Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by the Berkeley Vision and Learning Center (BVLC) and community contributors.
Check out the project site for all the details like
- DIY Deep Learning for Vision with Caffe
- Tutorial Documentation
- BVLC reference models and the community model zoo
- Installation instructions
and step-by-step examples.
Please join the caffe-users group or gitter chat to ask questions and talk about methods and models. Framework development discussions and thorough bug reports are collected on Issues.
Happy brewing!
Caffe is released under the BSD 2-Clause license. The BVLC reference models are released for unrestricted use.
Please cite Caffe in your publications if it helps your research:
@article{jia2014caffe,
Author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},
Journal = {arXiv preprint arXiv:1408.5093},
Title = {Caffe: Convolutional Architecture for Fast Feature Embedding},
Year = {2014}
}
This fork of Caffe contains an OpenCL backend and additional layers for fast image segmentation. This work is partially supported by:
- AMD
- HHMI Janelia
- UZH, INI
- ETH Zurich
For a C++ frontend and models to use for image segmentation with this fork, see:
- Frontend: https://github.com/naibaf7/caffe_neural_tool
- Models: https://github.com/naibaf7/caffe_neural_models
The backend is supposed to work with all vendors. Note however there may be problems with libOpenCL.so provided by nVidia. It is therefore recommended to install another OpenCL implementation after installing nVidia drivers. Possibilities are:
- Intel OpenCL, recommended if you have an Intel CPU along the nVidia GPU.
- AMD APP SDK (OpenCL), recommended if you have an AMD GPU or CPU.
Available on arXiv: http://arxiv.org/abs/1509.03371