ICCV 2019 (oral) RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution. PyTorch implementation
By Wenlong Zhang, Yihao Liu, Chao Dong, Yu Qiao
pip install numpy opencv-python lmdb
pip install tensorboardX
, for visualizing curves.git clone https://github.com/WenlongZhang0724/RankSRGAN.git
cd RankSRGAN
./LR
folder../experiments/pretrained_models/
. We provide three Ranker models and three RankSRGAN models (see model list).test.py
.python test.py -opt options/test/test_RankSRGAN.yml
./results
folder.python train_rank.py -opt options/train/train_Ranker.yml
We use a PSNR-oriented pretrained SR model to initialize the parameters for better quality.
mmsr_SRResNet_pretrain.pth
as the pretrained model that can be downloaded from Google Drive.options/train/train_RankSRGAN.json
python train.py -opt options/train/train_RankSRGAN.yml
or
python train_niqe.py -opt options/train/train_RankSRGAN.yml
Using the train.py can output the convergence curves with PSNR; Using the train_niqe.py can output the convergence curves with NIQE and PSNR.