StyleSpace-pytorch
StyleSpace-pytorch copied to clipboard
GANs inversion using encoder4editing
Hi!
I am implementing GANs inversion using repo encoder4editing. But I saw that they trained the model with stylegan2 generator to be fixed. In your notebook, you also use pretrained model of stylegans2, and then inject it into your encoder, decoder.
- Is your decoder with conv wrapper is what makes StyleSpace?
- I asked the author of encoder4editing and they said as follow:
But I do not clearly understand the phrase "extracting the StyleSpace representation during a forward pass of the generator". Could you explain me this? Thank you
The S space is made from the W space. The screenshot says to use any optimization method to get the W+ values. Now, you pass the W+ into the affine layer (see the affine layer A in the paper https://arxiv.org/abs/2011.12799 Figure 9). This will let you get the S space from the W+.