https://github.com/aditya-ranjan1234/celeb-face-gan

A GAN trained on the CelebA dataset for generating realistic human face images.
https://github.com/aditya-ranjan1234/celeb-face-gan

celeba-dataset computer-vision gan pytorch

Last synced: about 1 month ago
JSON representation

A GAN trained on the CelebA dataset for generating realistic human face images.

• Host: GitHub
• URL: https://github.com/aditya-ranjan1234/celeb-face-gan
• Owner: Aditya-Ranjan1234
• License: gpl-3.0
• Created: 2025-03-08T13:45:28.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2025-03-08T15:55:45.000Z (9 months ago)
• Last Synced: 2025-06-03T06:00:56.389Z (6 months ago)
• Topics: celeba-dataset, computer-vision, gan, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 1.01 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# GAN on CelebA Dataset

## Overview

This repository contains a Generative Adversarial Network (GAN) trained on the CelebA dataset to generate realistic human face images. The project leverages deep learning techniques to synthesize high-quality face images from random noise.

## Features

- Uses the CelebA dataset, which contains over 200,000 images of celebrity faces.

- Implements a Deep Convolutional GAN architecture.

- Generates high-quality and diverse human face images.

- Provides training scripts and pre-trained model checkpoints.

## Installation

```bash

# Clone the repository

git clone https://github.com/Aditya-Ranjan1234/Celeb-Face-GAN.git

cd Celeb-Face-GAN

```

## Dataset

The CelebA dataset can be downloaded from the official website: https://www.kaggle.com/datasets/jessicali9530/celeba-dataset

![Dataset](images/dataset.png)

## Results

Below is an example of the generated images afrer 106 epochs: