MMSegmentation环境配置

用之前搭建好的mmdetection，总显示找不到cuda10.1的so文件，没办法，只好重新安装一下，这次过程很简单。

1.创建conda虚拟环境

conda create -n mmseg python=3.7 -y
conda activate mmseg

2.配置环境

conda install pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=10.1 -c pytorch -y

3.安装 mmcv

# install the latest mmcv 注意安装mmcv-full时cuda和torch的版本一定要对应
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.6.0/index.html

4.安装 MMDetection

# install mmdetection
git clone https://gitee.com/open-mmlab/mmdetection.git
cd mmdetection
pip install -r requirements/build.txt
pip install -v -e .

5.安装MMSegmentation

# install mmdetection
git clone https://gitee.com/open-mmlab/mmsegmentation.git
cd mmsegmentation
pip install -v -e .

安装完成