ubuntu18.04配置Swin Transformer环境

1.安装pytorch

pip install torch==1.8.1 -i https://pypi.douban.com/simple/
pip install torchvision==0.9.1 -i https://pypi.douban.com/simple/

2.安装 mmcv (cuda与torch版本号可自行修改)

pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.8.1/index.html

3.安装 mmdetection

cd '/home/xzz/Swin-Transformer-Object-Detection-master'
 pip install -r requirements.txt -i https://pypi.douban.com/simple/
python setup.py develop

4.安装apex

cd apex-master
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" .

或者自己下载:

git clone  https://github.com/NVIDIA/apex
cd apex
python setup.py install --cpp_ext

5.运行

python demo/image_demo.py demo/demo.jpg configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco.py mask_rcnn_swin_tiny_patch4_window7.pth

猜你喜欢

转载自blog.csdn.net/qq_45752541/article/details/119979305