python - numpy，数组不同层的不同切片

Question

我有 3d 数组 m*n*k ，对于每个 2d 层，我想获取一个大小为 i*j 的子数组。我有一个数组 c，其大小为每层切片起始坐标的 2*k 。有没有好的简单方法可以在没有任何循环的情况下获得我需要的东西？

示例:

test = np.arange(18).reshape((3,3,2))
c = np.array([[0,1], [0, 1]])

test[:,:,0] = array([[ 0,  2,  4],
                     [ 6,  8, 10],
                     [12, 14, 16]])

test[:,:,1] = array([[ 1,  3,  5],
                     [ 7,  9, 11],
                     [13, 15, 17]])

我想要一个数组

  [[[ 0,  9],
    [ 2,  11]],

   [[ 6,  15],
    [ 8,  17]]]

带循环的解决方案:

h=2
w=2
layers = 2
F = np.zeros((h,w,layers))
for k in range(layers):
    F[:,:,k] = test[c[0,k]:c[0,k]+h, c[1,k]:c[1,k]+w, k]

Answer 1

这是利用 broadcasting 的矢量化方法和 advanced-indexing -

d0,d1,d2 = np.ogrid[:h,:w,:layers]
out = test[d0+c[0],d1+c[1],d2]

示例运行 -

In [112]: test = np.arange(200).reshape((10,10,2))
     ...: c = np.array([[0,1], [0, 1]])
     ...: 

In [113]: h=4
     ...: w=5
     ...: layers = 2
     ...: F = np.zeros((h,w,layers))
     ...: for k in range(layers):
     ...:     F[:,:,k] = test[c[0,k]:c[0,k]+h, c[1,k]:c[1,k]+w, k]
     ...:     

In [114]: d0,d1,d2 = np.ogrid[:h,:w,:layers]
     ...: out = test[d0+c[0],d1+c[1],d2]
     ...: 

In [115]: np.allclose(F, out)
Out[115]: True