毕业论文外文翻译-Caffe：快速特嵌入的卷积结构.doc

英文资料翻译 Caffe: Convolutional Architecture for Fast Feature Embedding ABSTRACT Caffe 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 neural networks and other deep models e ciently on commodity architectures. Ca e ts industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU ( 2.5 ms per image). By separating model representation from actual implementation, Ca e allows experimentation 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 Vision and Learning Center (BVLC) with the help of an active community 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 I.5.1 [Pattern Recognition]: [Applications{Computer vi- sion]; D.2.2 [Software Engineering]: [Design Tools and Techniques{Software libraries]; I.5.1 [Pattern Recognition]: [Models{Neural Nets] General Terms Algorithms, Design, Experimentation Keywords Open Source, Computer Vision, Neural Networks, Parallel Computation, Machine Learning Corresponding Authors. The work was done while Yangqing Jia was a graduate student at Berkeley. He is currently a research scientist at Google, 1600 Amphitheater Pkwy, Mountain View, CA 94043. 1. INTRODUCTION A key problem in multimedia data analysis is discovery of e ective representations for sensory inputs|images, sound-waves, haptics, etc. While performance of conventional, handcrafted features has plateaued in recent years, new developments in deep compositional architectures have kept perfor