from Cython.Build import cythonize
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):
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():
# 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'),
'lib64': pjoin(home, 'lib64')}
for k, v in cudaconfig.items():
#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()
try:
numpy_include = np.get_include()
except AttributeError:
numpy_include = np.get_numpy_include()
def customize_compiler_for_nvcc(self):
self.src_extensions.append('.cu')
default_compiler_so = self.compiler_so
super = self._compile
def _compile(obj, src, ext, cc_args, extra_postargs, pp_opts):
print(extra_postargs)
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_nms",
["cython_nms.pyx"],
extra_compile_args={'gcc': ["-Wno-cpp", "-Wno-unused-function"]},
include_dirs = [numpy_include]
),
Extension('utils.gpu_nms',
['nms_kernel.cu', 'gpu_nms.pyx'],
library_dirs=[CUDA['lib64']],
libraries=['cudart'],
language='c++',
runtime_library_dirs=[CUDA['lib64']],
extra_compile_args={'gcc': ["-Wno-unused-function"],
'nvcc': ['-arch=sm_35',
'--ptxas-options=-v',
'-c',
'--compiler-options',
"'-fPIC'"]},
include_dirs = [numpy_include, CUDA['include']]
),
]
setup(
ext_modules=ext_modules,
cmdclass={'build_ext': custom_build_ext},
)