My implementation of the model from the paper "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
I trained the model on the DIV2K-dataset
Instal dependencies:
pip install -r requirements.txt
To train using your custom dataset:
Clone the repository:
git clone https://github.com/pbcong/SRGAN-from-scratch
Train using train-notebook or run train.py
Pretrained models:
Results:\