version problems

[xiaridehehe]

Because I encountered a lot of problems in the process of running the code, mainly version problems, so here I share the version that I finally ran successfully.
conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge
pip install mmcv-full==1.6.2 -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10/index.html
The versions of pytorch, cuda, and mmcv must correspond, otherwise they cannot run through the code. Since the version of mmcv has been upgraded, you need to comment out the author's code for the mmcv version check, i.e., lines 26, 27, and 28 of the mmseg/_init.py file.