run 'train.py'
We provide two pre-trained models.
Mainly for different number of channels.
The dataset is consistent with that described in the paper and is a collection of the LOL dataset and the FiveK dataset.
You can also train with your own dataset.
Modify your pre-trained model path in 'data_test.py
If you find this work useful for you, please cite
@article{chen2024frr,
title={FRR-NET: a fast reparameterized residual network for low-light image enhancement},
author={Chen, Yuhan and Zhu, Ge and Wang, Xianquan and Yang, Huan},
journal={Signal, Image and Video Processing},
pages={1--10},
year={2024},
publisher={Springer}
}
If you have any questions, please contact Yuhan Chen at cyh1217552389@gmail.com