MMSegmentation installation configuration
A basic environment configuration
First install pytorch
pip3 install install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio==0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
Then use mim to install MMCV.
The above steps are not popular, and then follow the following operations: Install other required libraries
pip3 install opencv-python pillow matplotlib seaborn tqdm pytorch-lightning 'mmdet>=3.0.0rc1' -i https://pypi.tuna.tsinghua.edu.cn/simple
2. Install MMSegmentation
First check if there is MMSegmentation locally and delete it if so.
# 删掉原有的 mmsegmentation 文件夹(如有)
rm -rf mmsegmentation
Then clone it from the official website.
After the download is completed, we enter the folder we just downloaded and compile it: (I have cloned it many times and I always get raped)
After downloading, you can check whether the installation is successful by running the following command:
3. Using MMSegmentation
We can use the pre-trained model and weight file Model Zoo here
: https://github.com/open-mmlab/mmsegmentation/blob/master/docs/en/model_zoo.md
Here you can download its configuration file and pre- The training model can be easily applied.
We use PSPNet for experiments