- Run the setup instructions in tensorflow_gan/examples/README.md
- Run:
python esrgan/train.py
The Notebook files for training ESRGAN on Google Colaboratory can be found here
The ESRGAN model proposed in the paper ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks (Wang Xintao et al.) performs the task of image super-resolution which is the process of reconstructing high resolution (HR) image from a given low resolution (LR) image. Here we have trained the ESRGAN model on the DIV2K dataset and the model is evaluated using TF-GAN.
