1、函數

函數：f(z) = 1 / (1 + exp( ? z))

導數：f(z)‘ = f(z)(1 ? f(z))

2、tensorflow實現

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import tensorflow as tf

input_data = tf.Variable( [[0, 10, -10],[1,2,3]] , dtype = tf.float32 )
output = tf.nn.sigmoid(input_data)
with tf.Session() as sess:
    init = tf.initialize_all_variables()
    sess.run(init)
    print(sess.run(output))

　　輸出為：

[[ 5.00000000e-01 9.99954581e-01 4.53978719e-05]
[ 7.31058598e-01 8.80797029e-01 9.52574134e-01]]

tensorflow Sigmoid 應用