请参照我的第二次安装记录：

https://blog.csdn.net/weixin_38635229/article/details/88410695

---

Openpose emmmmm 一言难尽鸭

我大概用了5天，试了两台服务器，重装了三次ubuntu，终于弄出来了。

---

关键点：

1、protobuf版本。openpose与当前Anaconda中自带的protobuf版本不兼容，需要2.6.1版本的protobuf。（CMU官方github上说不要安装Anaconda，其实是可以的，像hdf5等等的依赖库用Anaconda就可以一起安装了，免去了自己安装的麻烦）

2、caffe版本。OpenPose贡献人员还没解决因最新版Caffe增加Layer导致不兼容的问题，所以需要使用commit为f019d0dfe86f49d1140961f8c7dec22130c83154的Caffe。（所以我们不能用openpose的脚本自动下载caffe，之前我用官方的方法直接配，全部编译通过了，但是运行的时候报错。我们要通过Anaconda下载指定版本的caffe来编译，在编译openpose时链接之前我们自己编译好的caffe）

---

首先感谢(reference)(前两个链接是官方的，后三个链接直接帮助我安装成功)：

https://github.com/CMU-Perceptual-Computing-Lab/openpose

https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/installation.md

https://blog.csdn.net/chenzhenyu123456/article/details/83188830 

https://blog.csdn.net/chenzhenyu123456/article/details/84205974

https://blog.csdn.net/chenzhenyu123456/article/details/84259851

 

那么我们开始吧~

首先说我的环境，我在实验室的一台冷宫服务器上开始了作死之路，先问了一下大伙有没有在上边存有用的东西，答曰没有，我就可以放飞自我了。按照安装顺序来：

系统：Linux_ubuntu_16.04

显卡驱动：410.78（强烈建议大家不要用cuda装驱动，失败概率极高。自己去nvidia官网下一个对应显卡型号的驱动，这样安装基本百发百中）

cuda：9.0（我的bashrc文件关于cuda-9.0的内容，大家可以加上）

export CUDA_HOME=/usr/local/cuda-9.0
export LD_LIBRARY_PATH=/usr/local/cuda-9.0/lib64:$LD_LIBRARY_PATH
export PATH=/usr/local/cuda-9.0/bin:$PATH

cudnn：7.1.4

---------------<以上这些的安装方法我就不多说了，我之前也写过类似的，网上也能搜到一大堆>----------------

好了，这些都完成之后，开始关键的部分。

1.Miniconda

在此链接https://mirrors.tuna.tsinghua.edu.cn/anaconda/miniconda/下载安装包，我用的py 3.6版本。

安装Miniconda：找到下载的.sh文件，命令行输入：

bash ${PACKAGE_NAME}.sh

在安装过程中，注意将PATH加入./bashrc。在安装的时候执行到这一步，输入yes即可。
安装完成后，重启。

加入清华镜像(这一步自己查具体怎么做，打开一个文件，把里边的内容用下边的(或者查到的)内容替换掉就可以)：

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

 

2.caffe编译

借鉴后三条链接的思路，因为担心Caffe会影响Miniconda3的其他环境，这里为Caffe单独创建一个沙盒环境。我的Python版本是2.7.15。

创建Caffe沙盒（我使用Protobuf2.6.1的原因是OpenPose是不兼容Miniconda3自带的Protobuf Compiler的），执行：

conda create --name caffe-py2.7.15-pr2.6.1 python=2.7.15

进入miniconda3/envs/caffe-py2.7.15-pr2.6.1, 下载Caffe，（这里不需要沙盒环境）执行以下命令：

cd ~/miniconda3/envs/caffe-py2.7.15-pr2.6.1/
git clone https://github.com/BVLC/caffe.git

今天是2018.12.26，CMU贡献人员还没解决因最新版Caffe增加Layer导致与OpenPose不兼容的问题，所以需要caffe的commit为f019d0dfe86f49d1140961f8c7dec22130c83154。（这里不需要沙盒环境）执行：

