This is the caffe in which our implementation for MLIC-KD-WSD is merged.

Installation

Please refer to Caffe document for instructions.

Implementation details

    ./caffe
        include
            ...
        src
            caffe
                layers
                    cross_entropy_loss_layer.cpp        // cross entropy loss for WSDDN
                    human_att_data_layer.cpp            // data layer
                    interp_layer.cpp                    // bilinear interpolation
                    roi_pooling_layer.cpp/cu            // add score
                    wsd_roigen_layer.cpp                // prepare rois for roi pooling
                    wsd_roigen_single_scale_layer.cpp   // convert rois' coordinates according to the given scale
                proto
                    caffe.proto (line 407-471)          // add some LayerParameters 
                utils
                    interp.cpp/cu                       // bilinear interpolation
                data_transformer.cpp (line 41-160)      // data augmentation  

The code has been tested successfully on Ubuntu 14.04 with CUDA 8.0, cuDNN 5.1 and OpenCV 3.1.0.

---

Caffe

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!

License and Citation

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}
}