Caffe + CRFasRNN

---

CRFasRNN + BVLC-Caffe + GPU= ❤️

Implementation

• Basic implementation Caffe-CRFasRNN-CPU based on original TorrVision-CRFasRNN code

• GPU implementation Caffe-CRFasRNN-GPU based on Hyenal-CRFasRNN code (CUDA implementation of Permutoheral Lattice)

Installation

cd $PATH_THIS_REPO/
mkdir build
cd build
cmake ..
make -j4
make pycaffe
make install

to setup your envirinemet with builded CRFasRNN-Caffe version you can use bash-script

Dataset

Please, read quick-dataset-instructions

CRFasRNN training pipeline

(1) Prepare train/validation/deploy models-protobuf:

cd $PATH_THIS_REPO/examples_crfasrnn/ex01_train_segm_net
./start01_generate_models.sh

(2) Pretrain FCN-model, and then finetune CRFasRNN model:

cd $PATH_THIS_REPO/examples_crfasrnn/ex01_train_segm_net
./start02_train_model_unet.sh
./start03_train_model_crfasrnn.sh

(3) Model inference (code sample) run03_inference_model_fcn_v1.py

Test CRFasRNN Model Train/Validation/Deploy:

---

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.

Custom distributions

• 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

Community

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 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}
}