np.array的shape |tf.nn.conv2d | t

python中的矩阵、多维数组----numpy

(base) C:\Users\凌安>python
Python 3.7.3 (default, Mar 27 2019, 17:13:21) [MSC v.1915 64 bit (AMD64)] :: Ana
conda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import numpy as np
>>> c = np.array([[[1,1],[1,2],[1,3],[1,4]],[[1,1],[1,2],[1,3],[1,4]]])
>>> c
array([[[1, 1],
        [1, 2],
        [1, 3],
        [1, 4]],

       [[1, 1],
        [1, 2],
        [1, 3],
        [1, 4]]])
>>> c.shape
(2, 4, 2)
>>> c = np.array([[[1,1],[1,2],[1,3],[1,4]],[[1,1],[1,2],[1,3],[1,4]],[[1,1],[1,
2],[1,3],[1,4]]])
>>> c.shape
(3, 4, 2)

上面这个(3, 4, 2)三维数组就可以看作3个4*2的二维矩阵。

tf.truncated_normal

TF-卷积函数 tf.nn.conv2d 介绍