Skip to content

KaneezFatima09/generative-adversarial-network-GAN-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

GAN on MNIST

This repository contains an implementation of a Generative Adversarial Network (GAN) trained on the MNIST dataset.
The purpose of this project is to show the basics of adversarial training and how a generator can learn to create realistic handwritten digits from noise.


Project Overview

  • Generator (G): Takes random noise (z) as input and outputs fake images resembling MNIST digits.
  • Discriminator (D): Takes an image (real or fake) and outputs a probability indicating whether it is real or generated.
  • Training Process:
    • The generator tries to fool the discriminator by producing realistic images.
    • The discriminator tries to correctly classify real vs. fake.
    • Both networks improve in a minimax game until the generator produces convincing samples.

Technologies Used

  • Python 3
  • PyTorch
  • Torchvision
  • Matplotlib (for visualization)

About

Implementation of a Generative Adversarial Network (GAN) trained on the MNIST handwritten digit dataset. This project demonstrates the fundamental concepts of GANs.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors