向量化嵌套的循环Python

这就是我的并行方法。首先，我创建一个查找表，其中每个像素都显示最近邻最大值的坐标。对于我的intel i7双核cpu上的100 * 100矩阵，该代码运行大约2秒钟。到目前为止，代码尚未优化，多重处理内部的数据处理有些奇怪，并且可以肯定变得更容易。请告诉我您想要什么。到目前为止，该代码仅将数据点的坐标添加到列表中，如果您需要这些值，请在适当的点进行更改或仅解析结果lines[]列表。

import numpy
import multiprocessing as mp
import time
start=time.time()
#Getting the number of CPUs present
num_cpu=mp.cpu_count()
#Creation of random data for testing
data=numpy.random.randint(1,30,size=(200,200))
x,y=data.shape
#Padding is introduced to cope with the border of the dataset.
#Change if you want other behaviour like wrapping, reflection etc.
def pad(data):
    '''Can be made faster, by using numpys pad function
    if present'''
    a=numpy.zeros((x+2,y+2))
    a[1:-1,1:-1]=data
    return a
data=pad(data)
#Kernel to get only the neighbours, change that if you only want diagonals or other shapes.
kernel=numpy.array([[1,1,1],[1,0,1],[1,1,1]])
result_list=[]  
#Setting up functions for Parallel Processing  
def log_result(result): 
    result_list.append(result) 
def max_getter(pixel):
    '''As this function is going to be used in a parallel processing environment,
    the data has to exist globally in order not to have to pickle it in the subprocess'''
    temp=data[pixel[0]-1:pixel[0]+2,pixel[1]-1:pixel[1]+2].copy()*kernel
    #Getting the submatrix without the central pixel
    compare=numpy.max(temp)==temp
    coords=numpy.nonzero(compare)
    if len(coords[0])!=1:
        coords=(coords[0][0],coords[1][0])
    #discards every maximum which is not the first. Change if you want.
    #Converting back to global coordinates
    return (pixel,(pixel[0]+(numpy.asscalar(coords[0])-1),pixel[1]+(numpy.asscalar(coords[1])-1)))
    #This assumes, that the maximum is unique in the subset, if this is not the case adjust here
def parallell_max():
    pool = mp.Pool() 
#You can experiment using more cores if you have hyperthreading and it's not correctly found by cpu_count
    for i in range(1,x+1):

        for j in range(1,y+1):

            pool.apply_async(max_getter, args = ((i,j),),callback=log_result) 
    pool.close()
    pool.join() 


#___________START Parallel Processing________
if __name__ == '__main__':
   # directions={}
    parallell_max()
    directions={}
    for i in result_list:
        directions[i[0]]=i[1]
    #Directions is a dictionary-like lookup-table, where every pixel gives the next pixel in the line
    lines=[]
    #The following code can also be easily parallelized as seen above.
    for i in range(1,x+1):
        for j in range(1,y+1):
            line=[]
            first,second=i,j
            for k in range(100):
                line.append((first,second))
                first,second=directions[(first,second)]
            lines.append(line)
    stop=time.time()
    print stop-start