Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/sanikamal/gan-diffusion-atoz

Generative Adversarial Networks in Pytorch and Tensorflow
https://github.com/sanikamal/gan-diffusion-atoz

deep-learning gan generative-model pytorch rbm tensorflow unsupervised-machine-learning vae

Last synced: 15 days ago
JSON representation

Generative Adversarial Networks in Pytorch and Tensorflow

Awesome Lists containing this project

README 

        
# GAN & Diffusion AtoZ 🎨🤖



Welcome to GAN & Diffusion AtoZ, a collection of Jupyter notebooks and Python scripts that provide a comprehensive introduction to Generative Adversarial Networks (GANs) and Diffusion Models.



## Table of Contents



- Overview

- Getting Started

- Projects

    - GAN

        - Project 1: Basic GAN

        - Project 2: Conditional GAN

        - Project 3: Wasserstein GAN

        - Project 4: StyleGAN

    - Diffusion

        - Introduction to 🤗 Diffusers

- Contributing

- License

- Acknowledgments



## 📚 Overview



This repository contains mini-projects covering various aspects of GANs and Diffusion Models, from basic concepts to advanced techniques. Each project is presented as a Jupyter notebook and includes detailed explanations, code examples, and visualizations to help you understand how GANs and Diffusion Models work and how to use them.



## 🚀 Getting started



To get started, you'll need to install the dependencies listed in `requirements.txt`. You can do this by running:



```pip install -r requirements.txt```



Once you've installed the dependencies, you can run the Jupyter notebooks in the notebooks directory. Each notebook includes step-by-step instructions and code examples to run and experiment with.



## 📝 Projects



### GAN



**Project 1: Basic GAN**



In this project, you'll learn the basics of GANs and build a simple GAN that generates images of handwritten digits. You'll also learn how to evaluate the performance of your GAN and how to generate new images.



**Project 2: Conditional GAN**



In this project, you'll learn how to build a conditional GAN that generates images of animals based on their species. You'll also learn how to use a pretrained classifier to guide the generation process and improve the quality of the generated images.



**Project 3: Wasserstein GAN**



In this project, you'll learn about Wasserstein GANs, a variant of GANs that use a different loss function to train the generator and discriminator. You'll build a Wasserstein GAN that generates images of faces and compare its performance to a traditional GAN.



**Project 4: StyleGAN**



In this project, you'll learn about StyleGAN, a state-of-the-art GAN architecture that can generate high-quality images with fine-grained control over the style and appearance. You'll build a StyleGAN that generates images of landscapes and experiment with different styles and settings.



### Diffusion



* [**Introduction to 🤗 Diffusers**](notebooks/introduction_to_diffusers.ipynb)

  

    In this notebook, a diffusion model is trained to generate images of cute butterflies 🦋. This process will cover the core components of the 🤗 Diffusers library, laying a solid foundation for more advanced applications.[]()



**Project 6: Diffusion with Conditioning**



In this project, you'll learn how to condition diffusion models on additional inputs to guide the generation process. You'll build a conditioned diffusion model to generate images based on specific conditions or constraints.



**Project 7: Advanced Diffusion Techniques**



In this project, you'll explore advanced techniques in diffusion models, including enhancements and modifications to improve the quality and efficiency of the generated images. You'll implement and experiment with state-of-the-art diffusion methods.



## 📝 Contributing



If you find a bug or have a suggestion for a new project, please open an issue or submit a pull request. We welcome contributions from the community and are happy to help newcomers get started.



## 📄 License



This repository is licensed under the MIT License. See the [LICENSE]() file for more information.



## 🙏 Acknowledgments



We would like to thank the authors of the papers and tutorials that inspired this collection, as well as the open-source contributors who made this work possible.