faster-rcnn 安装

faster-rcnn提出论文： 《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》

faster-rcnn 的算法详解可看这篇博文（清晰易懂，良心博文！）： http://blog.csdn.net/shenxiaolu1984/article/details/51152614

faster-rcnn Python版本源码地址：https://github.com/rbgirshick/py-faster-rcnn

这篇文章主要介绍搭建用faster-rcnn进行目标检测所需的环境。

1.电脑上已经有可运行caffe所需的环境

2.下载faster-rcnn python版本源码

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

3. 进入/py-faster-rcnn/lib 进行编译

 cd py-faster-rcnn/lib
 make

4.编译/py-faster-rcnn/caffe-fast-rcnn

 cd py-faster-rcnn/caffe-fast-rcnn

 cp Makefile.config.example Makefile.config

更改Makefile.config文件：

 # In your Makefile.config, make sure to have this line uncommented
 WITH_PYTHON_LAYER := 1
 # Unrelatedly, it's also recommended that you use CUDNN
 USE_CUDNN := 1

进行编译：

 make -j8 && make pycaffe

因为这个版本所用的cudnn为旧版本的，可能与新环境的cudnn不兼容，导致出现如下错误：

 In file included from ./include/caffe/util/cudnn.hpp:5:0,
                  from ./include/caffe/util/device_alternate.hpp:40,
                  from ./include/caffe/common.hpp:19,
                  from ./include/caffe/util/db.hpp:6,
                  from src/caffe/util/db.cpp:1:
 /usr/local/cuda/include/cudnn.h:803:27: note: declared here
  cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                            ^
 make: *** [.build_release/src/caffe/util/db.o] Error 1
 make: *** Waiting for unfinished jobs....

     

 解决办法：

         1).将/py-faster-rcnn/caffe-fast-rcnn/include/caffe/util/cudnn.hpp 换成最新版的caffe里的cudnn的实现，即相应的cudnn.hpp.

         2).将/py-faster-rcnn/caffe-fast-rcnn/src/caffe/layer里的，所有以cudnn开头的文件，例如cudnn_lrn_layer.cu，cudnn_pooling_layer.cpp，cudnn_sigmoid_layer.cu。

   都替换成最新版的caffe里的相应的同名文件。

1. src/caffe/layers/cudnn_relu_layer.cpp: In member function ‘virtual void caffe::CuDNNReLULayer::LayerSetUp(const std::vector*>&, const std::vector*>&)’:  
2. src/caffe/layers/cudnn_relu_layer.cpp:16:45: error: ‘activ_desc_’ was not declared in this scope  
3.    cudnn::createActivationDescriptor(&activ_desc_, CUDNN_ACTIVATION_RELU);  
4.                                              ^  
5. make: *** [.build_release/src/caffe/layers/cudnn_relu_layer.o] 错误 1

将./include/caffe/layers的，所有以cudnn开头的文件，例如cudnn_conv_layer.hpp，cudnn_lcn_laye.hpp

   都替换成最新版的caffe里的相应的同名文件  

5.运行faster-rcnn里的demo

 cd py-faster-rcnn/tools
 ./tools/demo.py