Arnab Kumar Mondal, Piyush Tiwary, Parag Singla & Prathosh AP
ICLR 2023
This folder provides a re-implementation of this paper in PyTorch, developed as part of the course METU CENG 796 - Deep Generative Models. The re-implementation is provided by:
Erce Güder, guder.erce@metu.edu.tr
Adnan Harun Doğan, adnan.dogan@metu.edu.tr
Please see the jupyter notebook file main.ipynb for a summary of paper, the implementation notes and our experimental results.
The conda environment can be created using the code snippet below:
conda env create -f environment.yml
conda activate 796
The following datasets:
as well as the weights of StyleGAN2 trained on FFHQ (drive) can be downloaded via:
bash download_data.sh