Metadata-Version: 2.1
Name: gans-implementations
Version: 0.0.2
Summary: A bunch of GAN implementations
Home-page: https://github.com/UdbhavPrasad072300/GANs-Implementations
Author: Udbhav Prasad
Author-email: udbhavprasad072300@gmail.com
License: MIT
Platform: UNKNOWN
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: License :: OSI Approved :: MIT License
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3 :: Only
Description-Content-Type: text/markdown

# GANs-Implementations

GANs Implementations and their Training (in .ipynb)

Implemented:
<ul>
  <li>Vanilla GAN</li>
  <li>DCGAN - Deep Convolutional GAN</li>
  <li>WGAN - Wasserstein GAN</li>
  <li>SNGAN - Spectrally Normalized GAN </li>
  <li>StyleGAN</li>
</ul>

## Installation

<a href="https://pypi.org/project/gans-implementations/">PyPi Installation</a>

```bash
$ pip install gans-implementations
```

## Handwritten Digits - MNIST 

<ul>
  <li><a href="https://github.com/UdbhavPrasad072300/GANs-Implementations/blob/main/notebooks/GAN%20with%20BCE%20-%20MNIST.ipynb">GAN with BCELoss</a></li>
  <li><a href="https://github.com/UdbhavPrasad072300/GANs-Implementations/blob/main/notebooks/DCGAN%20with%20BCE%20-%20MNIST.ipynb">DCGAN with BCELoss</a></li>
  <li><a href="https://github.com/UdbhavPrasad072300/GANs-Implementations/blob/main/notebooks/SN-WGAN%20with%20GP%20-%20MNIST.ipynb">SN-WGAN with Wasserstein Loss</a></li>
</ul>

## Work Cited

https://www.coursera.org/specializations/generative-adversarial-networks-gans?


