Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" [Paper]

This is a prototype implementation developed by Harry Yang.

####Training prepare your images under a sub-folder of a root folder

train_folder=your_root_folder model_folder=your_save_folder th run_sr.lua 

By default it resizes the images to 96x96 as ground truth and 24x24 as input, but you can specify the size using loadSize and scale.

####Loading a saved model to train

D_path=your_saved_D_model G_path=your_saved_G_model th run_resume.lua

####Testing prepare your test images under a sub-folder of a root folder

test_folder=your_root_folder model_file=your_G_model result_path=your_result_path th run_test.lua

Contact

##Todo:

1. Add TV loss.
2. Provide trained models.