stylegan2-pytorch
stylegan2-pytorch copied to clipboard
lucidrains
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
With ref to : https://github.com/lucidrains/stylegan2-pytorch/blob/0588213d4e552095905873a24f577007c40c1667/stylegan2_pytorch/stylegan2_pytorch.py#L215-L226 I think "`map(lambda ddp: ddp.no_sync, ddps)`" should be changed to "`list(map(lambda ddp: ddp.no_sync, ddps))`" Otherwise, since map is an iterator, it can be used only...
How to generate full size image, Is there any options?
Add: - support to log loss metrics and generated images to Weights & Biases (`log_images_to_wandb` static method) - type-hinting to the `train_from_folder` function - type-hinting to the `Trainer` class -...
From https://arxiv.org/abs/2006.14567 (taken from the Projects page for this repo) Currently testing on my own, but so far has had very promising early results.
Hi everyone. I met the error saying "RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters...
Hi， thank you provide a code for Dual Contrastive Loss， and is it useful for performance on FFHQ dataset？？ and did you add self-attention and reference-attention in D？
Hi! First of all, thank you so much for your implementation! I am trying to train the StyleGAN on grayscale MNIST images (single channel), and I am having quite a...
Hi, I am currently trying to train a model. But it seems to me that my GPU is not used fully all the time. As I can tell by the...
Metadata
Owner
Metadata
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement