py-faster-rcnn+ubuntu16.04+cuda8.0+py2.7安装+anaconda3

一、环境准备

装cuda9.0时make runtest会出现，Check failed: status == CUBLAS_STATUS_SUCCESS (13 vs. 0) CUBLAS_STATUS_EXECUTION_FAILED

改装成cuda8.0之后一切OK，目测是cuda9.0和显卡驱动的兼容问题影响的。

1、anaconda3创建虚拟环境激活环境create -n py2.7 python=2.7

2、克隆py-faster-rcnn源码，参数递归克隆

git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git

二、依赖安装

进入到caffe-faster-rcnn目录执行pip install -r requirement.s.txt

sudo apt-get install python-numpy python-scipy python-matplotlib python-sklearn python-skimage  python-h5py python-protobuf python-leveldb python-networkx python-nose python-pandas python-gflags Cython ipython python-yaml 

sudo pip install easydict

安装opencv及其组件

pip install opencv-python

pip install opencv-contrib-python

安装openblas（BLAS是为caffe打造的基于c++的矩阵运算库，类似numpy）

git clone https://github.com/xianyi/OpenBLAS.git

cd OpenBLAS

make -j8

make install

#设置环境变量

export LD_LIBRARY_PATH=/opt/OpenBLAS/lib/:$LD_LIBRARY_PATH

condalist截图：

pip list结

三、修改Makefile.configue 编译文件取消注释并修改
USE_CUDNN := 1
# OPENCV_VERSION := 3   如果使用的是opencv3就取消注释，否则不。

BLAS := open
BLAS_INCLUDE := /opt/OpenBLAS/include
BLAS_LIB := /opt/OpenBLAS/lib

#cuda8.0要求把_20,_21删除，加上

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  \

WITH_PYTHON_LAYER := 1   #开启python

替换

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

四、修改Makefile

#LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5    替换为
LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial

将：NVCCFLAGS +=-ccbin=$(CXX) -Xcompiler-fPIC $(COMMON_FLAGS)
替换为：
NVCCFLAGS += -D_FORCE_INLINES -ccbin=$(CXX) -Xcompiler -fPIC $(COMMON_FLAGS)

蓝色的这一句好像改不改都不影响，建议先不改，后面报错了再改吧。
 

五、Faster R-CNN 并不支持CUDNN5.1以上， 所以需要合并Caffe来支持。

替换py-faster-rcnn中/include/caffe/layers/cudnn_*

/src/caffe/layers/cudnn_*

/include/caffe/utils/cudnn.hpp

以上三个必换，还有就是网上说有换src/caffe/utils/cudnn_*的，不换好像也不影响，反正能不换就不换。

六、编译

修改python_layer.hp

版本合并后，打开caffe-fast-rcnn/include/caffe/layers/python_layer.hp，self_.attr("phase") = static_cast<int>(this->phase_);这一行(line29)删除（如果有的话就删除，没有就不修改，可能会没有）

cd $FRCN_ROOT/lib （或者cd py-faster-rcnn/lib）  make  #编译Cython
cd py-faster-rcnn

make -j8

make test

make runtest

make pycaffe

七、报错：CXX .build_release/src/caffe/proto/caffe.pb.cc
AR -o .build_release/lib/libcaffe.a
LD -o .build_release/lib/libcaffe.so.1.0.0-rc3
/usr/bin/ld: 找不到 -lopencv_imgcodecs
collect2: error: ld returned 1 exit status
Makefile:554: recipe for target '.build_release/lib/libcaffe.so.1.0.0-rc3' failed
make: *** [.build_release/lib/libcaffe.so.1.0.0-rc3] Error 1

解决办法：修改Makefile   ：LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs

报错：src/caffe/test/test_smooth_L1_loss_layer.cpp:11:35: fatal error: caffe/vision_layers.hpp: 没有那个文件或目录
compilation terminated.
Makefile:564: recipe for target '.build_release/src/caffe/test/test_smooth_L1_loss_layer.o' failed
make: *** [.build_release/src/caffe/test/test_smooth_L1_loss_layer.o] Error 1

解决办法：vim ~/py-faster-rcnn/caffe-fast-rcnn/src/caffe/tes/test_smooth_L1_loss_layer.cpp  屏蔽
//#include "caffe/vision_layers.hpp"