取不同维度的数据

import numpy as np
import matplotlib.pyplot as plt
def zero_pad(X, pad):
    """
    把数据集X的图像边界全部使用0来扩充pad个宽度和高度。

    参数：
        X - 图像数据集，维度为（样本数，图像高度，图像宽度，图像通道数）
        pad - 整数，每个图像在垂直和水平维度上的填充量
    返回：
        X_paded - 扩充后的图像数据集，维度为（样本数，图像高度 + 2*pad，图像宽度 + 2*pad，图像通道数）

    """

    X_paded = np.pad(X, (
        (0, 0),  # 样本数，不填充
        (pad, pad),  # 图像高度,你可以视为上面填充x个，下面填充y个(x,y)
        (pad, pad),  # 图像宽度,你可以视为左边填充x个，右边填充y个(x,y)
        (0, 0)),  # 通道数，不填充
                     'constant', constant_values=0)  # 连续一样的值填充

    return X_paded

np.random.seed(1)
x = np.random.randn(4,3,3,2)
x_paded = zero_pad(x,2)
#查看信息
print ("x.shape =", x.shape)
print(x)
print ("x_paded.shape =", x_paded.shape)
print ("x[1, 1] =", x[1, 1])

生成的数据

x.shape = (4, 3, 3, 2)
[[[[ 1.62434536 -0.61175641]
   [-0.52817175 -1.07296862]
   [ 0.86540763 -2.3015387 ]]

  [[ 1.74481176 -0.7612069 ]
   [ 0.3190391  -0.24937038]
   [ 1.46210794 -2.06014071]]

  [[-0.3224172  -0.38405435]
   [ 1.13376944 -1.09989127]
   [-0.17242821 -0.87785842]]]


 [[[ 0.04221375  0.58281521]
   [-1.10061918  1.14472371]
   [ 0.90159072  0.50249434]]

  [[ 0.90085595 -0.68372786]
   [-0.12289023 -0.93576943]
   [-0.26788808  0.53035547]]

  [[-0.69166075 -0.39675353]
   [-0.6871727  -0.84520564]
   [-0.67124613 -0.0126646 ]]]


 [[[-1.11731035  0.2344157 ]
   [ 1.65980218  0.74204416]
   [-0.19183555 -0.88762896]]

  [[-0.74715829  1.6924546 ]
   [ 0.05080775 -0.63699565]
   [ 0.19091548  2.10025514]]

  [[ 0.12015895  0.61720311]
   [ 0.30017032 -0.35224985]
   [-1.1425182  -0.34934272]]]


 [[[-0.20889423  0.58662319]
   [ 0.83898341  0.93110208]
   [ 0.28558733  0.88514116]]

  [[-0.75439794  1.25286816]
   [ 0.51292982 -0.29809284]
   [ 0.48851815 -0.07557171]]

  [[ 1.13162939  1.51981682]
   [ 2.18557541 -1.39649634]
   [-1.44411381 -0.50446586]]]]
   
x_paded.shape = (4, 7, 7, 2)
x[1, 1] = [[ 0.90085595 -0.68372786]
 [-0.12289023 -0.93576943]
 [-0.26788808  0.53035547]]
x_paded[1, 1] = 1.74481176421648

这里用x[1,1]来取数据,例如
x[1,1]
x[1, 1, :, :]和这个x[1,1]结果一样

x[1, 1] = [[ 0.90085595 -0.68372786]
 [-0.12289023 -0.93576943]
 [-0.26788808  0.53035547]]

x[1,1,2]取出的是

x[1, 1, 2] = [-0.26788808  0.53035547]

x[1,1,2,1]取出的是

x[1, 1, 2, 1] = 0.530355466738186

不断加深维度,最后变成一个值,维度都从0开始算

带上":"的理解

X[:,0]结果输出为：
[1 1 3 4 5 6 6 0 4 2 5 9 3]
X[:,1]结果输出为：
[2 2 4 5 6 7 7 4 6 9 8 7 7]
X[:,m:n]结果输出为：
[[1]
 [1]
 [3]
 [4]
 [5]
 [6]
 [6]
 [0]
 [4]
 [2]
 [5]
 [9]
 [3]]
X[:,:,0]结果输出为：
[[ 1  1  3  7  4]
 [ 1  1  3  8  5]
 [ 8  1  3  7  4]
 [ 1  1  3  7  7]
 [ 9  1  3  7  4]
 [ 8  1  3  7 43]
 [ 1  1  3  7  4]
 [ 1  1  3 17  4]
 [11  1  3  7  4]]
X[:,:,1]结果输出为：
[[  2   0   4   9   0]
 [  4   5   6   9   0]
 [  2   8   5   3   6]
 [  1   2   5   6   8]
 [  2   3   5  67   4]
 [  2   9  43   3   0]
 [ 22   2  42  29  20]
 [  5  20  24   9  10]
 [  2 110  14   4   2]]
X[:,:,m:n]结果输出为：
[[[ 1]
  [ 1]
  [ 3]
  [ 7]
  [ 4]]
 
 [[ 1]
  [ 1]
  [ 3]
  [ 8]
  [ 5]]
 
 [[ 8]
  [ 1]
  [ 3]
  [ 7]
  [ 4]]
 
 [[ 1]
  [ 1]
  [ 3]
  [ 7]
  [ 7]]
 
 [[ 9]
  [ 1]
  [ 3]
  [ 7]
  [ 4]]
 
 [[ 8]
  [ 1]
  [ 3]
  [ 7]
  [43]]
 
 [[ 1]
  [ 1]
  [ 3]
  [ 7]
  [ 4]]
 
 [[ 1]
  [ 1]
  [ 3]
  [17]
  [ 4]]
 
 [[11]
  [ 1]
  [ 3]
  [ 7]
  [ 4]]]