记录自本人安装过程，环境建议：

• Linux or macOS (Windows is not currently officially supported)
• Python 3.6+
• PyTorch 1.3+
• CUDA 9.2+ (If you build PyTorch from source, CUDA 9.0 is also compatible)
• GCC 5+

1. torch & torchvision

我使用的是 torch 1.5.1 + torchvision 0.6.1

pip install torch==1.5.1 torchvision==0.6.1 [-i https://pypi.douban.com/simple]

https://pytorch.org/get-started/previous-versions/

2. mmcv

pip install mmcv-full

3. mmdetection

git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection

pip install -r requirements/build.txt
pip install -v -e .  # or "python setup.py develop"

4. test

下载数据

mkdir checkpoints
wget -c https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth \
      -O checkpoints/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth

此时查看文件目录树如下

> tree checkpoints
checkpoints
└── mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth

运行image_demo.py测试mmdet是否安装成功

python demo/image_demo.py demo/demo.jpg configs/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco.py checkpoints/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth 

若安装成功，会显示如下图像：

Some ERROR

libcudart.so.10.1: cannot open shared object file: No such file or directory

先卸载原有cudatoolkit：conda uninstall cudatoolkit

再安装10.1版本：conda install cudatoolkit=10.1