windows 下 编译py-faster-rcnn,py-rfcn, py-pva-frcn 下的lib。编译Cython模块

windows下想要运行py-faster-rcnn,py-rfcn, py-pva-frcn ,首先就是要编译lib文件夹下的setup.py ,建立Cython模块。其实这一些方法的lib都差不多,只需对照原版的setup.py进行相应的微改,记得修改代码中相应的文件夹名字。在Linux下编译这个很简单,在windows下面直接在cmd下编译是不会通过的,需要修改setup.py。 这里提供修改后的版本(windows下),将setup.py 分成两个文件:newsetup.py 和 setup_cuda.py(因为lib里面有.cu 文件需要编译,针对使用gpu的,如果是用cpu的话,就不需要编译这个文件了。)

(有问题可以加群交流334227548

这里提供pva-faster-rcnn版本的两个文件(其他算法的lib下的setup.py 相似。)

1 先编译newsetup.py 

cmd 输入 如下命令: 


如果需要如下问题:


cmd中输入如下指令:

SET VS90COMNTOOLS=%VS110COMNTOOLS% (如果用的是vs2012的话)
SET VS90COMNTOOLS=%VS120COMNTOOLS% (如果用的是vs2013的话)

编译成功截图:


下面提供newsetup.py 的代码:

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

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

#change for windows, by MrX
nvcc_bin = 'nvcc.exe'
lib_dir = 'lib/x64'

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 'CUDA_PATH' in os.environ:
        home = os.environ['CUDA_PATH']
        print("home = %s\n" % home)
        nvcc = pjoin(home, 'bin', nvcc_bin)
    else:
        # otherwise, search the PATH for NVCC
        default_path = pjoin(os.sep, 'usr', 'local', 'cuda', 'bin')
        nvcc = find_in_path(nvcc_bin, 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 $CUDA_PATH')
        home = os.path.dirname(os.path.dirname(nvcc))
        print("home = %s, nvcc = %s\n" % (home, nvcc))


    cudaconfig = {'home':home, 'nvcc':nvcc,
                  'include': pjoin(home, 'include'),
                  'lib64': pjoin(home, lib_dir)}
    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 cl/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.spawn 
    #default_compiler_so = self.rc
    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(sources, output_dir=None, macros=None, include_dirs=None, debug=0, extra_preargs=None, extra_postargs=None, depends=None):
        postfix=os.path.splitext(sources[0])[1]
        
        if postfix == '.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['cl']


        return super(sources, output_dir, macros, include_dirs, debug, extra_preargs, postargs, depends)
        # reset the default compiler_so, which we might have changed for cuda
        #self.rc = 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 = [
    # unix _compile: obj, src, ext, cc_args, extra_postargs, pp_opts
    Extension(
        "utils.cython_bbox",
        sources=["utils\\bbox.pyx"],
        #define_macros={'/LD'},
        #extra_compile_args={'cl': ['/link', '/DLL', '/OUT:cython_bbox.dll']},
        #extra_compile_args={'cl': ['/LD']},
        extra_compile_args={'cl': []},
        include_dirs = [numpy_include]
    ),
    Extension(
        "nms.cpu_nms",
        sources=["nms\\cpu_nms.pyx"],
        extra_compile_args={'cl': []},
        include_dirs = [numpy_include],
    ),
     Extension(
        'pycocotools._mask',
        sources=['pycocotools\\maskApi.c', 'pycocotools\\_mask.pyx'],
        include_dirs = [numpy_include, 'pycocotools'],
        extra_compile_args={'cl': []},
    ),
    #Extension(   # just used to get nms\gpu_nms.obj
    #    "nms.gpu_nms",
    #    sources=['nms\\gpu_nms.pyx'],
    #    language='c++',
    #    extra_compile_args={'cl': []},
    #    include_dirs = [numpy_include]
    #),
]

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


2. 编译setup_cuda.py 

cmd执行命令:和上面类似,将newsetup.py 改成setup_cuda.py即可。编译成功的显示也和上面的一样。

注:nms文件夹下没有gpu_nms.cu 的话,已上传到群文件lib.rar文件(群号:334227548。此群针对windows caffe的使用者交流学习)。

下面提供setup_cuda.py 的代码:

#!/usr/bin/env python

import numpy as np
import os
# on Windows, we need the original PATH without Anaconda's compiler in it:
PATH = os.environ.get('PATH')
from distutils.spawn import spawn, find_executable
from setuptools import setup, find_packages, Extension
from setuptools.command.build_ext import build_ext
import sys

# CUDA specific config
# nvcc is assumed to be in user's PATH
nvcc_compile_args = ['-O', '--ptxas-options=-v', '-arch=sm_35', '-c', '--compiler-options=-fPIC']
nvcc_compile_args = os.environ.get('NVCCFLAGS', '').split() + nvcc_compile_args
cuda_libs = ['cublas']


