- Python 3 (Recommend to use Anaconda)
- PyTorch >= 1.0.0
- NVIDIA GPU + CUDA
- Python packages:
pip install numpy opencv-python lmdb tensorboardX
- Place your low-resolution images in
test_image/LR
folder. - Download pretrained models from Google Drive and place them in
test_image/pretrained_models
. - Run the command:
python test_image/test.py test_image/pretrained_models/nESRGANplus.pth
(or any other models). - The results are in
test_image/results
folder.
- Prepare the datasets which can be downloaded from Google Drive.
- Prepare the PSNR-oriented pretrained model (all pretrained models can be downloaded from Google Drive).
- Modify the configuration file
codes/options/train/train_ESRGANplus.json
. - Run the command
python train.py -opt codes/options/train/train_ESRGANplus.json
.
- This code is based on BasicSR.
@INPROCEEDINGS{9054071,
author = {N. C. {Rakotonirina} and A. {Rasoanaivo}},
booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
title={ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network},
year={2020},
volume={},
number={},
pages={3637-3641},}