Read full article on towardsdatascience
GANs are an exciting and rapidly changing field, delivering on the promise of generative models in their ability to generate realistic examples across a range of problem domains. It is not an easy task to understand GAN or any machine learning and deep learning field overnight. It needs patience and a lot of practice, plus understanding.
In previous days it was not possible for aspiring ML enthusiasts like us to perform repetitive practice to see how it went. But now, a platform likes Spell provides a system to run and manage our projects so that we can run and test our models.
What we have created is just a simple representation of how a GAN can be created and what GAN can do. There are still more advanced tweaks yet to perform.
To take it further you can tweak the parameters and see how it generates the images differently.
There are still a lot of things one can research.
[1] Generative Adversarial Network , Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2014
[2] A Gentle Introduction to Generative Adversarial Networks (GANs), Jason Brownlee, 2019 [Online]
https://machinelearningmastery.com/what-are-generative-adversarial-networks-gans/
[3] A Beginner's Guide to Generative Adversarial Networks (GANs), Chris, 2019 [Online]