四维数组的数学理解与tensorflow中对四维数组解释的不同之处

import numpy as np
n = np.array([[2,1,2,1],
              [0,-1,3,0],
              [2,1,-1,4],
              [1,2,5,7],
              [2,1,2,1],
              [0,1,3,0],
              [2,1,-1,4],
              [8,7,9,5],
              [6,3,2,1],
              [1,2,5,7],
              [2,1,2,1],
              [1,2,5,7]],dtype="float32").reshape(2,4,3,2)
              print(n)

运行后的结果

[[[[ 2.  1.]
   [ 2.  1.]
   [ 0. -1.]]

  [[ 3.  0.]
   [ 2.  1.]
   [-1.  4.]]

  [[ 1.  2.]
   [ 5.  7.]
   [ 2.  1.]]

  [[ 2.  1.]
   [ 0.  1.]
   [ 3.  0.]]]


 [[[ 2.  1.]
   [-1.  4.]
   [ 8.  7.]]

  [[ 9.  5.]
   [ 6.  3.]
   [ 2.  1.]]

  [[ 1.  2.]
   [ 5.  7.]
   [ 2.  1.]]

  [[ 2.  1.]
   [ 1.  2.]
   [ 5.  7.]]]]

数学样式