Tensorflow 中的平均欧几里德距离

Question

I have two tensors of sequences of size [batch_size, seq_length, 2]. I want to compute mean Euclidean distance between tensors. What is the elegant way to do this?

Answer 1

给定两个张量A和B每个张量A形状为[batch_size, seq_length, 2] ，您可以使用tf.norm计算欧几里得距离（L2 范数）：

l2_norm = tf.norm(A-B, ord='euclidean')

Answer 2

You can also use tf.math.reduce_euclidean_norm:

tf.math.reduce_euclidean_norm(
    input_tensor, axis=None, keepdims=False, name=None
)

see the documentation here .