这篇文章主要记录py-faster-rcnn的编译及测试，是实战案例的前期准备。想动手训练自己的数据集可以参考下一篇文章Caffe经典模型--faster-rcnn目标检测实战案例（二）（训练kitti数据集）
在编译py-faster-rcnn之前，首先要确保机器上已经安装后caffe，如果还没有安装好caffe，可以参考Centos下的Caffe编译安装简易手册
下面正式开始py-faster-rcnn的编译和安装
第一步：下载源码
在命令行执行下载源代码：git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git
注意：确保要有--recursive ，这个会确保将faster-rcnn下的caffe-fast-rcnn一同下载
如果没有下载到caffe-faster-rcnn，则需要手动去下载，执行命令：git submodule update --init --recursive
如果，没有git命令，则使用命令：yum -y install git 安装git
第二步：编译lib目录
1、编译lib目录（带GPU时）
先确定当前GPU的计算能力，修改py-faster-rcnn/lib/setup.py文件（按照如下方式修改）：
执行编译命令：
$>cd py-faster-rcnn/lib
$>make
2、编译lib目录（无GPU时）
（a）首先按照如下方式修改py-faster-rcnn/lib/setup.py文件（取消使用GPU的配置）
将文件中58行的CUDA=locate_cuda()注释掉
将125行开始的含有nms.gpu_nms的Extension部分也注释掉（也就是将如下内容全部注释）
（b）在/py-faster-rcnn/lib/fast_rcnn/config.py文件中取消GPU的配置
在该文件的第205行的__C.USE_GPU_NMS = True中的True改为False，如下所示：
（c）在py-faster-rcnn/lib/fast_rcnn/nms_wrapper.py文件中取消GPU的配置
将该文件的第9行的from nms.gpu_nms import gpu_nms注释掉，如下所示：
注意：如果没有GPU，直接编译将会报错，显示没有CUDA的相关信息
第三步：编译FasterRCNN
1、配置caffe-fast-rcnn的Makefile.config
将caffe-fast-rcnn目录下的Makefile.config.example 复制一份到Makefile.config，然后编辑Makefile.config
修改的地方有如下几处：
a）取消 WITH_PYTHON_LAYER := 1 这一行的注释.
b）如果有GPU的话，将 USE_CUDNN := 1 这一行的注释也取消
如下是我的Makefile.config文件的内容：
## 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
# 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
# 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_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 := open
# 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
BLAS_INCLUDE := /usr/include/openblas
# 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/lib64/python2.7/site-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location, sometimes it's in root.
# ANACONDA_HOME := $(HOME)/anaconda
# 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 python3.6m
#PYTHON_INCLUDE := /usr/include/python3.6m \
# /usr/local/lib64/python3.6/site-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 ?= @
2、编译fast-rcnn
在caffe-fast-rcnn目录下执行如下命令：
$>make all -j8 && make pycaffe
第四步：下载预训练的模型探测器
1、下载模型压缩包
在py-faster-rcnn/data目录下执行如下命令去下载模型的压缩包
$>./scripts/fetch_faster_rcnn_models.sh
下载完后会在py-faster-rcnn/data目录下得到faster_rcnn_models.tgz这个压缩文件
2、解压模型压缩包的到模型文件
执行如下命令解压faster_rcnn_models.tgz文件：
$>tar -zxvf faster_rcnn_models.tgz
解压后得到VGG16_faster_rcnn_final.caffemodel和ZF_faster_rcnn_final.caffemodel两个模型文件
这两个模型是使用VOC2007数据集训练后得到的
第五步：运行图片探测---执行Demo
在执行demo之前首先将探测的图片放到py-faster-rcnn/data/demo目录下
在py-faster-rcnn目录下执行如下命令：(默认使用GPU，如果是cpu，需要在后面添加 --cpu )
$>./tool/demo.py