Skip to content

You can use Google Colab to apply ESRGAN on your own images. Also high model compatibility because "old-arch" and "new-arch" models should work.

License

Notifications You must be signed in to change notification settings

edstoica/Colab-ESRGAN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Simply download Colab-ESRGAN.ipynb and open it inside your Google Drive or click here and copy the file with "File > Save a copy to Drive..." into your Google Drive.

My Colab: Open In Colab

Alternative Colab with efonte/ESRGAN: Open In Colab

Credits

Enhanced Super-Resolution Generative Adversarial Networks by Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, Chen Change Loy

Original Colab file created by shahidul56 can be found here and here. This notebook is a modification by styler00dollar.

Also thanks to ata4 for creating esrgan-launcher and Joey for further improving that repo.

Important information

  • If you can't open Colab-ESRGAN.ipynb inside your Google Drive, try this colab link and save it to your Google Drive. The "open in Colab"-button can be missing in Google Drive, if that person never used Colab.
  • ESRGAN tutorials and custom models can be found in this wiki page.
  • Google Colab does assign a random GPU. It depends on luck.
  • The Google Colab VM does have a maximum session length of 12 hours. Additionally there is a 30 minute timeout if you leave colab. The VM will be deleted after these timeouts.

BibTeX

@InProceedings{wang2018esrgan,
    author = {Wang, Xintao and Yu, Ke and Wu, Shixiang and Gu, Jinjin and Liu, Yihao and Dong, Chao and Qiao, Yu and Loy, Chen Change},
    title = {ESRGAN: Enhanced super-resolution generative adversarial networks},
    booktitle = {The European Conference on Computer Vision Workshops (ECCVW)},
    month = {September},
    year = {2018}
}

Qualitative Results

PSNR (evaluated on the Y channel) and the perceptual index used in the PIRM-SR challenge are also provided for reference.

About

You can use Google Colab to apply ESRGAN on your own images. Also high model compatibility because "old-arch" and "new-arch" models should work.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Jupyter Notebook 55.4%
  • Python 44.6%