Generative Adversarial Networks For Image Generation
- 1 min This project was done for fun and is purely to explore the possibilities of the new deep learning architecture presented called Generative Adversarial Networks introduced by Ian J. Goodfellow and co-authors in 2014.
GANs are mainly used in image processing but can also be applied in the context of other data types such as text, sound or video. Besides numerous fun projects, they have become particularly useful in the field of data augmentation.
My work is based on artistic paintings and allows to generate "new" images (data instances) that resemble the provided training data.
