RCNN（五）：Ubuntu 15.04 配置Faster RCNN

git地址：https://github.com/rbgirshick/py-faster-rcnn
本文对于git上的要求做了翻译，对于一些可能遇到的坑做了修改。
关于CUDA、CUDNN等软件安装请参照：http://blog.csdn.net/u011587569/article/details/52054168

Requirements: software

sudo apt-get install git cython python-opencv
sudo pip install cython easydict

Requirements: hardware

1. For training smaller networks (ZF, VGG_CNN_M_1024) a good GPU (e.g.Titan, K20, K40, …) with at least 3G of memory suffices
2. For training Fast R-CNN with VGG16, you’ll need a K40 (~11G of memory)
3. For training the end-to-end version of Faster R-CNN with VGG16, 3G of GPU memory is sufficient (using CUDNN)

Installation

1.Clone the Faster R-CNN repository

#Make sure to clone with --recursive
git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git

2.Build the Cython modules

cd $FRCN_ROOT/lib
make

note：如果一直提示找不到CUDA，请将setup.py中所有CUDA[lib64]改为CUDA[lib]，如下：

# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

import os
from os.path import join as pjoin
from setuptools import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext
import subprocess
import numpy as np

def find_in_path(name, path):
    "Find a file in a search path"
    # Adapted fom
    # http://code.activestate.com/recipes/52224-find-a-file-given-a-search-path/
    for dir in path.split(os.pathsep):
        binpath = pjoin(dir, name)
        if os.path.exists(binpath):
            return os.path.abspath(binpath)
    return None


def locate_cuda():
    """Locate the CUDA environment on the system

    Returns a dict with keys 'home', 'nvcc', 'include', and 'lib64'
    and values giving the absolute path to each directory.

    Starts by looking for the CUDAHOME env variable. If not found, everything
    is based on finding 'nvcc' in the PATH.
    """

    # first check if the CUDAHOME env variable is in use
    if 'CUDAHOME' in os.environ:
        home = os.environ['CUDAHOME']
        nvcc = pjoin(home, 'bin', 'nvcc')
    else:
        # otherwise, search the PATH for NVCC
        default_path = pjoin(os.sep, 'usr', 'local', 'cuda', 'bin')
        nvcc = find_in_path('nvcc', os.environ['PATH'] + os.pathsep + default_path)
        if nvcc is None:
            raise EnvironmentError('The nvcc binary could not be '
                'located in your $PATH. Either add it to your path, or set $CUDAHOME')
        home = os.path.dirname(os.path.dirname(nvcc))

    cudaconfig = {
    'home':home, 'nvcc':nvcc,
                  'include': pjoin(home, 'include'),
                  'lib': pjoin(home, 'lib')}
    for k, v in cudaconfig.iteritems():
        if not os.path.exists(v):
            raise EnvironmentError('The CUDA %s path could not be located in %s' % (k, v))

    return cudaconfig
CUDA = locate_cuda()


# Obtain the numpy include directory.  This logic works across numpy versions.
try:
    numpy_include = np.get_include()
except AttributeError:
    numpy_include = np.get_numpy_include()

def customize_compiler_for_nvcc(self):
    """inject deep into distutils to customize how the dispatch
    to gcc/nvcc works.

    If you subclass UnixCCompiler, it's not trivial to get your subclass
    injected in, and still have the right customizations (i.e.
    distutils.sysconfig.customize_compiler) run on it. So instead of going
    the OO route, I have this. Note, it's kindof like a wierd functional
    subclassing going on."""

    # tell the compiler it can processes .cu
    self.src_extensions.append('.cu')

    # save references to the default compiler_so and _comple methods
    default_compiler_so = self.compiler_so
    super = self._compile

    # now redefine the _compile method. This gets executed for each
    # object but distutils doesn't have the ability to change compilers
    # based on source extension: we add it.
    def _compile(obj, src, ext, cc_args, extra_postargs, pp_opts):
        if os.path.splitext(src)[1] == '.cu':
            # use the cuda for .cu files
            self.set_executable('compiler_so', CUDA['nvcc'])
            # use only a subset of the extra_postargs, which are 1-1 translated
            # from the extra_compile_args in the Extension class
            postargs = extra_postargs['nvcc']
        else:
            postargs = extra_postargs['gcc']

        super(obj, src, ext, cc_args, postargs, pp_opts)
        # reset the default compiler_so, which we might have changed for cuda
        self.compiler_so = default_compiler_so

    # inject our redefined _compile method into the class
    self._compile = _compile


# run the customize_compiler
class custom_build_ext(build_ext):
    def build_extensions(self):
        customize_compiler_for_nvcc(self.compiler)
        build_ext.build_extensions(self)


ext_modules = [
    Extension(
        "utils.cython_bbox",
        ["utils/bbox.pyx"],
        extra_compile_args={
    'gcc': ["-Wno-cpp", "-Wno-unused-function"]},
        include_dirs = [numpy_include]
    ),
    Extension(
        "nms.cpu_nms",
        ["nms/cpu_nms.pyx"],
        extra_compile_args={
    'gcc': ["-Wno-cpp", "-Wno-unused-function"]},
        include_dirs = [numpy_include]
    ),
    Extension('nms.gpu_nms',
        ['nms/nms_kernel.cu', 'nms/gpu_nms.pyx'],
        library_dirs=[CUDA['lib']],
        libraries=['cudart'],
        language='c++',
        runtime_library_dirs=[CUDA['lib']],
        # 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']]
    ),
    Extension(
        'pycocotools._mask',
        sources=['pycocotools/maskApi.c', 'pycocotools/_mask.pyx'],
        include_dirs = [numpy_include, 'pycocotools'],
        extra_compile_args={
            'gcc': ['-Wno-cpp', '-Wno-unused-function', '-std=c99']},
    ),
]

setup(
    name='fast_rcnn',
    ext_modules=ext_modules,
    # inject our custom trigger
    cmdclass={
    'build_ext': custom_build_ext},
)

note：如果提示G++ 或是C++缺少函数，请将gcc升级为4.9.2版本，如下操作：

$ cd /usr/bin
$ sudo rm gcc
$ sudo ln -s gcc-4.9 gcc
$ sudo rm g++
$ sudo ln -s g++-4.9 g++

3.Build Caffe and pycaffe
将我们之前配置Caffe的Makefile.config拷贝到caffe-fast-rcnn文件夹下。（http://blog.csdn.net/u011587569/article/details/52054168）做如下改动：
WITH_PYTHON_LAYER := 1
然后编译

cd $FRCN_ROOT/caffe-fast-rcnn
sudo make -j8 
sudo make pycaffe

note：一定要加sudo 不然可能会提示权限不够。

4.Download pre-computed Faster R-CNN detectors

cd $FRCN_ROOT
./data/scripts/fetch_faster_rcnn_models.sh

note：下载可能比较慢，这时候我们打开fetch_faster_rcnn_models.sh，获取到下载链接，使用迅雷等下载工具下载然后放到data下，然后解压就可以了。

Demo

cd $FRCN_ROOT
./tools/demo.py

note：默认演示的是系统自带的图片，当然我们也可以修改成自己的图片。

1.将我们自己的图片放到data/demo文件夹下面
2.将tools下的demo.py

im_names = ['000456.jpg', '000542.jpg', '001150.jpg','001763.jpg', '004545.jpg']

在上面添加我们自己图片的名称就可以了。

测试集验证

参考如下博文：http://blog.csdn.net/u011587569/article/details/52166775