A fork of Caffe (with DeepLab additions), maintained for the Tamp project.
Tamp reduces the space and compute of deep neural networks by replacing dense weight matrices with structured transforms — circulant, Toeplitz, skew-circulant, low-rank, and ACDC. Vanilla Caffe has no interface for such custom layers, so this fork adds the Caffe-side plugin hooks that Tamp builds against; enable them with
USE_TAMPinMakefile.config. See the Tamp repository for how the pieces fit together and how to build.Branches: the Tamp build pins
color; other branches hold per-transform experiments (circulant,skewcirculant,reskewcirculant,fftw,GPUOptimize, …), whilemastertracks upstream BVLC Caffe (release tagsrc–rc5,v0.1–v0.9999).
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/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
- BAIR reference models and the community model zoo
- Installation instructions
and step-by-step examples.
- Intel Caffe (Optimized for CPU and support for multi-node), in particular Xeon processors (HSW, BDW, SKX, Xeon Phi).
- OpenCL Caffe e.g. for AMD or Intel devices.
- Windows Caffe
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 BAIR/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}
}