My own Caffe development branch with some tools:
- Multi Mean Field Iteration (transfer from CRF-RNN caffe)
- Segmetation Accuracy Layer (micro averaged F1 score or Mean IoU/Jaccard score, with plugin files acommedating to various datasets)
- hard awared statistical contextual loss for parsing (under construction)
- Blob Align (python layer, resize a feature map to the same size of another feature map)
- imgResize (python layer)
- salientArea (Pyhton layer, convert parsing labels to 0/1 binary map - bg or object)
- image seg data layer (transfer from Deeplab v1 caffe)
- dense crf layer (transfer from Deeplab v1 caffe)
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, 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}
}