A lightweight DCGAN implementation on images of dogs in grayscale. With the model, we are able to generate realistic pictures of man's best friend. If GitHub doesn't render dcgan.ipynb please view the notebook here:
https://nbviewer.jupyter.org/github/jparcill/gansbestfriend/blob/master/dcgan.ipynb
And just in case you didn't want to sleep tonight, we have this nightmare of a picture generated by the algorithm.
Here are some links to papers, articles, and tutorials that assisted me in creating this project.
- https://arxiv.org/pdf/1701.00160.pdf
- https://arxiv.org/pdf/1511.06434.pdf
- https://medium.com/@utk.is.here/keep-calm-and-train-a-gan-pitfalls-and-tips-on-training-generative-adversarial-networks-edd529764aa9
- https://pytorch.org/tutorials/_downloads/e9c8374ecc202120dc94db26bf08a00f/dcgan_faces_tutorial.ipynb