ubuntu14.04、CPU的py-faster-rcnn安装步骤

py-faster-rcnn的CPU安装步骤：

(1)安装cython和easydict：
sudo pip install cython  
sudo pip install easydict   
(2)下载项目：
git clone --recursive  https://github.com/rbgirshick/py-faster-rcnn.git  
(3)编译cython：
到/py-faster-rcnn/lib/目录下修改setup.py文件，然后make，修改如下
#CUDA = locate_cuda()  
#self.set_executable('compiler_so', CUDA['nvcc'])  
#Extension('nms.gpu_nms',  

#['nms/nms_kernel.cu', 'nms/gpu_nms.pyx'],  

 

#library_dirs=[CUDA['lib64']],  

#libraries=['cudart'],  
        #language='c++',  
        #runtime_library_dirs=[CUDA['lib64']],  
# this syntax is specific to this build system  
# we're only going to use certain compiler args with nvcc and not with  
# gcc the implementation of this trick is in customize_compiler() below  
#extra_compile_args={'gcc': ["-Wno-unused-function"],  

 

#                    'nvcc': ['-arch=sm_35',  

#                             '--ptxas-options=-v',  

#                             '-c',  
#                             '--compiler-options',  
#                             "'-fPIC'"]},  
#include_dirs = [numpy_include, CUDA['include']]  
#), 
(4)修改相关文件：
a、到/py-faster-rcnn/caffe-fast-rcnn/目录下，修改Makefile.config文件，为了make指令的执行，将 Makefile.config.example文件名重命名修改为Makefile.config。
$ cd ~/caffe
$ cp Makefile.config.example Makefile.config
     打开Makefile.config文件：去掉CPU_ONLY:= 1的注释
     由于是仅CPU安装，注释掉CUDA有关的行：  
#CUDA_DIR := /usr/local/cuda  
#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_50,code=compute_50  
   去掉注释WITH_PYTHON_LAYER := 1  
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial  
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/i386-linux-gnu/hdf5/serial /usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial  
#TEST_GPUID := 0  
b、修改caffe/examples/cpp_classification/classification.cpp文件，加入：
#include <opencv2/imgproc/types_c.h>
#include <opencv2/objdetect/objdetect_c.h>
c、Makefile 修改： 
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5 lmdb opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs
d、修改CMakeLists.txt文件（OFF改成ON）：
caffe_option(CPU_ONLY  "Build Caffe without CUDA support" ON) # TODO: rename to USE_CUDA  
(5)编译caffe：
cd ~/py-faster-rcnn/caffe-fast-rcnn  
make -j8&& make pycaffe  
(6)测试demo：
cd ~/py-faster-rcnn  
./data/scripts/fetch_faster_rcnn_models.sh  
(7)然后修改一些文件：
a、修改/py-faster-rcnn/lib/fast_rcnn/config.py文件（True改成False）
# Use GPU implementation of non-maximum suppression
__C.USE_GPU_NMS = False
b、将/py-faster-rcnn/tools/test_net.py和 /py-faster-rcnn/tools/train_net.py的caffe.set_mode_gpu()修改为caffe.set_mode_cpu().
c、修改/py-faster-rcnn/lib/fast_rcnn/nms_wrapper.py文件（注释该引用，并将False改成True）
#from nms.gpu_nms import gpu_nms
def nms(dets, thresh, force_cpu=True):
(8)最后，运行demo：
cd ~/py-faster-rcnn  
./tools/demo.py --cpu