This repository is a Keras implementation of Deblur GAN. You can find a tutorial on how it works on Medium. Below is a sample result (from left to right: sharp image, blurred image, deblurred image)
virtualenv venv -p python3
. venv/bin/activate
pip install -r requirements/requirements.txt
pip install -e .
Get the GOPRO dataset, and extract it in the deblur-gan
directory. The directory name should be GOPRO_Large
.
Use:
python scripts/organize_gopro_dataset.py --dir_in=GOPRO_Large --dir_out=images
python scripts/train.py --n_images=512 --batch_size=16 --log_dir /path/to/log/dir
Use python scripts/train.py --help
for all options
python scripts/test.py
Use python scripts/test.py --help
for all options
python scripts/deblur_image.py --weight_path=/path/to/generator.h5 --input_dir=/path/to/image/dir --output_dir=/path/to/deblurred/dir