tf.nn.l2_normalize L2范化函数详解

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；取0为按列范化，取1为按行范化，也可以取其他数值 
epsilon的范化的最小值边界；

举例:

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(output)

计算方法： 

输出结果为：

若dim=1则输出：
[[0.26726124 0.5345225 0.8017837 ]
[0.45584232 0.5698029 0.6837635 ]
[0.5025707 0.5743665 0.64616233]]

举例二：

import tensorflow as tf
x=tf.constant([[[[1.,2.,3],[4.,5.,6.],[4.,5.,6.]],
                [[1.,2.,3],[4.,5.,6.],[4.,5.,6.]],
                [[1.,2.,3],[4.,5.,6.],[4.,5.,6.]]]])
l2=tf.nn.l2_normalize(x, [3],epsilon=1e-12)
with tf.Session() as sess:
    print(sess.run(l2))

输出结果：

[[[[0.26726124 0.5345225  0.8017837 ]
   [0.45584232 0.5698029  0.6837635 ]
   [0.45584232 0.5698029  0.6837635 ]]

  [[0.26726124 0.5345225  0.8017837 ]
   [0.45584232 0.5698029  0.6837635 ]
   [0.45584232 0.5698029  0.6837635 ]]

  [[0.26726124 0.5345225  0.8017837 ]
   [0.45584232 0.5698029  0.6837635 ]
   [0.45584232 0.5698029  0.6837635 ]]]]