Home

Awesome

ShuffleMixer

LICENSE Python PyTorch

Paper | Supplementary Material | Discussion

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

By Long Sun, Jinshan Pan, and Jinhui Tang

Network Architecture

<img src = "./assets/framework.png">

Dependencies

Installation

# Clone the repo
git clone https://github.com/sunny2109/ShuffleMixer.git
# Install dependent packages
cd ShuffleMixer
pip install -r requirements.txt
# Install BasicSR
python setup.py develop

You can also refer to this INSTALL.md for installation

Training

python basicsr/train.py -opt options/train/ShuffleMixer/train_base_DF2K_x4.yml

Testing

python basicsr/test.py -opt options/test/ShuffleMixer/test_base_benchmark_x4.yml

Results

Citation

If you find this repository helpful, you may cite:

@InProceedings{Sun_2022,
    author    = {Sun, Long and Pan, Jinshan and Tang, Jinhui},
    title     = {{ShuffleMixer}: An Efficient ConvNet for Image Super-Resolution},
    booktitle = {Advances in Neural Information Processing Systems},
    year      = {2022}
}

Acknowledgment: This code is based on the BasicSR toolbox