import tensorflow as tf
a1 = tf.constant([[1,2],[3,4],[5,6]])
a2 = tf.constant([[[1],[2]],[[3],[4]],[[5],[6]]])
a3 = tf.constant([[[[1]],[[2]]],[[[3]],[[4]]],[[[5]],[[6]]]])
r1 = a1/tf.constant(2)
r2 = a2/tf.constant(2)
r3 = a3/tf.constant(2)
sess = tf.Session()
print(sess.run(r1))
print(sess.run(r2))
print(sess.run(r3))
[[ 0.5 1. ]
[ 1.5 2. ]
[ 2.5 3. ]]
[[[ 0.5]
[ 1. ]]
[[ 1.5]
[ 2. ]]
[[ 2.5]
[ 3. ]]]
[[[[ 0.5]]
[[ 1. ]]]
[[[ 1.5]]
[[ 2. ]]]
[[[ 2.5]]
[[ 3. ]]]]
也就是说无论多少维的tensor,都是对于最终的每个元素都除的