GitHub Repository: probml/pyprobml
Path: blob/master/deprecated/gan/README.md
¹¹⁹² views

PyProbML GAN zoo 🐅

This is a collection of Generative Adverserial Networks (GANs) implemented in pytorch written by Ang Ming Liang (Neoanarika@). The focus is on reproducibility and creating reusable blocks that can be used in any project. The aim of this project is to provide a quick and simple working example for many of the cool GAN idea in the textbook. All the models are trained on the CelebA dataset for consistency and comparison.

Compare results of different GANs :

GAN tricks and what the different GAN try to address :

Requirements

Python >= 3.7
PyTorch >= 1.8
Pytorch Lightning == 1.4.0
CUDA enabled computing device

To download this subdirectory only

Copy the url of the subdirectory and past it to this webstie and then download this subdirectory as a zipfile

Instruction For Training The Model

Download celeba data

Important : Make sure to get your kaggle.json from these instructions then run

mkdir /root/.kaggle 
cp kaggle.json /root/.kaggle/kaggle.json
chmod 600 /root/.kaggle/kaggle.json
rm kaggle.json

to copy kaggle.json into a folder first. Then to download the data first donwload the following script

wget -q https://raw.githubusercontent.com/probml/pyprobml/master/scripts/download_celeba.py

and run the following script

python download_celeba.py

To Train Model

python run.py -config ./configs/dcgan.yaml

Results

Model	Paper	Samples
GAN (Code, Config)	Link
SNGAN (Code, Config)	Link
LOGAN (Code, Config)	Link
WGAN (Code, Config)	Link
GP-WGAN (Code, Config)	Link

Acknowledgement

The idea of this zoo and some of the scripts were based on Anand Krishnamoorthy Pytorch-VAE library, we also used the script from sayantanauddy to transform and download the celeba from kaggle.