This yolo2 branch is a port of yolo2 darknet to Caffe, the code is modified from these following repositories:
Network prototxt and scripts for training/inference is at examples/yolo2.
- examples/yolo2/yolo_detection.cpp could be used to test a picture.
- examples/yolo2/data/convert.sh generates lmdb for training. Images are letterboxed as in yolo2 provided weights are trained on, the script converting yolo2 weights to caffemodel is also provided.
- To do training please note the file path in script and prototxt. Tested on VOC dataset.
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}
}