1. Create the environment from the environment.yml file:

    conda env create -f environment.yml
   

2. Activate the new environment:

    conda activate uie
   

3. Verify that the new environment was installed correctly:

    conda env list
   

You can also use conda info --envs.

Use this line to train the model

    python train.py --cuda_id 0 --exp CCMSRNet.yml

Use this line to predict results

    python test.py --cuda_id 0 --exp CCMSRNet.yml --ckpt ./weights/checkpoint.pth --input path_to_img_folder --output path_to_save_folder

Please note that there was a minor bug in the script used to compute the UCIQE metric. To calculate the UCIQE value, please use "calculate_metrics.m" instead. The corrected results are shown below.

If our work is useful for your research, please cite our work

    @ARTICLE{10336777,
     author={Qi, Hao and Zhou, Huiyu and Dong, Junyu and Dong, Xinghui},
     journal={IEEE Transactions on Geoscience and Remote Sensing}, 
     title={Deep Color-Corrected Multi-scale Retinex Network for Underwater Image Enhancement}, 
     year={2023},
     doi={10.1109/TGRS.2023.3338611}}