配置mmsegmentation

mmcv与mmsegmentation总是不匹配

于是按照RDRNet中的配置去重新写

conda create -n mmseg python=3.8.10

conda activate mmseg

pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113 -i https://pypi.tuna.tsinghua.edu.cn/simple

按照玩pytorch后按照mmcv，进入mmcv官网安装 — mmcv 2.2.0 文档

pip install mmcv==2.0.0 -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.12/index.html -i https://pypi.tuna.tsinghua.edu.cn/simple

接下来要按照mmsegmentation，注意mmcv要有mmseg版本匹配

pip install "mmsegmentation==1.0.0"