通過

with tf.Session() as sess:

    print (sess.run(y))

即可打印出變數的值。下面給出例子

import numpy as np
import tensorflow as tf
x = tf.constant([1,2,3,4,5,6])
y=tf.reshape(x,(2,3))
with tf.Session() as sess:
    print (sess.run(y))

2.在有的程式中需要使用如下

init_op = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op)
 

print(sess.run(y))

來檢視張量，例子：

import numpy as np
import tensorflow as tf
x = tf.constant([1,2,3,4,5,6])
y=tf.reshape(x,[1,1,1,2,3])
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op)
    print(sess.run(y))

import numpy as np
import 
 
tensorflow as tf
x = tf.constant([1,2,3,4,5,6])
y=tf.reshape(x,[1,1,1,2,3])
print (y.shape)