Pairwise Euclidean distance computation of elements in 2 tensors, in TensorFlow.

.py

def pairwise_dist (A, B):  
  """
  Computes pairwise distances between each elements of A and each elements of B.

  Args:
    A,    [m,d] matrix
    B,    [n,d] matrix

  Returns:
    D,    [m,n] matrix of pairwise distances
  """
  with tf.variable_scope('pairwise_dist'):
    # squared norms of each row in A and B
    na = tf.reduce_sum(tf.square(A), 1)
    nb = tf.reduce_sum(tf.square(B), 1)
    
    # na as a row and nb as a co"lumn vectors
    na = tf.reshape(na, [-1, 1])
    nb = tf.reshape(nb, [1, -1])

    # return pairwise euclidead difference matrix
    D = tf.sqrt(tf.maximum(na - 2*tf.matmul(A, B, False, True) + nb, 0.0))
  return D

D=tf.reduce_sum((tf.expand_dims(A, 1)-tf.expand_dims(B, 0))**2,2)
makes more sense

tf.reduce_sum((tf.expand_dims(A, 1)-tf.expand_dims(B, 0))**2,2)

Tested! Thanks a lot :) Bless you!