build ALRPLoss mmdet

橘子辉煌鸭

于 2020-12-27 15:45:59 发布

阅读量382

点赞数

CC 4.0 BY-SA版权

分类专栏： python

本文链接：https://blog.csdn.net/weixin_43256434/article/details/111811924

python 专栏收录该内容

5 篇文章

订阅专栏

博客推荐了Python 3.7、PyTorch 1.4、CUDA 10.1和mmcv 0.6.2的配置。若配置未一次成功，可能出现'libtorch_cpu.so: cannot open shared object file: No such file or directory'问题，解决办法是执行'rm -r build'和'python setup.py develop'。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Recommended configuration: Python 3.7,PyTorch 1.4, CUDA 10.1 and mmcv 0.6.2.

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

conda install pytorch=1.4 cudatoolkit=10.1 torchvision -c pytorch
pip install mmcv==0.6.2
git clone https://github.com/kemaloksuz/aLRPLoss.git
cd aLRPLoss

pip install -r requirements/build.txt
pip install "git+https://github.com/open-mmlab/cocoapi.git#subdirectory=pycocotools"
pip install -v -e .