This is a pytorch implementation of Zhou et al (2015). NOTICE: We have released a upgraded version of iCNN naming STN-iCNN, check the paper or code for more information.
The network archtecture is as following:
1.  Smith et al. Resized HelenDataset
2. Unzip it into ./datas/helen/
1. python3 ./utils/extract_parts.py
Run Jupyter Notebook: visual_test.ipynb
git clone https://github.com/aod321/icnn-face
cd icnn-face pip install -r requirements.txt
python train_stage1.py
python train_stage2.py
all the checkpoints can be found at checkpoints_{uuid} or checkpoints_{parts_name}_{uuid}
Comparison with State-of-the-art Methods on HELEN
Others
