Tensorflow:如何处理试图平铺和连接两个张量的动态形状？

Question

我有两个张量，例如 x = [1,2] and y=[3] ，我想沿另一个轴复制最后一个，获得z = [[1,3],[2,3]].理想情况下在 tensorflow 中:

x = tf.placeholder(shape=[None, 2], dtype = tf.float32)
y = tf.placeholder(shape=[1], dtype = tf.float32)
z = tf.concat(x, tf.tile(y, [ x.shape[0] ]) , 1)

问题是 x 占位符第一个维度未确定，我该如何解决？

Answer 1

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

x = tf.placeholder(shape=[None, 2], dtype = tf.float32)
y = tf.placeholder(shape=[1], dtype = tf.float32)

dim = tf.shape(x)[0]
y1 = tf.expand_dims(y, axis = 1)
y1 = tf.tile(y1, [dim, 1])
z = tf.concat((x, y1), axis = 1)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    z_val = sess.run(z, feed_dict = {x:[[2,5],[5,7],[8,9]], y:[3]})
    print(z_val)

输出:

[[ 2.  5.  3.]
 [ 5.  7.  3.]
 [ 8.  9.  3.]]