Hello, thanks for your great work. I tried to optimize the latent codes of a given face image with your pre-trained CelebAHQ model but failed with 'CUDA out of memory'(on a single TITAN xp GPU,12G). I simply use the rgb l1 loss between the gt image and generate image, Adam optimizer. Could you please offer some official code or some strategy about solving this problem?
Hello, thanks for your great work. I tried to optimize the latent codes of a given face image with your pre-trained CelebAHQ model but failed with 'CUDA out of memory'(on a single TITAN xp GPU,12G). I simply use the rgb l1 loss between the gt image and generate image, Adam optimizer. Could you please offer some official code or some strategy about solving this problem?