stylegan2-pytorch icon indicating copy to clipboard operation
stylegan2-pytorch copied to clipboard

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

Results 135 stylegan2-pytorch issues
Sort by recently updated
recently updated
newest added

Hi I get the following errors while trying to use the Fused activation.Do any one have an idea why? Traceback (most recent call last): File "/is/ps2/pghosh/.virtualenvs/gif/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 960, in _build_extension_module...

After I created the lmdb dataset, I started training the model.This error will occur.My dataset is all .jpg files.

I am trying to export the stylegan generator to onnx but the custom FusedLeakyReLUFunction is not proper for this purpose. Someone can help??? Is this possible?

Hi, I'm trying to load the CIFAR10 checkpoint (from NVIDIA official implementation page, after I converted the weights). I do this with this code `model = Generator(32, 512, 2) ckpt...

Use code snippets format for easier accessibility > python prepare_data.py --out LMDB_PATH --n_worker N_WORKER --size SIZE1,SIZE2,SIZE3,... DATASET_PATH => ```shell python prepare_data.py --out LMDB_PATH --n_worker N_WORKER --size SIZE1,SIZE2,SIZE3,... DATASET_PATH ```

Thanks for the code. Does anybody have had same problem with me? I got problem on fused_act.py and upfirdn2d.py here is my error message: File "E:\face\code\pytorchNo1\venv\lib\site-packages\torch\utils\cpp_extension.py", line 1740, in _run_ninja_build...

I'm trying to use a native pytorch version of `fused_leaky_relu` and `upfirdn2d` #66 #70 However there is a dimensionality bug in the `upfirdn2d_native` so I fixed it like this, ```python...

**run:** python convert_weight.py --repo ../stylegan2 stylegan2-ffhq-config-f.pkl **Error** Traceback (most recent call last): File "convert_weight.py", line 11, in from model import Generator, Discriminator File "/home/dan.wang/train_script/GAN/gan2shape/GAN2Shape/gan2shape/stylegan2/stylegan2-pytorch/model.py", line 11, in from op import...

Hi, I want to use the pre-trained styleGAN2 discriminator as the supervision for training another image generation network. However, the pre-trained discriminator always outputs negative scores ( denotes fake images)...

Hi, thanks for watching this. I've tried to use convert_weight.py to convert my .pkl snapshot to a .pt file. I git cloned the stylegan2 model that the author suggested but...