Super Resolution Examples

We run this script under TensorFlow 1.1 and the self-contained TensorLayer. If you got error, you may need to update TensorLayer.

SRGAN Architecture

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

Results

Prepare Data and Pre-trained VGG

• In this experiment, we used images from DIV2K - bicubic downscaling x4 competition, you can also use your own data by setting your image folder in config.py

• Download VGG model as tutorial_vgg16.py show.

Run

• 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

Reference

• [1] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
• [2] Is the deconvolution layer the same as a convolutional layer ?