Caffe
Yangqing Jia, Evan Shelhamer, Jeff Donahue et al. · ACM International Conference on Multimedia (ACM MM) · 2014
Caffe provides multimedia scientists and practitioners with a clean and modifiable 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 efficiently on commodity architectures. Caffe fits industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU (approx 2 ms per image). By separating model representation from actual implementation, Caffe allows experimentation and seamless switching among platforms for ease of development and deployment from prototyping machines to cloud environments.
Cited by 10,928 works. doi:10.1145/2647868.2654889
Authors
- Yangqing Jia
- Evan Shelhamer
- Jeff Donahue
- Sergey Karayev
- Jonathan Long
- Ross Girshick
- Sergio Guadarrama
- Trevor Jackson Darrell
References
- ImageNet classification with deep convolutional neural networks
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Selective Search for Object Recognition
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Torch7: A Matlab-like Environment for Machine Learning
- OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
- Pylearn2: a machine learning research library
- PANDA: Pose Aligned Networks for Deep Attribute Modeling
- Open-vocabulary Object Retrieval