PyTorch implementation of RPC-LLE
- Python 3.7
- PyTorch 1.4.0
- opencv
- torchvision
- numpy
- pillow
- scikit-learn
- tqdm
- matplotlib
- visdom
SCL-LLE does not need special configurations. Just basic environment.
The following shows the basic folder structure.
├── datasets
│ ├── data
│ │ ├── cityscapes
| ├── test_data
│ ├── cityscapes.py
| └── util.py
├── network
├── lowlight_test.py # low-light image enhancement testing code
├── train.py # training code
├── lowlight_model.py
├── Myloss.py
├── checkpoints
│ ├── LLE_model.pth # A pre-trained SCL-LLE model
- cd RPC-LLE
python lowlight_test.py
The script will process the images in the sub-folders of "test_data" folder and make a new folder "result" in the "datasets". You can find the enhanced images in the "result" folder.
- cd RPC-LLE
- download the Cityscapes dataset
- download the cityscapes training data google drive and contrast training data google drive
- unzip and put the downloaded "train" folder to "datasets/data/cityscapes/leftImg8bit" folder
python train.py