python - 如何在Tensorflow中形成多层张量

Question

在tensorflow中，我有一个形状为[2,3,3,1]的张量，现在我想将张量复制到多层到形状为[2,3,3,3]的张量，我怎样才能这样做吗？

Answer 1

您可以使用tf.tile或tf.concat来实现此目的:

t = tf.random_uniform([2, 3, 3, 1], 0, 1)
s1 = tf.tile(t, [1, 1, 1, 3])
s2 = tf.concat([t]*3, axis=-1)

with tf.Session() as sess:
    tnp, s1np, s2np = sess.run([t, s1, s2])
    print(tnp.shape)
    print(s1np.shape)
    print(s2np.shape)

打印内容

(2, 3, 3, 1)
(2, 3, 3, 3)
(2, 3, 3, 3)

为了说明发生的情况，查看 2d 示例可能会更容易:

import tensorflow as tf

t = tf.random_uniform([2, 1], 0, 1)
s1 = tf.tile(t, [1, 3])
s2 = tf.concat([t]*3, axis=-1)

with tf.Session() as sess:
    tnp, s1np, s2np = sess.run([t, s1, s2])
    print(tnp)
    print(s1np)
    print(s2np)

打印内容

[[0.52104855]
 [0.95304275]]
[[0.52104855 0.52104855 0.52104855]
 [0.95304275 0.95304275 0.95304275]]
[[0.52104855 0.52104855 0.52104855]
 [0.95304275 0.95304275 0.95304275]]