This branch of Caffe extends BVLC-led Caffe by adding other functionalities such as managed-code wrapper, Faster-RCNN, R-FCN, etc. And it has been modified to be complied by c++4.4 and glibc 2.12.
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.
Copy Makefile.config.example to Makefile.config
Download CUDA Toolkit 7.5 from nVidia website.
The code doesn't support the CPU_ONLY.
For cuDNN acceleration using NVIDIA’s proprietary cuDNN software, uncomment the USE_CUDNN := 1 switch in Makefile.config. cuDNN is sometimes but not always faster than Caffe’s GPU acceleration.
Download cuDNN v3 or cuDNN v4 from nVidia website. And unpack downloaded zip to $CUDA_PATH (It typically would be /usr/local/cuda/include and /usr/local/cuda/lib64)
Simply type
make -j8 && make pycaffe
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}
}