cd caffe/
git checkout f019d0dfe86f49d1140961f8c7dec22130c83154

安装依赖（有的东西是确实有用的，有的没用，总之装了不会犯错）（这里不需要沙盒环境）： 

sudo apt-get update
sudo apt-get upgrade
sudo apt-get install -y build-essential cmake git pkg-config
sudo apt-get install -y libprotobuf-dev libleveldb-dev libsnappy-dev protobuf-compiler
sudo apt-get install -y libatlas-base-dev 
sudo apt-get install -y --no-install-recommends libboost-all-dev
sudo apt-get install -y libgflags-dev libgoogle-glog-dev liblmdb-dev
sudo apt-get install -y libopencv-dev libhdf5-serial-dev
sudo apt-get install -y build-essential cmake git libgtk2.0-dev pkg-config python-dev python-numpy libdc1394-22 libdc1394-22-dev libjpeg-dev libpng12-dev libtiff5-dev libjasper-dev libavcodec-dev libavformat-dev libswscale-dev libxine2-dev libgstreamer0.10-dev libgstreamer-plugins-base0.10-dev libv4l-dev libtbb-dev libqt4-dev libfaac-dev libmp3lame-dev libopencore-amrnb-dev libopencore-amrwb-dev libtheora-dev libvorbis-dev libxvidcore-dev x264 v4l-utils unzip
conda install scikit-image scikit-learn pandas
pip install jupyter
pip install easydict
pip install lxml
pip install seaborn
pip install tqdm

 激活caffe环境并安装opencv（这里需要沙盒环境）：

source activate caffe-py2.7.15-pr2.6.1
conda install opencv

Protobuf版本选择：（请注意这一步非常非常重要！！！）
编译Caffe时Protobuf版本的选择也是有讲究的（如果你需要其他特定版本的库，具体做法和这个类似）。拿我的库举个例子：Miniconda3的Protobuf版本是3.5.2，而通过apt-get 安装的Protobuf版本是2.6.1。
我们这里使用自己的protobuf版本2.6.1，首先你要保证当前的沙盒环境中没有libprotobuf和protobuf这两个库（激活当前的caffe-py2.7.15-pr2.6.1，然后conda list查看是否有这两个库，如果有的话需要删掉），然后注释掉Miniconda3在bashrc的环境变量，接下来就可以直接使用系统的库去编译Caffe了。

执行：

vim ～/.bashrc

注释掉Miniconda3的环境变量之后，执行：

source ~/.bashrc

修改完毕之后，重启终端进入Caffe目

cd ~/miniconda3/envs/caffe-py2.7.15-pr2.6.1/caffe/

修改编译文件，执行：

cp Makefile.config.example Makefile.config

gedit Makefile.config

我的Makefile.config如下：

## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers
# USE_OPENCV := 0
# USE_LEVELDB := 0
# USE_LMDB := 0
# This code is taken from https://github.com/sh1r0/caffe-android-lib
# USE_HDF5 := 0

# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
#    You should not set this flag if you will be reading LMDBs with any
#    possibility of simultaneous read and write
# ALLOW_LMDB_NOLOCK := 1

# Uncomment if you're using OpenCV 3
OPENCV_VERSION := 3

# To customize your choice of compiler, uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda-9.0
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0, comment the *_50 through *_61 lines for compatibility.
# For CUDA < 8.0, comment the *_60 and *_61 lines for compatibility.
# For CUDA >= 9.0, comment the *_20 and *_21 lines for compatibility.
CUDA_ARCH := -gencode arch=compute_20,code=sm_20 \
        -gencode arch=compute_20,code=sm_21 \
        -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_52,code=sm_52 \
        -gencode arch=compute_60,code=sm_60 \
        -gencode arch=compute_61,code=sm_61 \
        -gencode arch=compute_61,code=compute_61

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := atlas
# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
# Leave commented to accept the defaults for your choice of BLAS
# (which should work)!
# BLAS_INCLUDE := /path/to/your/blas
# BLAS_LIB := /path/to/your/blas

# Homebrew puts openblas in a directory that is not on the standard search path
# BLAS_INCLUDE := $(shell brew --prefix openblas)/include
# BLAS_LIB := $(shell brew --prefix openblas)/lib

# This is required only if you will compile the matlab interface.
# MATLAB directory should contain the mex binary in /bin.
# MATLAB_DIR := /usr/local
# MATLAB_DIR := /Applications/MATLAB_R2012b.app

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
# PYTHON_INCLUDE := /usr/include/python2.7 \
        # /usr/lib/python2.7/dist-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location, sometimes it's in root.
ANACONDA_HOME := $(HOME)/miniconda3/envs/caffe-py2.7.15-pr2.6.1
PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
        $(ANACONDA_HOME)/include/python2.7 \
        $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include

# Uncomment to use Python 3 (default is Python 2)
# PYTHON_LIBRARIES := boost_python3 python3.5m
# PYTHON_INCLUDE := /usr/include/python3.5m \
#                 /usr/lib/python3.5/dist-packages/numpy/core/include

# We need to be able to find libpythonX.X.so or .dylib.
# PYTHON_LIB := /usr/lib
PYTHON_LIB := $(ANACONDA_HOME)/lib

# Homebrew installs numpy in a non standard path (keg only)
# PYTHON_INCLUDE += $(dir $(shell python -c 'import numpy.core; print(numpy.core.__file__)'))/include
# PYTHON_LIB += $(shell brew --prefix numpy)/lib

# Uncomment to support layers written in Python (will link against Python libs)
WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include 
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
# INCLUDE_DIRS += $(shell brew --prefix)/include
# LIBRARY_DIRS += $(shell brew --prefix)/lib

# NCCL acceleration switch (uncomment to build with NCCL)
# https://github.com/NVIDIA/nccl (last tested version: v1.2.3-1+cuda8.0)
# USE_NCCL := 1

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

# N.B. both build and distribute dirs are cleared on `make clean`
BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @

编译Caffe,执行：

mkdir build
cd build/
cmake ..

