win10 mmdetection2.7

0.更换清华源
conda
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
conda config --set show_channel_urls yes
pip
在C:\Users\39314\pip 创建一个pip.ini，写入。
[global]
index-url = https://pypi.tuna.tsinghua.edu.cn/simple
[install]
trusted-host = https://pypi.tuna.tsinghua.edu.cn

1.创建虚拟环境
conda create -n open-mmlab python=3.7 -y
conda activate open-mmlab

2.安装vs2015

3.安装pytorch
pip install torch==1.6.0+cu101 torchvision==0.7.0+cu101 -f https://download.pytorch.org/whl/torch_stable.html

4.安装mvcc
pip install mmcv-full==1.1.5 -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.6.0/index.html

5.安装mmdetection2.6
下载2.6,解压后
pip install -r requirements.txt
python setup.py develop 
pip install opencv-python==4.2.0.34 


6.测试
python demo\webcam_demo.py configs\faster_rcnn\faster_rcnn_r50_fpn_1x_coco.py checkpoints\faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth

7.修改
G:\anaconda\envs\mmd27\Lib\site-packages\mmcv\runner\epoch_based_runner.py
172 shutil.copy(filepath,dst_file)