swapping-autoencoder-pytorch

swapping-autoencoder-pytorch copied to clipboard

Questions regarding some design choices

3

Really impressive work and high-quality code release! I found several intriguing design choices while digging into the codebase, and looking for some clarifications or explanations of them: 1. **Blur in...

hubert0527

Hi! Can you please explain why if the training mode is 'generator' the discriminator is trained? Thanks. https://github.com/taesungp/swapping-autoencoder-pytorch/blob/d67e60f8a702868d08e5b943fc7f46908d78e48b/optimizers/swapping_autoencoder_optimizer.py#L61-L64

kampelmuehler

Mixed precision training?

1

I'm trying to add mixed precision training support. I'm newbie at this~ What I have figured out so far is the `upfirdn2d` & `fused` modules are compiled at runtime. I...

cceyda

The outputs are not correct.

2

Hello, I load the checkpoints and testphotos, and run the command `python -m experiments ffhq512_pretrained test swapping_grid` and get the output  The same as other commands. I didn't modified...

panhtt

Hi, I find the work of this repo very interesting and I would like to try it, but the version of Python 3.6 referred to in the README is currently...

migonsa

Hello,Thank you for your work.I hope others can notice that when you want dim>2, please make corresponding modifications ` style = self.modulation(style) if self.demodulate: style = style * torch.rsqrt(style.pow(2).mean([1], keepdim=True)...

AltoriaDD

Question about the code

1

Thank you very much for the code! It's really great! In the `compute_generator_losses` function, one can read: ```python if self.opt.lambda_PatchGAN > 0.0: real_feat = self.Dpatch.extract_features( self.get_random_crops(real), aggregate=self.opt.patch_use_aggregation).detach() mix_feat = self.Dpatch.extract_features(self.get_random_crops(mix))...

alamie