This is a slightly modified version of Caffe as used by the Deep Learning API & server Deepdetect. The repository is kept up to date with the original Caffe master branch.
Improvements and new features include:
- Switch from
LOG(FATAL)error toCaffeErrorExceptionthrown on every recoverable errors. This allows the safe use of Caffe as a C++ library from external applications, and in production - Various fixes, including ability to run the exact same job in parallel
- Makefile fixes with default build supporting all NVIDIA architectures
- Sparse inputs and CPU/GPU computations
While this is intended to be used with DeepDetect, this is a great alternative to the original Caffe if you'd like to avoid uncaptured errors.
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}
}