install openmmlab

https://github.com/open-mmlab

https://github.com/open-mmlab/mmdetection

GET STARTED — MMDetection 3.3.0 documentation

mmcv  安装

先安装cuda和pytorch。

根据 cuda 版本和已安装的 torch 版本,选择 mmcv 版本。

确定了mmcv版本,然后再找mmdetection mmseg mmdetection3d对应的版本

Installation — mmcv 2.2.0 documentation

https://mmcv.readthedocs.io/zh-cn/1.x/get_started/installation.html

mmcv-full

pip install mmcv-full==1.4.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.10/index.html

 mmcv

pip install mmcv==1.4.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.10/index.html

安装mmdetection

根据mmcv版本找对应的mmdetection版本

Prerequisites — MMDetection 2.24.0 documentation

MMDetection versionMMCV version
mastermmcv-full>=1.3.17, <1.6.0
2.24.0mmcv-full>=1.3.17, <1.6.0
2.23.0mmcv-full>=1.3.17, <1.5.0
2.22.0mmcv-full>=1.3.17, <1.5.0
2.21.0mmcv-full>=1.3.17, <1.5.0
2.20.0mmcv-full>=1.3.17, <1.5.0
2.19.1mmcv-full>=1.3.17, <1.5.0
2.19.0mmcv-full>=1.3.17, <1.5.0
2.18.0mmcv-full>=1.3.17, <1.4.0
2.17.0mmcv-full>=1.3.14, <1.4.0
2.16.0mmcv-full>=1.3.8, <1.4.0
2.15.1mmcv-full>=1.3.8, <1.4.0
2.15.0mmcv-full>=1.3.8, <1.4.0
2.14.0mmcv-full>=1.3.8, <1.4.0
2.13.0mmcv-full>=1.3.3, <1.4.0
2.12.0mmcv-full>=1.3.3, <1.4.0
2.11.0mmcv-full>=1.2.4, <1.4.0
2.10.0mmcv-full>=1.2.4, <1.4.0
2.9.0mmcv-full>=1.2.4, <1.4.0
2.8.0mmcv-full>=1.2.4, <1.4.0
2.7.0mmcv-full>=1.1.5, <1.4.0
2.6.0mmcv-full>=1.1.5, <1.4.0
2.5.0mmcv-full>=1.1.5, <1.4.0
2.4.0mmcv-full>=1.1.1, <1.4.0
2.3.0mmcv-full==1.0.5
2.3.0rc0mmcv-full>=1.0.2
2.2.1mmcv==0.6.2
2.2.0mmcv==0.6.2
2.1.0mmcv>=0.5.9, <=0.6.1
2.0.0mmcv>=0.5.1, <=0.5.8

Step 1. Install MMDetection.

Case a: If you develop and run mmdet directly, install it from source:

git clone https://github.com/open-mmlab/mmdetection.git 
cd mmdetection
git checkout v0.16  # switch version
pip install -v -e . 

# "-v" means verbose, or more output 
# "-e" means installing a project in editable mode, 
# thus any local modifications made to the code will take effect without reinstallation.

Case b: If you use mmdet as a dependency or third-party package, install it with MIM:

mim install mmdet

安装mmdetection3d

git clone https://github.com/open-mmlab/mmdetection3d.git
cd mmdetection3d
git checkout v0.17.1       # 切换版本
pip install -v -e .

