Questions
- Why do we need a Pix2Pix GAN if a supervised learning algorithm such as UNet could have worked to generate images from contours?
- Why do we need to optimize for three different loss functions in CycleGAN?
- How do the tricks used by ProgressiveGAN help in building a StyleGAN model?
- How do we identify the latent vectors that correspond to a given custom image?
Learn more on Discord
Join our community’s Discord space for discussions with the authors and other readers: