gzhhhere
gzhhhere
请问你解决问题了吗，我也想知道如何使用自己的数据训练。
> I really would suggest to use `Docker` for this in combination with `nvidia-docker2`. Here is my working Dockerfile: > > ``` > FROM nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04 > > RUN apt update...
oh, maybe i should install tensorflow
installed tensorflow 2.6.0, still no module named dnnlib.
i saw 'You need to clone official repositories, (https://github.com/NVlabs/stylegan2) as it is requires for load official checkpoints.'
i used docker by 'docker pull nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04' and ' pip3 install tensorflow-gpu==1.14.0 scipy==1.3.3 requests==2.22.0 Pillow==6.2.1 h5py==2.9.0 imageio==2.9.0 imageio-ffmpeg==0.4.2 tqdm==4.49.0 torch==1.4.0 torchvision==0.5.0 pandas numpy pillow==6.2.1 opencv-python scikit-learn matplotlib seaborn jupyterlab ninja'...
> Thanks for your attention, what i try to convert is the 'stylegan2-celebahq-256x256.pkl' which is downloaded from https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/stylegan2/files. By the way  is the file structure right? i put your...
> Yes, it is right. when i try to convert 'stylegan2-celebahq-256x256.pkl' i have ' File "convert_weight.py", line 236, in generator, discriminator, g_ema = pickle.load(f) ModuleNotFoundError: No module named 'torch_utils' when...
> It seems like that it is for stylegan3. Currently it is not supported. you are right, the weight from https://nvlabs-fi-cdn.nvidia.com/stylegan2/networks/ is converable using your code, however, i still can't...
> Does anyone have the pre-trained model of stylegan2 on CelebA dataset? hi! do you solve your problem? i have the weight in tensorflow and i need the weight in...