TD 2 : GAN & cGAN

MSO 3.4 Apprentissage Automatique

We recommand to use the notebook (.ipynb) but the Python script (.py) is also provided if more convenient for you.

How to submit your Work ?

This work must be done individually. The expected output is a private repository named gan-cgan on https://gitlab.ec-lyon.fr. It must contain your notebook (or python files) and a README.md file that explains briefly the successive steps of the project. Don't forget to add your teacher as developer member of the project. The last commit is due before 11:59 pm on Monday, April 1st, 2024. Subsequent commits will not be considered.

Part1: DC-GAN

In this first part we re-train a DCGAN on the MNIST dataset. The code is available here : GAN notebook.

Here are the results of training:

Part2: Conditional GAN

In this part we train a conditional GAN on a dataset made up of facades over 200 epochs. We compare the results after 100 and 200 epochs.

First, we implement a U-net structure which will act as a generator. Then we implement a Patch GAN as a discriminator.

The code is also available here : GAN notebook.