This is the official pytorch implementation of Self-Supervised Deep Learning for Fisheye Image Rectification. The code is written by Byron Hsu and Brian Chao from Department of Electrical Engineering, National Taiwan University. This work is currently in the submission to 2020 ICASSP.
We welcome any advice for this work. Feel free to send issue or PR!
- Clone the project
git clone ...
- Install the prerequisites
pip3 install -r requirements.txt
- Start training!
bash train_gcgan.sh [dataset_path] [name]
- Monitor the training process by tensorboard
tensorboard --logdir runs
bash test_gcgan.sh [dataset_path] [name] [which_epoch]