Faster R-CNN 源码编译Windows

最近在看一篇博客，

Faster R-CNN 源码解析（Tensorflow版）（https://blog.csdn.net/u012457308/article/details/79566195）

也是Faster R-CNN 的源码解析 https://www.cnblogs.com/darkknightzh/p/10043864.html

相关原理https://blog.csdn.net/williamyi96/article/details/77648047

使用的代码是https://github.com/endernewton/tf-faster-rcnn

问题是这个代码window10编译是个坑，所以又找了一堆资料，最后找到这个

https://github.com/endernewton/tf-faster-rcnn/issues/335
原文：

Modified, with gpu_nms supports
I ran it on windows successfully (Python 3.6.6, VS2015 compiler, CUDA 9.0 with CUDNN v7), just modify some code.
Tested both cpu_nms and gpu_nms (but don't know why gpu_nms is a little slower than cpu_nms).

Note: If any strange error occurred, I suggest deleting all the generated .c and .cpp files (lib/nms/cpu_nms.c, lib/nms/gpu_nms.cpp, lib/utils/bbox.c) and everything in lib/build

file lib/nms/cpu_nms.pyx:
change (line 25)

cdef np.ndarray[np.int_t, ndim=1] order = scores.argsort()[::-1]

to

cdef np.ndarray[np.int64_t, ndim=1] order = scores.argsort()[::-1]

file lib/nms/gpu_nms.pyx:
change (line 25)

    cdef np.ndarray[np.int_t, ndim=1] \

to

    cdef np.ndarray[np.int64_t, ndim=1] \

file lib/datasets/pascal_voc.py:
change (line 226)

      '{:s}.xml')

to

      '{0:s}.xml')

file lib/datasets/voc_eval.py
change (line 121)

    with open(cachefile, 'w') as f:

to

    with open(cachefile, 'wb') as f:

file lib/setup.py (nearly full modified, new code is as follow):

# --------------------------------------------------------
# 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
import numpy as np
from distutils.core import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext

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
        nvcc = find_in_path('nvcc.exe', os.environ['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'),
                  'lib64': pjoin(home, 'lib', 'x64')}
    for k, v in iter(cudaconfig.items()):
        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):
    # _msvccompiler.py imports:
    import os
    import shutil
    import stat
    import subprocess
    import winreg

    from distutils.errors import DistutilsExecError, DistutilsPlatformError, \
                                 CompileError, LibError, LinkError
    from distutils.ccompiler import CCompiler, gen_lib_options
    from distutils import log
    from distutils.util import get_platform

    from itertools import count

    super = self.compile
    self.src_extensions.append('.cu')
    # find python include
    import sys
    py_dir = sys.executable.replace('\\', '/').split('/')[:-1]
    py_include = pjoin('/'.join(py_dir), 'include')

    # override method in _msvccompiler.py, starts from line 340
    def compile(sources,
                output_dir=None, macros=None, include_dirs=None, debug=0,
                extra_preargs=None, extra_postargs=None, depends=None):

        if not self.initialized:
            self.initialize()
        compile_info = self._setup_compile(output_dir, macros, include_dirs,
                                           sources, depends, extra_postargs)
        macros, objects, extra_postargs, pp_opts, build = compile_info

        compile_opts = extra_preargs or []
        compile_opts.append('/c')
        if debug:
            compile_opts.extend(self.compile_options_debug)
        else:
            compile_opts.extend(self.compile_options)

        add_cpp_opts = False

        for obj in objects:
            try:
                src, ext = build[obj]
            except KeyError:
                continue
            if debug:
                # pass the full pathname to MSVC in debug mode,
                # this allows the debugger to find the source file
                # without asking the user to browse for it
                src = os.path.abspath(src)

