yolact部署到Docker中，需要單獨編譯DCNv2
cd external/DCNv2
python setup.py build develop
但是這個DCNv2的編譯需要依賴GPU，總是編不過。
失敗1：使用python:3.6鏡像
FROM python:3.6
...
WORKDIR ***/external/DCNv2
RUN python setup.py build develop
...
執行後編譯報錯，通過docker run進入到docker裏面依然編譯報錯：
No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
Traceback (most recent call last):
File "setup.py", line 64, in <module>
ext_modules=get_extensions(),
File "setup.py", line 41, in get_extensions
raise NotImplementedError('Cuda is not availabel')
NotImplementedError: Cuda is not availabel
原因分析：python:3.6鏡像未安裝cuda驅動
失敗2：改用pytorch/pytorch:1.2-cuda10.0-cudnn7-runtime鏡像
FROM pytorch/pytorch:1.2-cuda10.0-cudnn7-runtime
...
WORKDIR ***/external/DCNv2
RUN python setup.py build develop
...
無論是Dockerfile編譯，還是docker run進入到docker裏面編譯，依然報錯：
No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
Traceback (most recent call last):
File "setup.py", line 64, in <module>
ext_modules=get_extensions(),
File "setup.py", line 41, in get_extensions
raise NotImplementedError('Cuda is not availabel')
NotImplementedError: Cuda is not availabel
原因分析：torch.cuda.is_available() 顯示爲True，但是from torch.utils.cpp_extension import CUDA_HOME，CUDA_HOME爲NULL，看了一下/usr/local目錄下確實沒有cuda相關的目錄。
失敗3：改用pytorch/pytorch:1.2-cuda10.0-cudnn7-devel鏡像
FROM pytorch/pytorch:1.2-cuda10.0-cudnn7-devel
...
WORKDIR ***/external/DCNv2
RUN python setup.py build develop
...
中間出現過一個apt-get update失敗的問題：Failed to fetch https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/Packages.gz Hash Sum mismatch
解決方法：
...
# Update source
RUN sed -i s:/archive.ubuntu.com:/mirrors.tuna.tsinghua.edu.cn/ubuntu:g /etc/apt/sources.list
RUN cat /etc/apt/sources.list
RUN apt-get clean
RUN apt-get -y update --fix-missing --allow-unauthenticated
...
docker build跑起來，結果編譯依然報錯（吐血）：
No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
Traceback (most recent call last):
File "setup.py", line 64, in <module>
ext_modules=get_extensions(),
File "setup.py", line 41, in get_extensions
raise NotImplementedError('Cuda is not availabel')
NotImplementedError: Cuda is not availabel
但是通過docker run --gpus all -it ... /bin/bash進入到docker裏面，居然編譯成功了。
running build
running build_ext
running develop
running egg_info
writing DCNv2.egg-info/PKG-INFO
writing dependency_links to DCNv2.egg-info/dependency_links.txt
writing top-level names to DCNv2.egg-info/top_level.txt
reading manifest file 'DCNv2.egg-info/SOURCES.txt'
writing manifest file 'DCNv2.egg-info/SOURCES.txt'
running build_ext
copying build/lib.linux-x86_64-3.6/_ext.cpython-36m-x86_64-linux-gnu.so ->
Creating /opt/conda/lib/python3.6/site-packages/DCNv2.egg-link (link to .)
Adding DCNv2 0.1 to easy-install.pth file
Installed ***/external/DCNv2
Processing dependencies for DCNv2==0.1
Finished processing dependencies for DCNv2==0.1
原因分析：通過docker run進入到docker裏面編譯時，已通過--gpus選項爲docker指定了GPU，所以可以使用GPU並編譯成功。但在docker build執行Dockerfile時並未爲docker指定GPU，所以依然無法使用GPU。
終極方案：不在docker build時通過Dockerfile編譯，而是在ENDPOINT中執行編譯：
FROM pytorch/pytorch:1.2-cuda10.0-cudnn7-devel
...
ENTRYPOINT ["sh", "run.sh"]
在run.sh中編譯DCNv2：
cd external/DCNv2
python setup.py build develop
cd ../..
python ***.py