Closed bb12346 closed 2 years ago
e4e is an inversion method that predicts latent codes that are more suitable for editing. e4e is trained using FFHQ and tested using CelebA-HQ which is exactly correct. We followed the StyleCLIP method to invert the latent codes of CelebA-HQ with e4e and split them into training and testing parts, in the same way as StyleCLIP. You can download latent codes from train set, test set.
Thank you for your reply.
Thank you for your great project!
In this paper, you said “We train and evaluate our hair mapper on the CelebA-HQ dataset. Since we use e4e [43] as our inversion encoder, we follow its division of the training set and test set.” However, I found that e4e used the FFHQ dataset for training and the CelebA-HQ test dataset for evaluation. Hence, I feel confused. My question is that how to split the training and test datasets on the CelebA-HQ dataset?