c++调用caffe ssd_CentOS安装caffe-ssd算法

CentOS安装caffe

1. 下载源码

su guxiaotu # 切换到用户guxiaotu

# 切换到当前用户主目录下

cd $HOME

sudo yum install -y git # 安装git

git clone https://github.com/weiliu89/caffe.git caffe-ssd #下载代码并且重命名为caff-ssd

# 进入caffe-ssd源代码目录

cd caffe-ssd

# checkout出ssd算法源码

git checkout ssd

2. 设置环境变量

# 设置环境变量

echo 'export CAFFE_ROOT=$HOME/caffe-ssd' >> ~/.bashrc# 配置$CAFFE_ROOT

# 将/usr/lib/python2.7/dist-packages和$CAFFE_ROOT/python追加到$PYTHONPATH.

echo 'export PYTHONPATH=$PYTHONPATH:/usr/lib/python2.7/dist-packages:$CAFFE_ROOT/python'>>~/.bashrc

# 将$CAFFE_ROOT/build/tool命令工具追加到$PATH中

echo 'export PATH=$PATH:$CAFFE_ROOT/build/tool' >> ~/.bashrc

# 使环境变量生效

source ~/.bashrc

3. 安装第三方库

sudo yum install -y epel-release \

wget \

zip \

gcc-c++ \

cmake \

protobuf-devel \

leveldb-devel \

snappy-devel \

boost-devel \

hdf5-devel \

gflags-devel \

glog-devel \

lmdb-devel \

openblas-devel \

python-devel \

liblas-devel \

atlas-devel\

libopenblas-dev \

python-matplotlib \

numpy

# 清除缓存包

sudo yum clean all

sudo rm -rf /var/cache/yum

centos中opencv-devel默认为2.4.5，会提示"warning: GStreamer: unable to query position of stream (/builddir/build/BUILD/opencv-2.4.5/modules/highgui/src/cap_gstreamer.cpp:660)"，国外论坛2013年讨论过，源代码有问题。所以选择手动安装opencv

sudo wget -O /opt/opencv2.4.13.6.zip https://github.com/opencv/opencv/archive/2.4.13.6.zip

sudo unzip /opt/opencv2.4.13.6.zip -d /opt

cd /opt/opencv-2.4.13.6/ && sudo mkdir release/ && cd release

sudo cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local ..

sudo make && sudo make install

# glog

sudo wget https://storage.googleapis.com/google-code-archive-downloads/v2/code.google.com/google-glog/glog-0.3.3.tar.gz -P /opt

tar zxvf /opt/glog-0.3.3.tar.gz -C /opt

cd /opt/glog-0.3.3

sudo ./configure

sudo make && sudo make install

# gflags

sudo wget https://codeload.github.com/gflags/gflags/zip/v2.0 -O /opt/gflags-2.0.zip

sudo unzip /opt/gflags-2.0.zip -d /opt

cd /opt/gflags-2.0

sudo ./configure

sudo make && sudo make install

# lmdb

git clone https://github.com/LMDB/lmdb /opt/lmdb

cd /opt/lmdb/libraries/liblmdb

sudo make && sudo make instal

提醒：

每次重新make编译源代码前，需要进入之前源代码包make clean清除下编译

Ø 出现问题:如果gflags高于2.0版本会出现以下问题

/usr/bin/ld: /usr/local/lib/libgflags.a(gflags.cc.o): relocation R_X86_64_32S against `.rodata' can not be used when making a shared object; recompile with -fPIC /usr/local/lib/: could not read symbols: Bad value collect2: ld returned 1 exit status make: [libglog.la] Error 1

Ø 分析原因：

Glog Need to be compiled into shared library.

4. 安装Python以及第三方库

sudo yum install -y python-pip

sudo pip install --upgrade pip # 升级pip到10.0.1版本

# 临时设置阿里云的pip源加快Python库的下载速度

sudo pip install -i https://mirrors.aliyun.com/pypi/simple ansible

# 安装Python第三方库

pip install Cython \

numpy \

scipy \

scikit-image \

matplotlib==1.5.3 \

ipython \

h5py \

leveldb \

networkx \

nose \

pandas \

python-dateutil \

protobuf \

python-gflags \

pyyaml \

Pillow \

mkl \

pyldap \

six --user

# 也可以按照$CAFFE_ROOT/python/requirements.txt中指定具体版本安装

pip install Cython==0.19.2 \

numpy==1.7.1 \

scipy==0.13.2 \

scikit-image==0.9.3 \

matplotlib==1.3.1 \

ipython==3.0.0 \

h5py==2.2.0 \

leveldb==0.191 \

networkx==1.8.1 \

nose==1.3.0 \

pandas==0.12.0 \

python-dateutil==2.6.0 \

protobuf==2.5.0 \

python-gflags==2.0 \

pyyaml==3.10 \

Pillow==2.3.0 \

six==1.1.0 --user

注意

matplotlib==1.5.3，1.5.3是当前1.0版本中最高版本，超过版本2.0.0之后，会提示“ImportError: cannot import name cbook”

5. 编译caffe环境

# 设置行号

echo 'set number' >> /etc/vimrc

# 进入caffe-ssd目录

cd $CAFFE_ROOT

cp Makefile.config.example Makefile.config

sudo vim Makefile.config

# 修改以下内容

8 CPU_ONLY := 1# 第8行，将前面#取消，启用只使用CPU模式

89 WITH_PYTHON_LAYER := 1 # 第89行，取消注释表示使用Python编写layer

# 第91~92行后面追加配置hdf5路径

91 INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial

92 LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib/usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial

# 编译caffe

make all

# 编译pycaffe，前提确保$CAFFE_ROOT/python添加到环境变量PYTHONPATH中(详细请看2. 设置环境变量)

make pycaffe

make test

# 可选

make runtest -j8

Ø 出现问题:

