Metadata-Version: 2.1
Name: ganify
Version: 1.0.10
Summary: An Easy way to use GANs for data augmentation
Home-page: https://github.com/arnonbruno/ganify
Author: Arnon Bruno
Author-email: asantos.quantum@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: tensorflow (>=2.0.0)
Requires-Dist: pandas (>=0.25)
Requires-Dist: numpy (>=1.16)
Requires-Dist: scikit-learn (>=0.21)
Requires-Dist: matplotlib (>=3.1)
Requires-Dist: tqdm (>=4.15)

# GANify
<p align="center">
<img width="200" height="200" src="https://github.com/arnonbruno/ganify/blob/master/logo.png">
</p>

<b> Description: </b> GANify is an algorithm based on Generative Adversarial Learning to generate synthetic non-tensor data. The name GANify is an adaptation of acronym <b>GAN</b> (generative adversarial network) and Ampl<b>IFY</b>, meaning you can amplify the amount of data available with GANs .


<b> Installation: </b>
One can easily install GANify using the PIP:

<i>pip install ganify</i>


<b>How to use:</b>
Once installed, simply import the library and instatiate the model as described below:
<p align="center">
<img width="600" height="500" src="https://github.com/arnonbruno/ganify/blob/master/ganify.gif">
</p>

<b> Other info: </b>
The package also enables the creation of synthetic data using both <b> GANs </b> and <b> WGANs </b>, by simply changing the argument <i>"type"</i> on <i>"fit_data"</i>
Additionally, you can view the model overall loss performance by calling the <i>"plot_performance()"</i> method after fit.


