tensorflow实现对张量数据的切片操作

import tensorflow as tf
a=tf.constant([[[1,2,3,4],[4,5,6,7],[7,8,9,10]],
            [[11,12,13,14],[20,21,22,23],[15,16,17,18]]])
print(a.shape)
b,c=tf.split(a,2,0)  #参数1、张量  2`在这里插入代码片`、获得的切片数 3、切片的维度     将两个切片分别赋值给b,c
print(b.shape)
print(c.shape
with tf.Session() as sess:  #查看运行结果
    print(sess.run(b))
    print(sess.run(c))

输出结果为

(2, 3, 4)
(1, 3, 4)
(1, 3, 4)
[[[ 1  2  3  4]
  [ 4  5  6  7]
  [ 7  8  9 10]]]
[[[11 12 13 14]
  [20 21 22 23]
  [15 16 17 18]]]

注意到此时b,c均为三维张量数据，若想转换为二维数组，可使用tf.reshape命令

d=tf.reshape(b,[3,4])
print(d.shape)      

#output
(3, 4)