replicate a row tensor using tf.tile?

Question

I have a tensor which is simply a vector, vector = [0.5 0.4] and tf.shape indicates that it has shape=(1,), I would like to replicate the vector m times and have the shape of [m, 2], so for m = 2, matrix = [[0.5 0.4], [0.5 0.4]]. How do I achieve that using tf.tile?

Answer 1

Take the following, vec is a vector, multiply is your m, the number of times to repeat the vector. tf.tile is performed on the vector and then using tf.reshape it is reshaped into the desired structure.

import tensorflow as tf

vec = tf.constant([1, 2, 3, 4])
multiply = tf.constant([3])

matrix = tf.reshape(tf.tile(vec, multiply), [ multiply[0], tf.shape(vec)[0]])
with tf.Session() as sess:
    print(sess.run([matrix]))

This results in:

[array([[1, 2, 3, 4],
       [1, 2, 3, 4],
       [1, 2, 3, 4]], dtype=int32)]

Answer 2

The same can be achieved by multiplying a ones matrix with vec and let broadcasting do the trick:

tf.ones([m, 1]) * vec

vec = tf.constant([1., 2., 3., 4.])
m = 3
matrix = tf.ones([m, 1]) * vec

with tf.Session() as sess:
   print(sess.run([matrix]))

#Output: [[1., 2., 3., 4.],
#         [1., 2., 3., 4.],
#         [1., 2., 3., 4.]]