FengyangZhang / caffe_roomnet

Segnet-like CNN for room layout estimation
Other
27 stars 7 forks source link

Caffe_Roomnet

A CNN-based neural network for layout estimation from a monocular vision image. Although there's still things to be done about it, you can train the model by the following command now:

./build/tools/caffe train -solver models/roomnet/roomnet_solver.prototxt

You may have to play with the parameters a little bit, but in my case the current one is doing well.

Roomnet paper

Find the original paper here: Chen-Yu Lee et. al., RoomNet: End-to-End Room Layout Estimation, arXiv:1703.06241

Caffe

Build Status License

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

and step-by-step examples.

Join the chat at https://gitter.im/BVLC/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!

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}
}