search

pbaylies / stylegan-encoder

StyleGAN Encoder - converts real images to latent space
Other
740 stars 182 forks source link

dlatent_avg explain #23

Closed khiemkhanh98 closed 4 years ago

khiemkhanh98 commented 4 years ago

Hi pbaylies,

just wanna say thank u for your wonderful repos. However, as i can see from the NVlabs original readme, they said that the truncation trick will be disables when we use the subnetwork of the G and we would have to do it manually. Since your code is using the dlatent and only make use of the synthesis network , i think that the dlatent_avg part is missing the truncation trick part. Please correct me if i'm wrong

pbaylies commented 4 years ago

Hi @khiemkhanh98 you need the dlatent average to perform the truncation trick properly in latents, you can see that from their example code as well. I'm glad you like the repo!