# key_masks：(N, T_k) N:batch_size T:maxlen
tf.tile(key_masks, [num_heads, 1]) # (h*N, T_k)

tile([x, y], [a, b])
# x 复制 a 次
# y 复制 b 次

tf.reduce_sum(keys, axis=-1)
# input按照第n维加和 
# 感觉就是那一维度没了
# [N, T, num_units] -> [N, T]

# 如果没有第二个参数，就是对矩阵中所有元素求和
def reduce_sum(input_tensor,
               axis=None,
               keepdims=None,
               name=None,
               reduction_indices=None,
               keep_dims=None):
  """Computes the sum of elements across dimensions of a tensor.

  Reduces `input_tensor` along the dimensions given in `axis`.
  Unless `keepdims` is true, the rank of the tensor is reduced by 1 for each
  entry in `axis`. If `keepdims` is true, the reduced dimensions
  are retained with length 1.

  If `axis` has no entries, all dimensions are reduced, and a
  tensor with a single element is returned.
"""