content-aware-gan-compression
content-aware-gan-compression copied to clipboard
lychenyoko
CVPR2021 Content-Aware GAN Compression
According to the following line, the `get_projected_image.py` code imports several functions from the `image_projector` (nested) in the `Evaluation` directory. However, I cannot find the package in the `Evaluation` directory. https://github.com/lychenyoko/content-aware-gan-compression/blob/64fd76b88a66e4699bad05515c8167c1289cbb85/get_projected_image.py#L11
Hi, I have been trying to prune a [StyleGAN2-ADA-PyTorch](https://github.com/NVlabs/stylegan2-ada-pytorch) model (which is saved in .pt format) which by default saves in .pkl format but, I have changed it to .pt...
Hello. I was deeply impressed by your paper. Therefore, I would like to apply your paper's method to other networks. Can this method be applied to other models such as...
Thank you for your very interesting paper. I want to compare cagc with GS using StyleGAN2. How can I conduct GS-pruning using StyleGAN2 to reproduce comparison which is listed in...
thank you for sharing the your code. I have a question about "Get_Weight_Gradient" function in content aware pruning. You only consider the gradient of to_rgbs[-1] in rgb layers. (I mean...
loss = torch.sum(torch.abs(noisy_img - img_tensor)) I hope to know why define pruning loss like above and the reason for minimizing this loss.
