配环境是个很玄学的事情，请一定按照顺序执行，本文档主要解决了的stgcn下环境的配置问题。
1.miniconda比较好安装，记得安装完了之后更改一下环境变量
参考：https://blog.csdn.net/Oxford1151/article/details/130326163
2.在终端（cmd or conda prompt）conda create -n nameXXX python=3.9
3.cuda的版本要根据显卡驱动的版本选择，首先在terminal 输入nvidia-smi看cuda支持的最高版本，我的是12.2，然后torch要版本对应
参考https://blog.csdn.net/A6456ef/article/details/131744237
cuda版本切换：https://blog.csdn.net/qq_42406643/article/details/109545766
4.安装torch0.4.0
参考
报错找不到torch：from torch._C import * ImportError: DLL load failed: 找不到指定的模块”去https://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy下载对应python版本的numpy
解决方法参考：https://blog.csdn.net/wslhynn277/article/details/103563052/
https://blog.csdn.net/xwy990/article/details/80995893
5.部分依赖包版本太高了：
pip install -i https://pypi.douban.com/simple scikit-learn0.19.2
pip install numpy1.17.0
6.却啥补啥，比如matplot、visdom之类的。
最终环境：
ca-certificates 2023.11.17 h56e8100_0 conda-forge
certifi 2021.5.30 py36ha15d459_0 conda-forge
charset-normalizer 2.0.12 pypi_0 pypi
cmake 3.28.1 pypi_0 pypi
colorama 0.4.5 pypi_0 pypi
cycler 0.11.0 pyhd8ed1ab_0 conda-forge
decorator 4.4.2 pypi_0 pypi
distro 1.9.0 pypi_0 pypi
freetype 2.12.1 hdaf720e_2 conda-forge
icu 69.1 h0e60522_0 conda-forge
idna 3.6 pypi_0 pypi
importlib-resources 5.4.0 pypi_0 pypi
intel-openmp 2023.2.0 h57928b3_50497 conda-forge
joblib 1.1.1 pypi_0 pypi
jpeg 9e hcfcfb64_3 conda-forge
jsonpatch 1.32 pypi_0 pypi
jsonpointer 2.3 pypi_0 pypi
kiwisolver 1.3.1 py36he95197e_1 conda-forge
lcms2 2.12 h2a16943_0 conda-forge
lerc 3.0 h0e60522_0 conda-forge
libblas 3.9.0 20_win64_mkl conda-forge
libcblas 3.9.0 20_win64_mkl conda-forge
libclang 13.0.1 default_h66ee7f4_5 conda-forge
libdeflate 1.10 h8ffe710_0 conda-forge
libhwloc 2.9.3 default_haede6df_1009 conda-forge
libiconv 1.17 hcfcfb64_2 conda-forge
liblapack 3.9.0 20_win64_mkl conda-forge
libpng 1.6.39 h19919ed_0 conda-forge
libsqlite 3.44.2 hcfcfb64_0 conda-forge
libtiff 4.3.0 hc4061b1_4 conda-forge
libxml2 2.12.4 hc3477c8_1 conda-forge
libzlib 1.2.13 hcfcfb64_5 conda-forge
matplotlib 3.3.4 py36ha15d459_0 conda-forge
matplotlib-base 3.3.4 py36h1abdf75_0 conda-forge
mkl 2023.2.0 h6a75c08_50497 conda-forge
networkx 2.5.1 pypi_0 pypi
numpy 1.17.0 pypi_0 pypi
olefile 0.46 pyh9f0ad1d_1 conda-forge
opencv-python 3.4.3.18 pypi_0 pypi
openjpeg 2.5.0 hb211442_0 conda-forge
openssl 1.1.1w hcfcfb64_0 conda-forge
packaging 21.3 pypi_0 pypi
pillow 8.4.0 pypi_0 pypi
pip 21.3.1 pyhd8ed1ab_0 conda-forge
pthreads-win32 2.9.1 hfa6e2cd_3 conda-forge
pyparsing 3.1.1 pyhd8ed1ab_0 conda-forge
pyqt 5.12.3 py36ha15d459_7 conda-forge
pyqt-impl 5.12.3 py36he2d232f_7 conda-forge
pyqt5-sip 4.19.18 py36he2d232f_7 conda-forge
pyqtchart 5.12 py36he2d232f_7 conda-forge
pyqtwebengine 5.12.1 py36he2d232f_7 conda-forge
python 3.6.15 h39d44d4_0_cpython conda-forge
python-dateutil 2.8.2 pyhd8ed1ab_0 conda-forge
python_abi 3.6 2_cp36m conda-forge
qt 5.12.9 h556501e_6 conda-forge
requests 2.27.1 pypi_0 pypi
scikit-build 0.16.7 pypi_0 pypi
scikit-learn 0.19.2 pypi_0 pypi
scipy 1.1.0 pypi_0 pypi
setuptools 58.0.4 py36ha15d459_2 conda-forge
six 1.16.0 pyh6c4a22f_0 conda-forge
sklearn 0.0 pypi_0 pypi
sqlite 3.44.2 hcfcfb64_0 conda-forge
tbb 2021.11.0 h91493d7_0 conda-forge
threadpoolctl 3.1.0 pypi_0 pypi
tk 8.6.13 h5226925_1 conda-forge
torch 0.4.0 pypi_0 pypi
torchvision 0.2.1 pypi_0 pypi
tornado 6.1 py36h68aa20f_1 conda-forge
tqdm 4.64.1 pypi_0 pypi
typing-extensions 4.1.1 pypi_0 pypi
ucrt 10.0.22621.0 h57928b3_0 conda-forge
urllib3 1.26.18 pypi_0 pypi
vc 14.3 hcf57466_18 conda-forge
vc14_runtime 14.38.33130 h82b7239_18 conda-forge
visdom 0.2.4 pypi_0 pypi
vs2015_runtime 14.38.33130 hcb4865c_18 conda-forge
websocket-client 1.3.1 pypi_0 pypi
wheel 0.37.1 pyhd8ed1ab_0 conda-forge
xz 5.2.6 h8d14728_0 conda-forge
zipp 3.6.0 pypi_0 pypi
zlib 1.2.13 hcfcfb64_5 conda-forge
zstd 1.5.5 h12be248_0 conda-forge