这一步如果出现以下Warning信息：

Make Warning (dev) in src/caffe/CMakeLists.txt:
Policy CMP0022 is not set: INTERFACE_LINK_LIBRARIES defines the link
interface.  Run "cmake --help-policy CMP0022" for policy details.  Use the
cmake_policy command to set the policy and suppress this warning.

在CMakeLists.txt第一行下边加入以下内容，再重新编译即可：

if(POLICY CMP0022)
  cmake_policy(SET CMP0022 NEW)
endif()

这是我的依赖信息，可以看到我使用的是Protobuf2.6.1。如果这一步出错，问题很有可能是你少装了一些库，具体错误信息会有提示，比如import XXX的时候出错，这时候你再装一下这个库就行了。

Dependencies:
--   BLAS              :   Yes (Atlas)
--   Boost             :   Yes (ver. 1.58)
--   glog              :   Yes
--   gflags            :   Yes
--   protobuf          :   Yes (ver. 2.6.1)
--   lmdb              :   Yes (ver. 0.9.17)
--   LevelDB           :   Yes (ver. 1.18)
--   Snappy            :   Yes (ver. 1.1.3)
--   OpenCV            :   Yes (ver. 2.4.9.1)
--   CUDA              :   Yes (ver. 9.0)
-- 
-- NVIDIA CUDA:
--   Target GPU(s)     :   Auto
--   GPU arch(s)       :   sm_61
--   cuDNN             :   Yes (ver. 7.1.4)
-- 
-- Python:
--   Interpreter       :   /usr/bin/python2.7 (ver. 2.7.12)
--   Libraries         :   /usr/lib/x86_64-linux-gnu/libpython2.7.so (ver 2.7.12)
--   NumPy             :   /usr/lib/python2.7/dist-packages/numpy/core/include (ver 1.11.0)

make，执行：

make all -j
make install -j
make runtest -j

 加入环境变量，打开bashrc，执行：

vim ~/.bashrc

加入环境变量
export PYTHONPATH=/home/czy/miniconda3/envs/caffe-py2.7.15-pr2.6.1/caffe/python:$PYTHONPATH
同时把Miniconda3的环境变量取消注释以及将特定版本库的环境变量注释掉

保存退出，执行：

source ~/.bashrc

重新开启终端, 进入caffe沙盒环境，执行：

source activate caffe-py2.7.15-pr2.6.1

安装一些依赖库（有些装不上没啥关系，往下继续就好了，之后如果报错少了什么再装什么）

conda install cython scikit-image protobuf scikit-learn ipython pandas jupyter tqdm lxml pillow

3.openpose安装

下载openpose到本地，执行：

git clone https://github.com/CMU-Perceptual-Computing-Lab/openpose

安装cmake GUI，执行：

sudo apt-get install cmake-qt-gui

配置编译参数，打开cmake-gui程序，执行：

cmake-gui

选择源程序和编译路径（以下图片均来自后三条链接）：

 点击Configure，如果没有build文件夹，会提醒并为你自动创建：

接下来链接Caffe，创建build文件夹之后，选择Unix Makefiles，点击Finish

当然初次Configure会报错，因为Caffe版本不匹配

注意：这里等待程序把model下载完毕即可，有时它的网站会出问题导致下载很慢。如果长时间没响应，那么先stop，把openpose/models/目录下刚才未成功下载的模型删掉，等一会再重新Configure。

模型下完之后，会提示如下错误：

我们需要链接自己的Caffe库，所以要对BUILD_CAFFE，Caffe_INCLUDE_DIRS，Caffe_LIBS进行修改，然后选择需要下载的模型（推荐DOWNLOAD模型全选，这里只是为了单纯验证，所以没有全选）

做完上述修改之后，再一次点击Configure，然后点击Generator

看到Configure done和Generator done就说明这一步成功了，先不要退出cmake-gui，等验证成功再退出。

编译OpenPose，执行：

cd ~/deep-learning/openpose/build/
make -j`nproc`

验证，首先切换到主目录：

cd ..

Running on Video，执行：

./build/examples/openpose/openpose.bin --video examples/media/video.avi

运行结果，成功了：