/srgan

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Primary LanguagePython

Super Resolution Examples

We run this script under TensorFlow 1.2 and the self-contained TensorLayer. If you got error, you may need to update TensorLayer.

⚠️ This repo will be merged into tensorlayer soon.

SRGAN Architecture

TensorFlow Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"

Results

Prepare Data and Pre-trained VGG

    1. You need to download the pretrained VGG19 model in here as tutorial_vgg19.py show.
    1. You need to have the high resolution images for training.
    • In this experiment, I used images from DIV2K - bicubic downscaling x4 competition, so the hyper-paremeters in config.py (like number of epochs) are seleted basic on that dataset, if you change a larger dataset you can reduce the number of epochs.
    • If you dont want to use DIV2K dataset, you can also use Yahoo MirFlickr25k, just simply download it using train_hr_imgs = tl.files.load_flickr25k_dataset(tag=None) in main.py.
    • If you want to use your own images, you can set the path to your image folder via config.TRAIN.hr_img_path in config.py.

Run

config.TRAIN.img_path = "your_image_folder/"
  • Start training.
python main.py
  • Start evaluation.
python main.py --mode=evaluate 

Reference

Author

License

  • For academic and non-commercial use only.
  • For commercial use, please contact dhsig552@163.com.