MobileStyleGAN.pytorch
MobileStyleGAN.pytorch copied to clipboard
bes-dev
An official implementation of MobileStyleGAN in PyTorch
when i try to convert to coreml the code crash with: RuntimeError: PyTorch convert function for op 'numel' not implemented.
Hello: I am new to Pytorch, and I want to learn how to use StyleGan2, and I found a big dataset from here: https://github.com/NVlabs/metfaces-dataset I download the datasets and found...
Hello and so happy to see you use Pytorch-Lightning! :tada: Just wondering if you already heard about quite the new **Pytorch Lightning (PL) ecosystem CI** where we would like to...
Have you tried using gt['rgb'] instead of gt['img'] to distll the student network? Or the gt['rgb'] is useless. https://github.com/bes-dev/MobileStyleGAN.pytorch/blob/2d18a80bed6be3ec0eec703cc9be50616f2401ee/core/loss/distiller_loss.py#L35
Thanks for sharing your ideas and code. It is rather fun to compare it to StyleGAN2. I am wondering about this 1. Why does your algorithm do poorly with eyeglasses?...
Hi there, much thanks for your work on MobileStyleGAN I have a few questions to ask. 1. How long should the training last? I have been training on my custom...
Hi, thank you very much for your work. Can MobileStyleGAN be deployed as openvino with fp16 accuracy?
Hi, here’s a thank you video for this model I was exploring multithreading it just recently. Hope it’s ok it says mobilestylegan only but I hope those interested find here...
You mentioned in the paper that setting batch_size==8 on four 2080Ti takes about three days to train.  But when I set batch_size>=4 on V100, I get an error. ...