# 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()


cudamat_ext = Extension('nms.gpu_nms',
                        sources=[
                                'nms\\gpu_nms.cu'
                                ],
                        language='c++',
                        libraries=cuda_libs,
                        extra_compile_args=nvcc_compile_args,
                        include_dirs = [numpy_include, 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v7.5\\include'])


class CUDA_build_ext(build_ext):
    """
    Custom build_ext command that compiles CUDA files.
    Note that all extension source files will be processed with this compiler.
    """
    def build_extensions(self):
        self.compiler.src_extensions.append('.cu')
        self.compiler.set_executable('compiler_so', 'nvcc')
        self.compiler.set_executable('linker_so', 'nvcc --shared')
        if hasattr(self.compiler, '_c_extensions'):
            self.compiler._c_extensions.append('.cu')  # needed for Windows
        self.compiler.spawn = self.spawn
        build_ext.build_extensions(self)

    def spawn(self, cmd, search_path=1, verbose=0, dry_run=0):
        """
        Perform any CUDA specific customizations before actually launching
        compile/link etc. commands.
        """
        if (sys.platform == 'darwin' and len(cmd) >= 2 and cmd[0] == 'nvcc' and
                cmd[1] == '--shared' and cmd.count('-arch') > 0):
            # Versions of distutils on OSX earlier than 2.7.9 inject
            # '-arch x86_64' which we need to strip while using nvcc for
            # linking
            while True:
                try:
                    index = cmd.index('-arch')
                    del cmd[index:index+2]
                except ValueError:
                    break
        elif self.compiler.compiler_type == 'msvc':
            # There are several things we need to do to change the commands
            # issued by MSVCCompiler into one that works with nvcc. In the end,
            # it might have been easier to write our own CCompiler class for
            # nvcc, as we're only interested in creating a shared library to
            # load with ctypes, not in creating an importable Python extension.
            # - First, we replace the cl.exe or link.exe call with an nvcc
            #   call. In case we're running Anaconda, we search cl.exe in the
            #   original search path we captured further above -- Anaconda
            #   inserts a MSVC version into PATH that is too old for nvcc.
            cmd[:1] = ['nvcc', '--compiler-bindir',
                       os.path.dirname(find_executable("cl.exe", PATH))
                       or cmd[0]]
            # - Secondly, we fix a bunch of command line arguments.
            for idx, c in enumerate(cmd):
                # create .dll instead of .pyd files
                #if '.pyd' in c: cmd[idx] = c = c.replace('.pyd', '.dll')  #20160601, by MrX
                # replace /c by -c
                if c == '/c': cmd[idx] = '-c'
                # replace /DLL by --shared
                elif c == '/DLL': cmd[idx] = '--shared'
                # remove --compiler-options=-fPIC
                elif '-fPIC' in c: del cmd[idx]
                # replace /Tc... by ...
                elif c.startswith('/Tc'): cmd[idx] = c[3:]
                # replace /Fo... by -o ...
                elif c.startswith('/Fo'): cmd[idx:idx+1] = ['-o', c[3:]]
                # replace /LIBPATH:... by -L...
                elif c.startswith('/LIBPATH:'): cmd[idx] = '-L' + c[9:]
                # replace /OUT:... by -o ...
                elif c.startswith('/OUT:'): cmd[idx:idx+1] = ['-o', c[5:]]
                # remove /EXPORT:initlibcudamat or /EXPORT:initlibcudalearn
                elif c.startswith('/EXPORT:'): del cmd[idx]
                # replace cublas.lib by -lcublas
                elif c == 'cublas.lib': cmd[idx] = '-lcublas'
            # - Finally, we pass on all arguments starting with a '/' to the
            #   compiler or linker, and have nvcc handle all other arguments
            if '--shared' in cmd:
                pass_on = '--linker-options='
                # we only need MSVCRT for a .dll, remove CMT if it sneaks in:
                cmd.append('/NODEFAULTLIB:libcmt.lib')
            else:
                pass_on = '--compiler-options='
            cmd = ([c for c in cmd if c[0] != '/'] +
                   [pass_on + ','.join(c for c in cmd if c[0] == '/')])
            # For the future: Apart from the wrongly set PATH by Anaconda, it
            # would suffice to run the following for compilation on Windows:
            # nvcc -c -O -o .obj .cu
            # And the following for linking:
            # nvcc --shared -o .dll .obj .obj -lcublas
            # This could be done by a NVCCCompiler class for all platforms.
        spawn(cmd, search_path, verbose, dry_run)

setup(name="py_fast_rcnn_gpu",
      description="Performs linear algebra computation on the GPU via CUDA",
      ext_modules=[cudamat_ext],
      cmdclass={'build_ext': CUDA_build_ext},
)


你可能感兴趣的:(windows 下 编译py-faster-rcnn,py-rfcn, py-pva-frcn 下的lib。编译Cython模块)