确定版本

Prerequisites — MMDetection3D 1.0.0rc1 documentation

MMDetection3D versionMMDetection versionMMSegmentation versionMMCV version
mastermmdet>=2.19.0, <=3.0.0mmseg>=0.20.0, <=1.0.0mmcv-full>=1.4.8, <=1.5.0
v1.0.0rc1mmdet>=2.19.0, <=3.0.0mmseg>=0.20.0, <=1.0.0mmcv-full>=1.4.8, <=1.5.0
v1.0.0rc0mmdet>=2.19.0, <=3.0.0mmseg>=0.20.0, <=1.0.0mmcv-full>=1.3.17, <=1.5.0
0.18.1mmdet>=2.19.0, <=3.0.0mmseg>=0.20.0, <=1.0.0mmcv-full>=1.3.17, <=1.5.0
0.18.0mmdet>=2.19.0, <=3.0.0mmseg>=0.20.0, <=1.0.0mmcv-full>=1.3.17, <=1.5.0
0.17.3mmdet>=2.14.0, <=3.0.0mmseg>=0.14.1, <=1.0.0mmcv-full>=1.3.8, <=1.4.0
0.17.2mmdet>=2.14.0, <=3.0.0mmseg>=0.14.1, <=1.0.0mmcv-full>=1.3.8, <=1.4.0
0.17.1mmdet>=2.14.0, <=3.0.0mmseg>=0.14.1, <=1.0.0mmcv-full>=1.3.8, <=1.4.0
0.17.0mmdet>=2.14.0, <=3.0.0mmseg>=0.14.1, <=1.0.0mmcv-full>=1.3.8, <=1.4.0
0.16.0mmdet>=2.14.0, <=3.0.0mmseg>=0.14.1, <=1.0.0mmcv-full>=1.3.8, <=1.4.0
0.15.0mmdet>=2.14.0, <=3.0.0mmseg>=0.14.1, <=1.0.0mmcv-full>=1.3.8, <=1.4.0
0.14.0mmdet>=2.10.0, <=2.11.0mmseg==0.14.0mmcv-full>=1.3.1, <=1.4.0
0.13.0mmdet>=2.10.0, <=2.11.0Not requiredmmcv-full>=1.2.4, <=1.4.0
0.12.0mmdet>=2.5.0, <=2.11.0Not requiredmmcv-full>=1.2.4, <=1.4.0
0.11.0mmdet>=2.5.0, <=2.11.0Not requiredmmcv-full>=1.2.4, <=1.3.0
0.10.0mmdet>=2.5.0, <=2.11.0Not requiredmmcv-full>=1.2.4, <=1.3.0
0.9.0mmdet>=2.5.0, <=2.11.0Not requiredmmcv-full>=1.2.4, <=1.3.0
0.8.0mmdet>=2.5.0, <=2.11.0Not requiredmmcv-full>=1.1.5, <=1.3.0
0.7.0mmdet>=2.5.0, <=2.11.0Not requiredmmcv-full>=1.1.5, <=1.3.0
0.6.0mmdet>=2.4.0, <=2.11.0Not requiredmmcv-full>=1.1.3, <=1.2.0
0.5.02.3.0Not requiredmmcv-full==1.0.5

某一依赖版本

 找到mmdet3d/__init__.py文件,可以查看依赖mmcv mmengine mmdet的版本,依次下载合适版本的进行安装

https://github.com/open-mmlab/mmdetection3d/blob/main/mmdet3d/__init__.py

mmdet3d/__init__.py

mmengine安装

 在一些早期版本的算法库中没有mmengine的依赖项。mmcv从1.x.x升级到2.x.x主要是

将mmcv-full拆分为mmcv和mmengine。

mmsegment

常见问题解答(FAQ) — MMSegmentation 0.30.0 文档

MMSegmentation versionMMCV versionMMClassification version
mastermmcv-full>=1.5.0, \<1.8.0mmcls>=0.20.1, \<=1.0.0
0.30.0mmcv-full>=1.5.0, \<1.8.0mmcls>=0.20.1, \<=1.0.0
0.29.1mmcv-full>=1.5.0, \<1.8.0mmcls>=0.20.1, \<=1.0.0
0.29.0mmcv-full>=1.5.0, \<1.7.0mmcls>=0.20.1, \<=1.0.0
0.28.0mmcv-full>=1.5.0, \<1.7.0mmcls>=0.20.1, \<=1.0.0
0.27.0mmcv-full>=1.5.0, \<1.7.0mmcls>=0.20.1, \<=1.0.0
0.26.0mmcv-full>=1.5.0, \<=1.6.0mmcls>=0.20.1, \<=1.0.0
0.25.0mmcv-full>=1.5.0, \<=1.6.0mmcls>=0.20.1, \<=1.0.0
0.24.1mmcv-full>=1.4.4, \<=1.6.0mmcls>=0.20.1, \<=1.0.0
0.23.0mmcv-full>=1.4.4, \<=1.6.0mmcls>=0.20.1, \<=1.0.0
0.22.0mmcv-full>=1.4.4, \<=1.6.0mmcls>=0.20.1, \<=1.0.0
0.21.1mmcv-full>=1.4.4, \<=1.6.0Not required
0.20.2mmcv-full>=1.3.13, \<=1.6.0Not required
0.19.0mmcv-full>=1.3.13, \<1.3.17Not required
0.18.0mmcv-full>=1.3.13, \<1.3.17Not required
0.17.0mmcv-full>=1.3.7, \<1.3.17Not required
0.16.0mmcv-full>=1.3.7, \<1.3.17Not required
0.15.0mmcv-full>=1.3.7, \<1.3.17Not required
0.14.1mmcv-full>=1.3.7, \<1.3.17Not required
0.14.0mmcv-full>=1.3.1, \<1.3.2Not required
0.13.0mmcv-full>=1.3.1, \<1.3.2Not required
0.12.0mmcv-full>=1.1.4, \<1.3.2Not required
0.11.0mmcv-full>=1.1.4, \<1.3.0Not required
0.10.0mmcv-full>=1.1.4, \<1.3.0Not required
0.9.0mmcv-full>=1.1.4, \<1.3.0Not required
0.8.0mmcv-full>=1.1.4, \<1.2.0Not required
0.7.0mmcv-full>=1.1.2, \<1.2.0Not required
0.6.0mmcv-full>=1.1.2, \<1.2.0Not required

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值