首先,我在 windows xp 机器上使用 python[2.7.2]、numpy[1.6.2rc1]、cython[0.16]、gcc[MinGW] 编译器。
我需要一个 3D 连接组件算法来处理存储在 numpy 数组中的一些 3D 二进制数据(即 1 和 0)。不幸的是,我找不到任何现有代码,因此我将此处找到的代码修改为使用 3D 数组。一切都很好,但是速度对于处理庞大的数据集是可取的。结果我偶然发现了 cython 并决定试一试。
到目前为止,cython 已经提高了速度: Cython:0.339 s Python:0.635 s
使用 cProfile,我在纯 python 版本中的耗时行是:
new_region = min(filter(lambda i: i > 0, array_region[xMin:xMax,yMin:yMax,zMin:zMax].ravel()))
问题: “cythonize”行的正确方法是什么:
new_region = min(filter(lambda i: i > 0, array_region[xMin:xMax,yMin:yMax,zMin:zMax].ravel()))
for x,y,z in zip(ind[0],ind[1],ind[2]):
任何帮助将不胜感激,并希望这项工作将对其他人有所帮助。
纯python版本[*.py]:
import numpy as np
def find_regions_3D(Array):
x_dim=np.size(Array,0)
y_dim=np.size(Array,1)
z_dim=np.size(Array,2)
regions = {}
array_region = np.zeros((x_dim,y_dim,z_dim),)
equivalences = {}
n_regions = 0
#first pass. find regions.
ind=np.where(Array==1)
for x,y,z in zip(ind[0],ind[1],ind[2]):
# get the region number from all surrounding cells including diagnols (27) or create new region
xMin=max(x-1,0)
xMax=min(x+1,x_dim-1)
yMin=max(y-1,0)
yMax=min(y+1,y_dim-1)
zMin=max(z-1,0)
zMax=min(z+1,z_dim-1)
max_region=array_region[xMin:xMax+1,yMin:yMax+1,zMin:zMax+1].max()
if max_region > 0:
#a neighbour already has a region, new region is the smallest > 0
new_region = min(filter(lambda i: i > 0, array_region[xMin:xMax+1,yMin:yMax+1,zMin:zMax+1].ravel()))
#update equivalences
if max_region > new_region:
if max_region in equivalences:
equivalences[max_region].add(new_region)
else:
equivalences[max_region] = set((new_region, ))
else:
n_regions += 1
new_region = n_regions
array_region[x,y,z] = new_region
#Scan Array again, assigning all equivalent regions the same region value.
for x,y,z in zip(ind[0],ind[1],ind[2]):
r = array_region[x,y,z]
while r in equivalences:
r= min(equivalences[r])
array_region[x,y,z]=r
#return list(regions.itervalues())
return array_region
纯python加速:
#Original line:
new_region = min(filter(lambda i: i > 0, array_region[xMin:xMax+1,yMin:yMax+1,zMin:zMax+1].ravel()))
#ver A:
new_region = array_region[xMin:xMax+1,yMin:yMax+1,zMin:zMax+1]
min(new_region[new_region>0])
#ver B:
new_region = min( i for i in array_region[xMin:xMax,yMin:yMax,zMin:zMax].ravel() if i>0)
#ver C:
sub=array_region[xMin:xMax,yMin:yMax,zMin:zMax]
nlist=np.where(sub>0)
minList=[]
for x,y,z in zip(nlist[0],nlist[1],nlist[2]):
minList.append(sub[x,y,z])
new_region=min(minList)
时间结果:
O:0.0220445
A:0.0002161
B:0.0173195
C:0.0002560
Cython 版本 [*.pyx]:
import numpy as np
cimport numpy as np
DTYPE = np.int
ctypedef np.int_t DTYPE_t
cdef inline int int_max(int a, int b): return a if a >= b else b
cdef inline int int_min(int a, int b): return a if a <= b else b
def find_regions_3D(np.ndarray Array not None):
cdef int x_dim=np.size(Array,0)
cdef int y_dim=np.size(Array,1)
cdef int z_dim=np.size(Array,2)
regions = {}
cdef np.ndarray array_region = np.zeros((x_dim,y_dim,z_dim),dtype=DTYPE)
equivalences = {}
cdef int n_regions = 0
#first pass. find regions.
