Ecosyste.ms: Awesome

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

Awesome Lists | Featured Topics | Projects

https://github.com/bniladridas/gan

This project focuses on training a GAN on the MNIST dataset to create synthetic handwritten digits.
https://github.com/bniladridas/gan

matplotlib numpy python tensorflow

Last synced: about 2 months ago
JSON representation

This project focuses on training a GAN on the MNIST dataset to create synthetic handwritten digits.

Host: GitHub
URL: https://github.com/bniladridas/gan
Owner: bniladridas
License: mit
Created: 2024-02-05T16:58:40.000Z (11 months ago)
Default Branch: main
Last Pushed: 2024-09-09T09:03:55.000Z (4 months ago)
Last Synced: 2024-10-20T05:40:51.780Z (3 months ago)
Topics: matplotlib, numpy, python, tensorflow
Language: Python
Homepage:
Size: 3.65 MB
Stars: 0
Watchers: 2
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

# 🎨 GAN Image Generation

Unleash the power of Generative Adversarial Networks (GANs) to produce stunningly realistic images. This project showcases the training of a GAN on the MNIST dataset to generate synthetic handwritten digits with incredible fidelity.

## 🚀 Table of Contents
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [Usage](#usage)
- [Project Structure](#project-structure)
- [License](#license)
- [Acknowledgments](#acknowledgments)

## 🛠️ Prerequisites

Ensure you have the following tools and libraries installed:

- Python 3.x
- TensorFlow
- Matplotlib
- NumPy

## 📥 Installation

1. **Clone the repository:**

```bash
git clone https://github.com/niladrridas/gan.git
cd gan
```

2. **Install the required packages:**

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

## 🚀 Usage

1. **Initiate GAN training:**

```bash
python src.py
```

This command will start the training process. The GAN will generate images at predefined intervals, with results saved in the project directory.

2. **Monitor Training:**

Track the evolution of generated images over epochs to witness the progressive improvements in quality.

## 📸 Preview

Explore the quality of generated images:

![Image Preview](/img/1.png)
![Image Preview](/img/2.png)

## 📂 Project Structure

- **`src.py`**: Core script for training the GAN.
- **`requirements.txt`**: Dependency list for the project.
- **`README.md`**: Comprehensive project documentation.

## 📝 License

This project is distributed under the MIT License. For full details, see the [LICENSE](https://github.com/niladrridas/gan/blob/main/LICENSE) file.

## 🙏 Acknowledgments

This project is inspired by cutting-edge advancements in GANs and image generation technologies.