Training a generative model

There are mainly 2 stages when training a generative model.

■ Perceptual Compression
- Process of removing high-frequency details
- Encapsulate data into an abstract representation
GANS accomplish this by projecting data from pixel space to a hyperspace called latent space.

■ Semantic Compression
- Capture semantic structure present in data
- Preservation of the context and inter-relationship of various objects
Transformers are good at capturing semantic structures