基于mmrotate旋转目标检测框架的训练

基本思想：需要检测带角度的目标。

前期因为配环境踩了很多坑，发现是mmdet和mmcv-full版本对应的问题

前言：

配置环境ubuntu20.04，GPU 3050RTX，mmrotate-0.3.2

一、搭建环境

拉取源码，因为前期踩了很多坑，没有拉取最新的，这里以0.3.2版本为例。

# 拉取源码
git clone https://github.com/open-mmlab/mmrotate/releases/tag/v0.3.2

cd mmrotate-0.3.2

# 创建conda环境
conda create -n mmrotate python=3.8

conda activate mmrotate

pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html

pip install mmcv-full==1.6.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html

pip install mmdet==2.25

pip install -r requirements/build.txt

pip install -v -e .

 在安装mmdet时候一定注意版本问题，要不后续运行将出现版本不匹配的报错问题。

AssertionError: MMCV==1.7.1 is used but incompatible. Please install mmcv>=2.0.0rc4, <2.1.0.

这里给出mmcv/mmmdet/mmdet3d版本对照表，参考此处 AssertionError: MMCV==1.7.1 is used but incompatible. Please install mmcv＞=2.0.0rc4, ＜2.1.0._MFT小白的博客-优快云博客

MMDetection3D version	MMDetection version	MMSegmentation version	MMCV、 version
master	mmdet>=2.24.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.5.2, <=1.7.0
v1.0.0rc4	mmdet>=2.24.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.5.2, <=1.7.0
v1.0.0rc3	mmdet>=2.24.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.4.8, <=1.6.0
v1.0.0rc2	mmdet>=2.24.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.4.8, <=1.6.0
v1.0.0rc1	mmdet>=2.19.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.4.8, <=1.5.0
v1.0.0rc0	mmdet>=2.19.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.3.17, <=1.5.0
0.18.1	mmdet>=2.19.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.3.17, <=1.5.0
0.18.0	mmdet>=2.19.0, <=3.0.0	mmseg>=0.20.0, <=1.0.0	mmcv-full>=1.3.17, <=1.5.0
0.17.3	mmdet>=2.14.0, <=3.0.0	mmseg>=0.14.1, <=1.0.0	mmcv-full>=1.3.8, <=1.4.0
0.17.2	mmdet>=2.14.0, <=3.0.0	mmseg>=0.14.1, <=1.0.0	mmcv-full>=1.3.8, <=1.4.0
0.17.1	mmdet>=2.14.0, <=3.0.0	mmseg>=0.14.1, <=1.0.0	mmcv-full>=1.3.8, <=1.4.0
0.17.0	mmdet>=2.14.0, <=3.0.0	mmseg>=0.14.1, <=1.0.0	mmcv-full>=1.3.8, <=1.4.0
0.16.0	mmdet>=2.14.0, <=3.0.0	mmseg>=0.14.1, <=1.0.0