setup_cuda.py 编译gpu_nms

setup_cuda.py

setup_cuda

1.修改

include_dirs = [numpy_include, r'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\include'])

2.报错：

LINK : fatal error LNK1181: 无法打开输入文件“ID=2.obj”

error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v8.0\\bin\\nvcc.exe' failed with exit status 2

解决方式：把ID=2去掉，手动编译

nvcc.exe --compiler-bindir "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\bin" --shared -LD:\Users\Administrator\Miniconda3\envs\python3\libs -LD:\Users\Administrator\Miniconda3\envs\python3\PCbuild\amd64 "-LC:\Program
Files (x86)\Microsoft Visual Studio 14.0\VC\LIB\amd64" "-LC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\ATLMFC\LIB\amd64" "-LC:\Program Files (x86)\Windows Kits\10\lib\10.0.15063.0\ucrt\x64" "-LC:\Program Files (x86)\Windows Kits\NETFXSDK\4.6.1\lib\um\x64"
"-LC:\Program Files (x86)\Windows Kits\10\lib\10.0.15063.0\um\x64" -lcublas build\temp.win-amd64-3.6\Release\nms\gpu_nms.obj -o build\lib.win-amd64-3.6\nms\gpu_nms.cp36-win_amd64.pyd --linker-options=/nologo,/INCREMENTAL:NO,/LTCG,/MANIFEST:EMBED,/MANIFESTUAC:NO,/IMPLIB:build\temp.win-amd64-3.6\Release\nms\gpu_nms.cp36-win_amd64.lib,/NODEFAULTLIB:libcmt.lib

3.异常：
File "setup_cuda.py", line 77, in spawn

    os.path.dirname(find_executable("cl.exe", PATH))

  File "D:\Users\sbd01\Miniconda3\envs\python3.6\lib\ntpath.py", line 242, in dirname

    return split(p)[0]

  File "D:\Users\sbd01\Miniconda3\envs\python3.6\lib\ntpath.py", line 204, in split

    p = os.fspath(p)

TypeError: expected str, bytes or os.PathLike object, not NoneType

注：用vs2013或vs2015等vs的编译器话，记得将vs的bin路径添加到环境变量里，不然会报关于“cl.exe”的错误。

我的解决方法：C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\bin 把这个添加到系统环境变量

调用代码：

E:\kangcheng\python\rfcn\tf_rfcn-master\lib\layer_utils\proposal_layer.py

#!/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, r'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\cuda\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 <file>.obj <file>.cu
# And the following for linking:
# nvcc --shared -o <file>.dll <file1>.obj <file2>.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},
)