DownloadThe goal of this project is to upscale and improve the quality of low-resolution images. This project contains Keras implementations of different Residual Dense Networks for Single Image Super-Resolution (ISR) as well as scripts to train these networks using content and adversarial loss components. Docker scripts and Google Colab notebooks are available to carry training and prediction. Also, we provide scripts to facilitate training on the cloud with AWS and Nvidia-docker with only a few commands. When training your own model, start with only PSNR loss (50+ epochs, depending on the dataset) and only then introduce GANS and feature loss. This can be controlled by the loss weights argument. The weights used to produce these images are available directly when creating the model object. ISR is compatible with Python 3.6 and is distributed under the Apache 2.0 license.
Features
- The super-scaling Residual Dense Network described in Residual Dense Network for Image Super-Resolution
- The super-scaling Residual in Residual Dense Network described in ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- A multi-output version of the Keras VGG19 network for deep features extraction used in the perceptual loss
- A custom discriminator network based on the one described in Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
- Currently 4 models are available, RDN: psnr-large, psnr-small, noise-cancel - RRDN: gans
- Predict on large images and avoid memory allocation errors
Project Samples
