Implementing some of the famous GANs architectures.
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
This repository contains a collection of Generative Adversarial Network (GAN) architectures implemented in Python using the PyTorch library. These implementations serve as educational resources for those interested in understanding and working with GANs.
- Conditional GAN (CGAN):
- Two variations of Conditional GANs are implemented, allowing for conditional image generation based on label information.
- Deep Convolutional GAN (DCGAN):
- A Deep Convolutional GAN is designed for generating high-quality images. It introduces convolutional layers for improved performance.
- GAN with MNIST Dataset:
- A basic GAN model is trained on the MNIST dataset to generate handwritten digits.
- Simple GAN for Number Generation:
- A straightforward GAN architecture for generating numerical data, such as sequences of numbers.
- InfoGAN (Information Maximizing GAN):
- An InfoGAN model that learns disentangled representations and allows for the control of specific attributes in generated images.
This research project was powered by a robust set of tools, libraries, and frameworks that facilitated data processing, analysis, and visualization:
-
The primary programming language for data manipulation, analysis, and visualization.
-
Used for interactive data exploration, analysis, and documentation, providing an intuitive environment for code execution and visualization.
-
An open-source deep learning framework for flexible and dynamic neural network development.
-
scikit-learn is a versatile machine learning library in Python that offers simple and efficient tools for data analysis and modeling, including classification, regression, clustering, and more.
-
NumPy is a fundamental package for scientific computing with Python, providing support for arrays and matrices, as well as a wide range of mathematical functions.
-
A versatile data manipulation library for cleaning, processing, and analyzing structured data.
-
A powerful statistical data visualization library that enhances the presentation of insights through beautiful and informative plots.
-
A widely-used data visualization library that offers extensive customization and control over plot aesthetics.
- Clone this repository to your local machine if you wish to replicate or build upon the work presented here.
git clone https://github.com/SimplyRamin/GANs.git
- Open the notebook you want to check.
Contributions are what makes the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Distributed under the MIT License. See LICENSE.txt
for more information.
Ramin F. - @SimplyRamin - ferdos.ramin@gmail.com - Website
Project Link: https://github.com/SimplyRamin/GANs
I would like to express my gratitude to the data science community for its constant inspiration and support. This project is a testament to the power of data-driven insights and the endless possibilities they offer in understanding and optimizing social media engagement.