TensorFlow实战框架Chp5-前向传播的理解--偏置项biases加法

• TensorFlow实战框架Chp5-前向传播的理解–偏置项加法

# -*- coding: utf-8 -*-
"""
Created on Fri Jul 20 21:49:21 2018

@author: muli
"""

import tensorflow as tf

a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3]) 
b = tf.constant([7, 8, 9, 10, 11, 12,2,2,2,2,2,2], shape=[3, 4]) 
c = tf.Variable(tf.constant(1,shape=[4]))

d=tf.matmul(a, b)

e=d+c

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(a))
    print(sess.run(b))
    print(sess.run(c))
    print("------------------------")
    print(sess.run(d))
    print("------------------------")
    print(sess.run(e))

• 可以看出，偏置项biases为一维数组
• 其值依次与二维数组中的每一行相加

[[1 2 3]
 [4 5 6]]
[[ 7  8  9 10]
 [11 12  2  2]
 [ 2  2  2  2]]
[1 1 1 1]
------------------------
[[ 35  38  19  20]
 [ 95 104  58  62]]
------------------------
[[ 36  39  20  21]
 [ 96 105  59  63]]