale media needs by puta- tion, processing over 40 million images a day on a single K40 or Titan GPU (≈ ms per image). By separating model representation from actual implementation, Ca?e allows ex- perimentation and seamless switching among platforms for ease of development and deployment from prototyping ma- chines to cloud environments. Ca?e is maintained and developed by the Berkeley Vi- sion and Learning Center (BVLC) with the help of an ac- munity of contributors on GitHub. It powers on- going research projects, large-scale industrial applications, and startup prototypes in vision, speech, and multimedia. Categories and Subject Descriptors [Pattern Recognition]: [p