stylegan2-pytorch

stylegan2-pytorch copied to clipboard

Is it okay to train the model pretrained with 1024*1024 ffhq with images with a lower resolution than this?

leeisack

finetune error based on stylegan2-ffhq-config-f.pt

8

I wanna do some finetune works based on my own dataset, I create LMDB dataset based on the guideline in the repo: `python prepare_data.py --out LMDB_PATH --n_worker N_WORKER --size SIZE1,SIZE2,SIZE3,......

Ethantequila

I want to project the picture into the latent space, and then generate the picture, how can I use your model to achieve it?

1

zhouyuezhou1

AssertionError : assert state["version"] in [2, 3, 4]

8

Hi, I tried running `convert_weight.py` in a couple of different environments but I get the following error: ``` File "/stylegan2/dnnlib/tflib/network.py", line 278, in __setstate__ assert state["version"] in [2, 3, 4]...

IvonaTau

Ask for Software environment

24

subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1. RuntimeError: Error building extension 'fused': [1/3] /usr/local/cuda/bin/nvcc ninja: build stopped: subcommand failed. I spent a day, but I can't train it.

JNUChenYiHong

Pretrain model on CelebA

1

Does anyone have the pre-trained model of stylegan2 on CelebA dataset?

GoGoDuck912

torch version

33

Some errors occurred during compiling the code, can you tell us the version of the torch, and other software environment, such as cuda, cudnn, gcc, ninja, re2c. Thank you !

qingzi02010

Hi, first of all thanks for your work. I'm having issues with projector.py when steps < 100. E.g. with !python projector.py --size 1024 --step 99 --ckpt /content/output/checkpoint/latest.pt $filepath I get...

smithee77

JJack27

I'm training on a smaller version of 256x256 FFHQ with only 3000 faces. `python -m torch.distributed.launch --nproc_per_node=2 train.py --batch 8 --augment --wandb /workspace/data/ffhq3k-lmdb/ ` The emitted samples have some faces...

jonilaserson