How to calculate the Cosine similarity between two tensors?

Question

I have two normalized tensors and I need to calculate the cosine similarity between these tensors. How do I do it with TensorFlow?

cosine(normalize_a,normali         


        

Answer 1

This will do the job:

a = tf.placeholder(tf.float32, shape=[None], name="input_placeholder_a")
b = tf.placeholder(tf.float32, shape=[None], name="input_placeholder_b")
normalize_a = tf.nn.l2_normalize(a,0)        
normalize_b = tf.nn.l2_normalize(b,0)
cos_similarity=tf.reduce_sum(tf.multiply(normalize_a,normalize_b))
sess=tf.Session()
cos_sim=sess.run(cos_similarity,feed_dict={a:[1,2,3],b:[2,4,6]})

This prints 0.99999988

Answer 2

Times change. With the latest TF API, this can be computed by calling tf.losses.cosine_distance.

Example:

import tensorflow as tf
import numpy as np


x = tf.constant(np.random.uniform(-1, 1, 10)) 
y = tf.constant(np.random.uniform(-1, 1, 10))
s = tf.losses.cosine_distance(tf.nn.l2_normalize(x, 0), tf.nn.l2_normalize(y, 0), dim=0)
print(tf.Session().run(s))

Of course, 1 - s is the cosine similarity!

Answer 3

You can normalize you vector or matrix like this:

[batch_size*hidden_num]
states_norm=tf.nn.l2_normalize(states,dim=1)
[batch_size * embedding_dims]
embedding_norm=tf.nn.l2_normalize(embedding,dim=1)
#assert hidden_num == embbeding_dims
after mat [batch_size*embedding]
user_app_scores = tf.matmul(states_norm,embedding_norm,transpose_b=True)