Thank you for open-sourcing this project! We are trying to implement the model, and are trying to better understand the affine_layers variable that is used to generate the synthetic images. What are these layers that are being taken from the pre-trained StyleGAN1 (SG1)? Are they specific hidden layers? Also, if we were to swap this SG1 for our own model, would the corresponding affine_layers be sufficient along with the randomly generated latent variable?
Thank you for open-sourcing this project! We are trying to implement the model, and are trying to better understand the
affine_layers
variable that is used to generate the synthetic images. What are these layers that are being taken from the pre-trained StyleGAN1 (SG1)? Are they specific hidden layers? Also, if we were to swap this SG1 for our own model, would the correspondingaffine_layers
be sufficient along with the randomly generatedlatent
variable?Thank you for your time, we appreciate it!