We run this script under TensorFlow 1.2 and the self-contained TensorLayer. If you got error, you may need to update TensorLayer.
TensorFlow Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
-
In this experiment, we used images from DIV2K - bicubic downscaling x4 competition, besides Yahoo MirFlickr25k is also a good choice. Alternatively, you can use your own data by setting your image folder in
config.py
. -
Download VGG model as tutorial_vgg16.py show.
- Set your image folder in
config.py
.
config.TRAIN.img_path = "your_image_folder/"
- Start training.
python main.py
- Start evaluation.
python main.py --mode=evaluate