tf.unstack的作用

import tensorflow as tf

A = [[1, 2, 3], [4, 5, 6]]
a_unstack = tf.unstack(A, num=3,axis=1)

我们得到：
[array([1, 4]), array([2, 5]), array([3, 6])]

即对A在y方向上对其进行切分，以获得每个单词的词向量。

import tensorflow as tf
a = tf.constant([1,2,3])
b = tf.constant([4,5,6])
c = tf.stack([a,b],axis=1)
d = tf.unstack(c,axis=0)
e = tf.unstack(c,axis=1)
print(c.get_shape())
with tf.Session() as sess:
    print(sess.run(c))
    print(sess.run(d))
    print(sess.run(e))

(3, 2)

[[1 4]
[2 5]
[3 6]]

[array([1, 4]), array([2, 5]), array([3, 6])]

[array([1, 2, 3]), array([4, 5, 6])]