Python 如何计算两个张量之间的余弦相似度？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/43357732/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
How to calculate the Cosine similarity between two tensors?
提问by Matias
I have two normalized tensors and I need to calculate the cosine similarity between these tensors. How do I do it with TensorFlow?
我有两个归一化张量，我需要计算这些张量之间的余弦相似度。我如何使用 TensorFlow 做到这一点？
cosine(normalize_a,normalize_b)
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)
回答by Miriam Farber
This will do the job:
这将完成这项工作：
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
这打印 0.99999988
回答by Rajarshee Mitra
Times change. With the latest TF API, this can be computed by calling tf.losses.cosine_distance.
时代在变。使用最新的 TF API，可以通过调用tf.losses.cosine_distance.
Example:
例子：
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 - sis the cosine similarity!
当然1 - s是余弦相似度！
回答by Andrew LD
You can normalize you vector or matrix like this:
您可以像这样对向量或矩阵进行归一化：
[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)
