1. Clone this code by git clone https://github.com/zeakey/hed --recursive, assume your source code directory is$HED;

2. Download training data from the original repo, and extract it to $HED/data/;

3. Build caffe with bash $HED/build.sh, this will copy reimplemented loss layer to caffe folder first;

4. Download initial model and put it into $HED/model/;

5. Start to train with cd $HED && python train.py --gpu GPU-ID 2>&1 | tee hed.log(will generate training/testing network prototxt automatically by calling $HED/model/hed.py).

1. Download pretrained model from original repo and put it into $HED/snapshot/;

2. Generate testing network prototxt by python $HED/model/hed.py(will generate training network prototxt as well);

3. Run cd $HED && python forward_all();

Checkout the demo!

By KAI ZHAO