stylegan2-pytorch

stylegan2-pytorch copied to clipboard

train with augment

6

do I train the model with python -m torch.distributed.launch --nproc_per_node=N_GPU --master_port=PORT train.py --batch BATCH_SIZE LMDB_PATH **--augment**

KunWang123

Could you please add the pretrained models for 512px and 1024px ,thank you

wangmengmeng99

First, thanks for you amazing work. I managed to generate latent image and latent 'pt' file using projector.py. This is the projector image:  But I failed to generate a...

digital-nomad-cheng

I want to train boundary with w_plus latent ,how can i generate w_plus?

zeta7337

Convert weights from Stylegan2-ada-pytorch

6

Hi. Is it possible to convert weights from stylegan2-ada-pytorch (https://github.com/NVlabs/stylegan2-ada-pytorch) pickle file to pt with convert_weight tool?

dokluch

Why flip weight and add 1 to bias when loading tensorflow pretrained model

1

Thanks to the great work. I noticed that when loading the tensorflow pretrained model you flip "Conv0_up.conv.weight" and add 1 to the "conv.modulation.bias. Is this because of the difference between...

zengxianyu

[Enhancement] Adaptive Convolution

1

Seeing as this repo has some experimental elements in it like SWAGAN, I thought you might be interested in this: https://studios.disneyresearch.com/2021/06/19/adaptive-convolutions-for-structure-aware-style-transfer/ There's a section outlining an alternative to weight demodulation...

torridgristle

Pretrained 256 ffhq model missing noise keys in state_dict

1

Trying to generate images using the 256x256 model linked in the readme I get the following error `RuntimeError: Error(s) in loading state_dict for Generator: Missing key(s) in state_dict: "noises.noise_0", "noises.noise_1",...

justinpinkney

Training with distributed sampling

2

I noticed that the data was not shuffled correctly while training. Seems that there should be `set_epoch` added when distributed training is used. See here https://github.com/pytorch/examples/blob/fe8abc3c810420df2856c6e668258f396b154cee/imagenet/main.py#L232. See here as well:...

BadourAlBahar

conditional implementation

6

Hi, did you also implement a conditional implementation, so that I can pass files with labels, as in the original TensorFlow implementation?

PieraRiccio