This project consisted in studying GANs in the case of Wasserstein distance, as part of the fifth-year course at INSA Toulouse in Applied Mathematics of High Dimensional and Deep Learning.

GAN python scholarship

Go to file

Paul Corbalan 30679c8173 Use presentation from notebook.ipynb for README.md		2024-01-30 18:07:56 +01:00
.devcontainer	feat(devcontainer): Remove ipykernel for Jupyter Notebook	2024-01-23 15:01:47 +01:00
data	Upload predicted_humans data	2024-01-30 13:22:50 +01:00
imgs	add readme	2017-01-30 20:11:11 +05:30
models	Remove dots from module names to execute the code with pytorch 1.0.0.	2018-12-25 22:59:23 +01:00
samples	Upload samples/out.log	2024-01-30 13:31:36 +01:00
.gitattributes	Upload samples/out.log	2024-01-30 13:31:36 +01:00
.gitignore	Upload samples/out.log	2024-01-30 13:31:36 +01:00
LICENSE	Add files from initial project repository	2023-12-16 12:40:12 +01:00
README.md	Use presentation from notebook.ipynb for README.md	2024-01-30 18:07:56 +01:00
generate.py	Save each image in its own file.	2018-12-26 16:03:28 +01:00
main.py	Move options to main	2024-01-09 23:06:55 +01:00
notebook.ipynb	Upload notebook.ipynb	2024-01-30 18:06:35 +01:00
requirements.txt	Update requirements.txt	2024-01-30 11:57:10 +01:00

README.md

Wasserstein GAN

L'objectif de ce projet était d'étudier les GANs dans le cas de la distance de Wasserstein.

Voici les membres de notre groupe classés par ordres alphabétiques pour leur nom de famille :

Paul Corbalan
Nicolas Gonel
Oihan Joyot
Tristan Portugues
Florian Zorzynski

Notre projet s'inspire grandement des ressources suivantes qui sont l'article initial de notre projet ainsi que le code correspondant.

Article : [1701.07875] Wasserstein GAN (arxiv.org)
Code : martinarjovsky/WassersteinGAN (github.com)