tf.shape详解

官网链接
https://tensorflow.google.cn/api_docs/python/tf/shape

tf.shape(
    input,
    name=None,
    out_type=tf.int32
)

返回一个一维整数Tensor，用以表示输入input的shape

例1

import tensorflow as tf
a=tf.constant([[1,2],
               [3,4],
               [5,6]])
with tf.Session() as sess:
    print(a.shape)
    print(tf.shape(a))
    print(sess.run(tf.shape(a)))

(3, 2)
Tensor("Shape:0", shape=(2,), dtype=int32)
[3 2]

例2

import tensorflow as tf

t = tf.constant([[[1, 1, 1], [2, 2, 2]], [[3, 3, 3], [4, 4, 4]]])
with tf.Session() as sess:
    print(tf.shape(t))
    print(sess.run(tf.shape(t)))

Tensor("Shape:0", shape=(3,), dtype=int32)
[2 2 3]