Super Resolution Examples
We run this script under TensorFlow 1.4 and the TensorLayer 1.8.0+.
SRGAN Architecture
TensorFlow Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
Results
Prepare Data and Pre-trained VGG
You need to download the pretrained VGG19 model in here as tutorial_vgg19.py show.
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/"
python main.py
python main.py --mode=evaluate
Reference
[1] [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://arxiv.org/abs/1609.04802)
[2] [Is the deconvolution layer the same as a convolutional layer ?](https://arxiv.org/abs/1609.07009)
Author
License