1参考的博客
包含各种问题,各种折腾
1.https://blog.csdn.net/qq_31531635/article/details/79963188
2.https://blog.csdn.net/wanzhen4330/article/details/81699769
3.https://blog.csdn.net/qq_39938666/article/details/89601658
4.https://blog.csdn.net/qq_42165939/article/details/86181585
5.https://blog.csdn.net/zzq060143/article/details/88042075
6.https://blog.csdn.net/qq_38671976/article/details/84332140
7.https://blog.csdn.net/WannaSeaU/article/details/88427010
8.https://blog.csdn.net/yucicheung/article/details/79095742
2.遇到的坑
1.Pytorch官网上没有CUDA8.0了,采用下面的方式安装
pip install https://download.pytorch.org/whl/cu80/torch-1.0.1.post2-cp36-cp36m-linux_x86_64.whl
pip install torchvision
2.直接安装巨慢无比,添加清华源
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
conda config --set show_channel_urls yes
添加的时候出现有关于yaml的错误,解决方法:使用pip安装升级
3.最终加载模型的时候
import torchvision
1.出现:ModuleNotFoundError: No module named 'Image'错误
2.出现:ModuleNotFoundError: No module named 'six'错误
解决方法:1.pip install -U pillow将pillow包给更新了
2.pip install -U six 全部更新