Framework of GAN Inversion

Introcuction

  • You can implement your own inversion idea using our repo. We offer a full range of tuning settings (in hparams.py), some excellent backbones and classics loss functions. You can modify the arch of network or loss easily.

Recent Updates

  • 2021.9.1 The simplfied framework of GAN Inversion is released.

Requirements

  • pip install git+git://github.com/lehduong/torch-warmup-lr.git
  • PyTorch1.7

Done

Tuning Setting

  • Apply_init
  • Optimizer_mode
  • Scheduler_mode
  • Open_warn_up

Backbone

Loss

TODO

  • DDP
  • More Backbones
  • Metrics

Acknowledgements

This repository is an unoffical PyTorch Framework of GAN Inversion and highly based on restyle-encoder, pixel2style2pixel, stylegan2-pytorch, AliProducts and stylegan2.Thank you for the above repo. Thank you to Daiheng Gao and Jie Zhang for all the help I received.

GitHub

https://github.com/MontaEllis/Framework-of-GAN-Inversion