From a design perspective, my early and original results - made by an algorithm called DCGAN (one of the most basic versions of a GAN network) - looked the best. But at a resolution of under 200x200px, they were also extremely pixeled and low-res. Let's enhance.
Looking at the past year, the biggest innovation in the GAN space might have been the BigGAN architecture. The mega-architecture, trained on 512 TPUs in the space of two days, also includes a sweatshirt category. I had to look into it
On the lookout for a new architecture, people told me to use SAGAN. The results are - interesting. I wasn't satisfied with a normal GAN architecture - so I started using SAGAN. So I set up my architecture, loaded in my
I liked GANs for a while. So much, that I started writing about them in reputable publications before I even had my first job in the Machine Learning field. I trained them mostly on faces, trying to enter the Uncanny Valley,