张量流中是否有 logit 函数?

Lar*_* Xu 5 machine-learning inverse neural-network tensorflow activation-function

张量流中是否有logit函数,即sigmoid函数的逆函数?我已经搜索过谷歌,但没有找到任何。

小智 5

tf.log_sigmoid()不是一个logit函数。它是逻辑函数的对数。

来自 TF 文档:

y = log(1 / (1 + exp(-x)))
Run Code Online (Sandbox Code Playgroud)

据我所知,TF 没有 logit 函数,因此您必须自己制作,正如第一个答案最初建议的那样。


ben*_*che 1

给定 logit 函数的定义(作为 sigmoidal 逻辑函数的反函数),自己实现它是相当简单的(参见维基百科“Logit”文章):

作为sigmoid(x) = 1 / (1 + exp(-x))

logit(y) = sigmoid(x)^-1 = log(y / (1 - p)) = -log( 1 / p - 1)


执行:

import tensorflow as tf

def logit(x):
    """ Computes the logit function, i.e. the logistic sigmoid inverse. """
    return - tf.log(1. / x - 1.)

x = tf.random_uniform((5, ), minval=-10., maxval=10., dtype=tf.float64)

# sigmoid(x):
x_sig = tf.sigmoid(x)

# logit(sigmoid(x)) = x:
x_id = logit(x_sig)

# Verifying the equality:
comp = tf.abs(x - x_id)

with tf.Session() as sess:
    a, a_id, co = sess.run([x, x_id, comp])
    print(a)
    # [ 0.99629643  1.4082849   6.6794731   7.64434123  6.99725702]
    print(a_id)
    # [ 0.99629643  1.4082849   6.6794731   7.64434123  6.99725702]
    print(co)
    # [  2.22044605e-16   0.00000000e+00   7.28306304e-14   4.35207426e-14 7.81597009e-14]
Run Code Online (Sandbox Code Playgroud)

注意:该等式适用于相当小的值(即forx的小值),因为快速收敛到其渐近线极限:nx in [-n, n]sigmoid(x)

import tensorflow as tf

def logit(x):
    """ Computes the logit function, i.e. the logistic sigmoid inverse. """
    return - tf.log(1. / x - 1.)

x = tf.constant([-1000, -100, -10, -1, 0, 1, 10, 100, 1000], dtype=tf.float64)

# sigmoid(x):
x_sig = tf.sigmoid(x)
# logit(sigmoid(x)) = x:
x_id = logit(x_sig)

with tf.Session() as sess:
    a, a_id = sess.run([x, x_id])
    print(a)
    # [-1000.  -100.   -10.    -1.     0.     1.    10.   100.  1000.]
    print(a_id)
    # [ -inf   -100.   -10.    -1.     0.     1.    10.   inf   inf  ]
Run Code Online (Sandbox Code Playgroud)