search

eladrich / pixel2style2pixel

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
https://eladrich.github.io/pixel2style2pixel/
MIT License
3.19k stars 570 forks source link

running Inference.py on win10 ltsc #123

Closed vbqgyy closed 3 years ago

vbqgyy commented 3 years ago

error01

win10 GTX3090 CUDA11.1 torch 1.8.1

_libgcc_mutex 0.1 main defaults ca-certificates 2020.4.5.1 hecc5488_0 conda-forge certifi 2020.4.5.1 py36h9f0ad1d_0 conda-forge cycler 0.10.0 dataclasses 0.8 kiwisolver 1.3.1 libffi 3.2.1 ha925a31_1007 conda-forge m2w64-gcc-libgfortran 5.3.0 6 conda-forge m2w64-gcc-libs 5.3.0 7 conda-forge m2w64-gcc-libs-core 5.3.0 7 conda-forge m2w64-gmp 6.1.0 2 conda-forge m2w64-libwinpthread-git 5.0.0.4634.697f757 2 conda-forge matplotlib 3.2.1 msys2-conda-epoch 20160418 1 conda-forge ninja 1.10.0 py36h7ef1ec2_0
numpy 1.18.4 opencv-python 4.2.0.34 openssl 1.1.1g he774522_1
Pillow 7.1.2 pip 20.0.2 pip 21.0.1 pip 20.0.2 py36_3 defaults pyparsing 2.4.7 pyreadline 2.1 py36ha15d459_1003 conda-forge python 3.6.7 he025d50_1008_cpython conda-forge python-dateutil 2.8.1 python_abi 3.6 1_cp36m conda-forge scipy 1.4.1 setuptools 46.4.0 py36_0 defaults setuptools 46.4.0 six 1.15.0 sqlite 3.31.1 h2a8f88b_1 defaults tk 8.6.8 hfa6e2cd_1000 conda-forge torch 1.8.1+cu111 torchvision 0.9.1+cu111 tqdm 4.46.0 typing-extensions 3.7.4.3 vc 14.2 hb210afc_4 conda-forge vs2015_runtime 14.28.29325 h5e1d092_4 conda-forge wheel 0.34.2 py36_0 conda-forge wincertstore 0.2 py36ha15d459_1006 conda-forge xz 5.2.5 h62dcd97_1 conda-forge zlib 1.2.11 h62dcd97_1010 conda-forge

yuval-alaluf commented 3 years ago

Have you looked at the other issues related to compiling ninja on windows? Also, I would recommend trying running with conda environment as this typically resolves most issues. You can check out a similar issue here: https://github.com/eladrich/pixel2style2pixel/issues/29

vbqgyy commented 3 years ago

Thank you for your reply. I read almost all the relevant content. Then I tried stylegan2-pytorch and it worked well. I have tried this project many times. I will continue to try this. Is a very interesting project. thank you very much .

yuval-alaluf commented 3 years ago

I see. If you were able to get stylegan2-pytorch to work on your system, you should be able to get pSp to work as well. You should try seeing how to compile ninja for CUDA 11.

vbqgyy commented 3 years ago

I'm trying. Fortunately, I succeeded once, and then I kept failing. Then I deleted the. Lock file and tried again, showing the same error. But I think I'm going to make it. I am grateful for your help.