This repository is part of the IIT Madras AI Club Deputy Coordinator Mini Project that aims at reimplementing the Pix2Pix paper. The project follows a structured week-wise approach, covering both theoretical concepts and practical implementations of Generative Adversarial Networks (GANs) and Conditional GANs (cGANs).
- Develop a step-by-step understanding of the Pix2Pix model.
- Explore the theoretical foundations of GANs and cGANs.
- Gain hands-on experience with machine learning libraries such as TensorFlow and PyTorch.
The Pix2Pix model, introduced in "Image-to-Image Translation with Conditional Adversarial Networks" by Isola et al., is a supervised deep learning method designed for various image-to-image translation tasks. It employs a U-Net-based generator and a PatchGAN discriminator, trained with adversarial and L1 losses.
To follow along with the course structure, navigate through the respective week folders and explore both the theoretical notes and code implementations.
Deputy Coordinators
- Kirthan S
- Mohammed Ikram C C
- Mothish M
- Sanika Pradeep Nair
- Sharan Keshav
- Smitali Bhandari
- Vedant Misra
Coordinators
- Arjun Krishnaswamy
- Anshuman Mishra