ind=np.where(Array==1)
cdef int xMin, xMax, yMin, yMax, zMin, zMax, max_region, new_region, x, y, z
for x,y,z in zip(ind[0],ind[1],ind[2]):
# get the region number from all surrounding cells including diagnols (27) or create new region
xMin=int_max(x-1,0)
xMax=int_min(x+1,x_dim-1)+1
yMin=int_max(y-1,0)
yMax=int_min(y+1,y_dim-1)+1
zMin=int_max(z-1,0)
zMax=int_min(z+1,z_dim-1)+1
max_region=array_region[xMin:xMax,yMin:yMax,zMin:zMax].max()
if max_region > 0:
#a neighbour already has a region, new region is the smallest > 0
new_region = min(filter(lambda i: i > 0, array_region[xMin:xMax,yMin:yMax,zMin:zMax].ravel()))
#update equivalences
if max_region > new_region:
if max_region in equivalences:
equivalences[max_region].add(new_region)
else:
equivalences[max_region] = set((new_region, ))
else:
n_regions += 1
new_region = n_regions
array_region[x,y,z] = new_region
#Scan Array again, assigning all equivalent regions the same region value.
cdef int r
for x,y,z in zip(ind[0],ind[1],ind[2]):
r = array_region[x,y,z]
while r in equivalences:
r= min(equivalences[r])
array_region[x,y,z]=r
#return list(regions.itervalues())
return array_region
Cython 加速:
使用:
cdef np.ndarray region = np.zeros((3,3,3),dtype=DTYPE)
...
region=array_region[xMin:xMax,yMin:yMax,zMin:zMax]
new_region=np.min(region[region>0])
时间:0.170,原始:0.339 s
结果
在考虑了提供的许多有用的评论和答案之后,我当前的算法运行在:
Cython:0.0219
Python:0.4309
Cython 的速度比纯 python 提高了 20 倍。
当前 Cython 代码:
import numpy as np
import cython
cimport numpy as np
cimport cython
from libcpp.map cimport map
DTYPE = np.int
ctypedef np.int_t DTYPE_t
cdef inline int int_max(int a, int b): return a if a >= b else b
cdef inline int int_min(int a, int b): return a if a <= b else b
@cython.boundscheck(False)
def find_regions_3D(np.ndarray[DTYPE_t,ndim=3] Array not None):
cdef unsigned int x_dim=np.size(Array,0),y_dim=np.size(Array,1),z_dim=np.size(Array,2)
regions = {}
cdef np.ndarray[DTYPE_t,ndim=3] array_region = np.zeros((x_dim,y_dim,z_dim),dtype=DTYPE)
cdef np.ndarray region = np.zeros((3,3,3),dtype=DTYPE)
cdef map[int,int] equivalences
cdef unsigned int n_regions = 0
#first pass. find regions.
ind=np.where(Array==1)
cdef np.ndarray[DTYPE_t,ndim=1] ind_x = ind[0], ind_y = ind[1], ind_z = ind[2]
cells=range(len(ind_x))
cdef unsigned int xMin, xMax, yMin, yMax, zMin, zMax, max_region, new_region, x, y, z, i, xi, yi, zi, val
for i in cells:
x=ind_x[i]
y=ind_y[i]
z=ind_z[i]
# get the region number from all surrounding cells including diagnols (27) or create new region
xMin=int_max(x-1,0)
xMax=int_min(x+1,x_dim-1)+1
yMin=int_max(y-1,0)
yMax=int_min(y+1,y_dim-1)+1
zMin=int_max(z-1,0)
zMax=int_min(z+1,z_dim-1)+1
max_region = 0
new_region = 2000000000 # huge number
for xi in range(xMin, xMax):
for yi in range(yMin, yMax):
for zi in range(zMin, zMax):
val = array_region[xi,yi,zi]
if val > max_region: # val is the new maximum
max_region = val
if 0 < val < new_region: # val is the new minimum
new_region = val
if max_region > 0:
if max_region > new_region:
if equivalences.count(max_region) == 0 or new_region < equivalences[max_region]:
equivalences[max_region] = new_region
else:
n_regions += 1
new_region = n_regions
array_region[x,y,z] = new_region
#Scan Array again, assigning all equivalent regions the same region value.
cdef int r
for i in cells:
x=ind_x[i]
y=ind_y[i]
z=ind_z[i]
r = array_region[x,y,z]
while equivalences.count(r) > 0:
r= equivalences[r]
array_region[x,y,z]=r
return array_region
安装文件 [setup.py]
from distutils.core import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext
import numpy
setup(
cmdclass = {'build_ext': build_ext},
ext_modules = [Extension("ConnectComp", ["ConnectedComponents.pyx"],
include_dirs =[numpy.get_include()],
language="c++",
)]
)
构建命令:
python setup.py build_ext --inplace