zhengyanxu / rpc-lle

RPC-LLE

Experiment

PyTorch implementation of RPC-LLE

Requirements

• 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.

Folder structure

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

Test

• 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.

Train

1. cd RPC-LLE
2. download the Cityscapes dataset
3. download the cityscapes training data google drive and contrast training data google drive
4. unzip and put the downloaded "train" folder to "datasets/data/cityscapes/leftImg8bit" folder

python train.py