WHAT I'VE LEARNED
- Understand GAN components, build basic GANs using PyTorch and advanced DCGANs using convolutional layers, control your GAN and build conditional GAN
- Use GANs for data augmentation and privacy preservation, survey GANs applications, and examine and build Pix2Pix and CycleGAN for image translation
- Compare generative models, use FID method to assess GAN fidelity and diversity, learn to detect bias in GAN, and implement StyleGAN techniques
SKILLS I'VE DEVELOPED
- Controllable Generation
- WGANs
- Conditional Generation
- Components of GANs
- DCGANs