I am getting the following error while loading the pre-trained weights, any idea how to solve this, I am running on a custom dataset. the training setup is the same as the default repo. I just changed data paths. python scripts/train.py --dataset_type=svo_encode --exp_dir=./experiments/svo_exp10 --...

I'm trying to run the code on CPU and I'm facing some issues. Can you please guide me on what changes I need to make to run the code on CPU?

When I run "ffhq_encode" in inference_playground.ipynb, I got incorrect output like this png file. Do you know why I can get this result? When I run the same code in Google colab, I could get the correct image. So, maybe it's the problem about my environment. My environment is here WSL2 (Ubuntu 22....

I tried to project face segmentations to real face images. To finish the task, I used CelebAMask-HQ dataset and load the model with psp_celebs_seg_to_face.pt. But I could't get diverse results althougn I set the randomize_noise is True. I want to know how to get the results like this.

https://github.com/Sxela/ArcaneGAN（like this project） Compared with this project（pix2pix-HD）, which one is more suitable for video conversion animation Is there any project related to converting video to animation? I hope you can recommend it

Can I use my own pretrained model .pt which I trained using vanilla StyleGAN2 for encoding my own images? Or Should I be training the encoder again from this repo?

pSp has BatchNorm2 layer. Do multiple GPUs need to change it to SyncBatchNorm？

Thank you for your great work. In the paper, you show you can encode the mask to the first seven w+ latant, and you random latent for the rest layers. But I see your code. The code directly encodes the mask to the whole w+ latent. Why? This will lead that the style-mixing operation generates differe...

I can encode real images (3,256,256) obtaining a latent vector of shape (18,512) Performing the encoding on many images, such as celebahq labelled dataset, i want to find the latent editing directions for some the annotated attributes. In particular i'll use an svm to extract a binary decision boun...

If I train on the following data pairs, how should I set the training parameters and training configuration? What pre-trained model do I need to use?