tf.squeeze和tf.expand_dims的用法

import numpy as np
import tensorflow as tf
a=[[2,2,3,3],[4,5,6,4]]
t1=tf.expand_dims(a,0,name="t1")
t2=tf.expand_dims(a,1,name="t2")
with tf.Session() as sess:
    print(sess.run(t1).shape)
    print(sess.run(tf.squeeze(t1,0)).shape)
    print(sess.run(t2).shape)
    print(sess.run(tf.squeeze(t2,1)).shape)

输出如下：

(1, 2, 4)
(2, 4)
(2, 1, 4)
(2, 4)