1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
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"
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.
"""
if 'CUDAHOME' in os.environ:
home = os.environ['CUDAHOME']
nvcc = pjoin(home, 'bin', 'nvcc.exe')
else:
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()
try:
numpy_include = np.get_include()
except AttributeError:
numpy_include = np.get_numpy_include()
def customize_compiler_for_nvcc(self):
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')
import sys
py_dir = sys.executable.replace('\\', '/').split('/')[:-1]
py_include = pjoin('/'.join(py_dir), 'include')
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:
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:
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:
h_dir = os.path.dirname(src)
rc_dir = os.path.dirname(obj)
try:
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')
self.spawn([self.rc, "/fo" + obj, rc_file])
except DistutilsExecError as msg:
raise CompileError(msg)
continue
elif ext == '.cu':
try:
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 += ['-Xcompiler', '/EHsc,/W3,/nologo,/Ox,/MD']
arg += postargs
self.spawn(arg)
continue
except DistutilsExecError as msg:
continue
else:
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
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(
"utils.cython_nms",
["utils/nms.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.cpp'],
library_dirs=[CUDA['lib64']],
libraries=['cudart'],
language='c++',
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(
name='tf_faster_rcnn',
ext_modules=ext_modules,
cmdclass={'build_ext': custom_build_ext},
)
|