            if ext in self._c_extensions:
                input_opt = "/Tc" + src
            elif ext in self._cpp_extensions:
                input_opt = "/Tp" + src
                add_cpp_opts = True
            elif ext in self._rc_extensions:
                # compile .RC to .RES file
                input_opt = src
                output_opt = "/fo" + obj
                try:
                    self.spawn([self.rc] + pp_opts + [output_opt, input_opt])
                except DistutilsExecError as msg:
                    raise CompileError(msg)
                continue
            elif ext in self._mc_extensions:
                # Compile .MC to .RC file to .RES file.
                #   * '-h dir' specifies the directory for the
                #     generated include file
                #   * '-r dir' specifies the target directory of the
                #     generated RC file and the binary message resource
                #     it includes
                #
                # For now (since there are no options to change this),
                # we use the source-directory for the include file and
                # the build directory for the RC file and message
                # resources. This works at least for win32all.
                h_dir = os.path.dirname(src)
                rc_dir = os.path.dirname(obj)
                try:
                    # first compile .MC to .RC and .H file
                    self.spawn([self.mc, '-h', h_dir, '-r', rc_dir, src])
                    base, _ = os.path.splitext(os.path.basename(src))
                    rc_file = os.path.join(rc_dir, base + '.rc')
                    # then compile .RC to .RES file
                    self.spawn([self.rc, "/fo" + obj, rc_file])

                except DistutilsExecError as msg:
                    raise CompileError(msg)
                continue
            elif ext == '.cu':
                # a trigger for cu compile
                try:
                    # 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']
                    arg = [CUDA['nvcc']] + sources + ['-odir', pjoin(output_dir, 'nms')]
                    for include_dir in include_dirs:
                        arg.append('-I')
                        arg.append(include_dir)
                    arg += ['-I', py_include]
                    # arg += ['-lib', CUDA['lib64']]
                    arg += ['-Xcompiler', '/EHsc,/W3,/nologo,/Ox,/MD']
                    arg += postargs
                    self.spawn(arg)
                    continue
                except DistutilsExecError as msg:
                    # raise CompileError(msg)
                    continue
            else:
                # how to handle this file?
                raise CompileError("Don't know how to compile {} to {}"
                                   .format(src, obj))

            args = [self.cc] + compile_opts + pp_opts
            if add_cpp_opts:
                args.append('/EHsc')
            args.append(input_opt)
            args.append("/Fo" + obj)
            args.extend(extra_postargs)

            try:
                self.spawn(args)
            except DistutilsExecError as msg:
                raise CompileError(msg)

        return objects

    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"],
        include_dirs = [numpy_include]
    ),
    Extension('nms.gpu_nms',
        ['nms/nms_kernel.cu', 'nms/gpu_nms.pyx'],
        library_dirs=[CUDA['lib64']],
        libraries=['cudart'],
        language='c++',
        # 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_52',
                                     '--ptxas-options=-v',
                                     '-c']},
        include_dirs = [numpy_include, CUDA['include']]
    )
]

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

It's take me some time to understand how MSVC compiler works, so I made an ugly patch for the compiler by overriding the compile method.

Note: Change the -arch=sm_52 above to fit your graphic card, otherwise using gpu_nms will get the corrupt result. You can follow the original installation guide.

Now, turn to lib directory, run python setup.py build_ext. It possible reports an error:

nms\gpu_nms.cpp(2075): error C2664: "void _nms(int *,int *,const float *,int,int,float,int)": cannot convert parameter 1 from '__pyx_t_5numpy_int32_t *' to 'int *'

Modify one line in the generated file in lib/nms/gpu_nms.cpp, search the keyword _nms, find the following line:
change (line 2075 in my generated cpp file)

  _nms((&(*__Pyx_BufPtrStrided1d(__pyx_t_5numpy_int32_t *, __pyx_pybuffernd_keep.rcbuffer->pybuffer.buf, __pyx_t_10, ...

to

  _nms((&(*__Pyx_BufPtrStrided1d(int *, __pyx_pybuffernd_keep.rcbuffer->pybuffer.buf, __pyx_t_10, ...

At last, run python setup.py build_ext again, copy everything in lib/build/lib.win-amd64-3.6 to lib.

 

第二个坑，需要一个pycocotools，pip安装失败，因为这个库本身不支持window。你妹

上网找了下参照了https://blog.csdn.net/chixia1785/article/details/80040172这个

直接说结论，使用pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI，记得要用管理员权限

搞定

 

数据下载

 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar

 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar

 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar

然后保存到faster_rcnn\data\VOCdevkit2007目录下，里面都是数据文件

下载

原始地址https://drive.google.com/drive/folders/0B1_fAEgxdnvJSmF3YUlZcHFqWTQ

百度网盘地址https://pan.baidu.com/s/1kWkF3fT

解压保存到

faster_rcnn\output\res101\voc_2007_trainval+voc_2012_trainval\default

然后运行\tools\demo.py

妹妹的，终于可以运行了，2天就这样过了