./include/caffe/util/cudnn.hpp:8:34:致命错误：caffe/proto/caffe.pb.h：没有那个文件或目录

Ø 分析原因：

应该是版本比较低。

pip install protobuf --upgrade -i http://pypi.douban.com/simple --trusted-host pypi.douban.com --user

pip install pillow --upgrade -i http://pypi.douban.com/simple --trusted-host pypi.douban.com --user

6. 准备模型以及数据集

6.1下载作者训练的模型数据，存放在$CAFFE_ROOT/models/VGGNet/

# 如果使用作者已经训练好的模型数据，请下载到$CAFFE_ROOT/model

sudo wget -P $CAFFE_ROOT/model http://www.cs.unc.edu/%7Ewliu/projects/SSD/models_VGGNet_VOC0712_SSD_300x300.tar.gz

# 解压到制定目录

tar -zxvf $CAFFE_ROOT/model/models_VGGNet_VOC0712_SSD_300x300.tar.gz -C $CAFFE_ROOT/model

6.2 下载VOC2007 and VOC2012数据集， 存放在默认目录$HOME/data/中

# 用户主目录下创建data目录后进入

mkdir $HOME/data

# 下载数据集

sudo wget -P $HOME/data http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar

sudo wget -P $HOME/data http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar

sudo wget -P $HOME/data http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar

# 解压到指定目录(必须按照以下顺序解压，不能颠倒)

tar -xvf $HOME/data/VOCtrainval_11-May-2012.tar -C $HOME/data

tar -xvf $HOME/data/VOCtrainval_06-Nov-2007.tar -C $HOME/data

tar -xvf $HOME/data/VOCtest_06-Nov-2007.tar -C $HOME/data

注意：三个压缩文件解压顺序一定不能打乱

6.3 创建LMDB文件

cd $CAFFE_ROOT # 必须保证在$CAFFE_ROOT中执行

sudo vim /etc/ld.so.conf.d/usr-libs.conf

# 添加以下内容

/usr/local/lib

# 在data/VOC0712/中创建trainval.txt, test.txt, and test_name_size.txt

./data/VOC0712/create_list.sh

# You can modify the parameters in create_data.sh if needed.

# It will create lmdb files for trainval and test with encoded original image:

# - $HOME/data/VOCdevkit/VOC0712/lmdb/VOC0712_trainval_lmdb

# - $HOME/data/VOCdevkit/VOC0712/lmdb/VOC0712_test_lmdb

# and make soft links at examples/VOC0712/

sudo vim data/VOC0712/create_data.sh

# 修改一下以下值

root_dir=$CAFFE_ROOT

# 执行sh脚本生成lmdb文件

./data/VOC0712/create_data.sh

注意：如果提示缺少某个model，说明缺少对应Python第三方库或者版本过低，使用sudo pip install --upgrade 具体包名安装，也可以制定具体版本安装

提示缺少sci无法使用pip install -U命令安装scikit-image，提示“Cannot uninstall 'pyparsing'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.”

# 由于其他库以来pyparsing，所以选择忽略它

pip install scikit-image --ignore-installed pyparsing --user

Ø 出现问题:

error while loading shared libraries: libgflags.so.2: cannot open shared object file: No such file or directory

Ø 分析原因：

原因是程序没有找到相应的依赖库，解决方法：

将所有的用户需要用到的库放到/usr/loca/lib；

在/etc/ld.so.conf.d/目录下新建文件usr-libs.conf，内容是：/usr/local/lib

sudo ldconfig

7. 训练/计算

7.1 训练模型

# It will create model definition files and save snapshot models in:

# - $CAFFE_ROOT/models/VGGNet/VOC0712/SSD_300x300/

# and job file, log file, and the python script in:

# - $CAFFE_ROOT/jobs/VGGNet/VOC0712/SSD_300x300/

# and save temporary evaluation results in:

# - $HOME/data/VOCdevkit/results/VOC2007/SSD_300x300/

# It should reach 77.* mAP at 120k iterations.

python examples/ssd/ssd_pascal.py

7.2 图片数据集上测试

# If you would like to test a model you trained, you can do:

python examples/ssd/score_ssd_pascal.py

7.3 视频数据测试$CAFFE_ROOT/examples/videos

cd $CAFFE_ROOT

# 测试示例视频

sudo vim $CAFFE_ROOT/examples/ssd/ssd_pascal_video.py

# 第99~100行修改模式为CPU，P.Solver.GPU修改为P.Solver.CPU

99 # Use GPU or CPU

100 solver_mode = P.Solver.CPU

# 第77~76行修改视频文件路径$CAFFE_ROOT/examples/videos

75 # The video file path

76 video_file = "examples/videos/ILSVRC2015_train_00755001.mp4"

7.4 摄像头测试

# 摄像头测试

sudo vim $CAFFE_ROOT/examples/ssd/ssd_pascal_webcam.py

# 第100~101行修改模式为CPU，P.Solver.GPU修改为P.Solver.CPU

99 # Use GPU or CPU

102 solver_mode = P.Solver.CPU

# If you would like to attach a webcam to a model you trained, you can do:

python examples/ssd/ssd_pascal_webcam.py