TensorFlow：How to calculate the Euclidean distance between two tensor?

Question

How to get from A and B to C? A and B are tensors and belong to the output of the network. Now I need to get C from the output operation of the two networks, and then use C to calculate loss function.

The key problem is to optimize A and B by loss function in the later stage, so it must be completed in the form of computational graphs. The TensorFlow formulas for calculating tensors don't seem to be able to solve this problem.

javidcf · Accepted Answer · 2019-01-11 14:07:51Z

2

Use tf.norm:

C = tf.norm(B - A, axis=-1)

answered Jan 11, 2019 at 14:07

javidcf

59.9k7 gold badges87 silver badges134 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

Adrian Mole · Accepted Answer · 2021-08-22 18:13:01Z

1

import tensorflow as tf

#Create The Tensors
pt_a = tf.constant([5., 10.,11.])
pt_b = tf.constant([8., 3.,12.])

#Print Euclidean Distance
print("Euclidean Distance:",tf.norm(pt_a-pt_b,ord='euclidean'))

edited Aug 22, 2021 at 18:13

Adrian Mole

52.1k193 gold badges61 silver badges101 bronze badges

answered Aug 22, 2021 at 2:39

Rajesh Ramachander

112 bronze badges

2 Comments

rmlockerd Over a year ago

Hi, welcome to SO. Consider adding an explanation of how your code answers the problem/question. Code-only answers are often less useful for people new to the language or topic.

Rajesh Ramachander Over a year ago

Define the points as tensor constants and use the tensor norm function to determine the euclidean distance.

Collectives™ on Stack Overflow

TensorFlow：How to calculate the Euclidean distance between two tensor?

2 Answers 2

Comments

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related