tf.nn.l2_normalize(x, dim, epsilon=1e-12, name=None)
上式:
x为输入的向量;
dim为l2范化的维数,dim取值为0或0或1;
epsilon的范化的最小值边界;
按例计算
例1:
import tensorflow as tf
input_data = tf.constant([[1.0,2,3],[4.0,5,6],[7.0,8,9]])
output = tf.nn.l2_normalize(input_data, dim = 0)
with tf.Session() as sess:
print sess.run(input_data)
print sess.run(output)
结果:
[[1. 2. 3.]
[4. 5. 6.]
[7. 8. 9.]]
[[0.12309149 0.20739034 0.26726127]
[0.49236596 0.51847583 0.53452253]
[0.86164045 0.82956135 0.80178374]]
计算方法:
dim = 0, 为按列进行l2范化
norm(1)=12+42+72−−−−−−−−−−√=66−−√
norm(2)=<