深度学习之tensorflow

Posted 哈哈丶Stupid

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了深度学习之tensorflow 相关的知识,希望对你有一定的参考价值。

一、TensorFlow简介

1.TensorFlow定义

   tensor  :张量,N维数组

   Flow   :  流,基于数据流图的计算

   TensorFlow : 张量从图像的一端流动到另一端的计算过程,是将复杂的数据结     构传输至人工智能神经网络中进行分析和处理的过程。


 

2. 工作模式:

    图graphs表示计算任务,图中的节点称之为op(operation) ,一个 op可以获得0个      或多个张量(tensor),通过创建会话(session)对象来执行计算,产生0个或多个tensor。 

   其工作模式分为两步:(1)define the computation graph

                                        (2)run the graph (with data) in session

 


 

3. 特点:

    (1)异步:一处写、一处读、一处训练

    (2)全局 : 操作添加到全局的graph中 , 监控添加到全局的summary中,

            参数/损失添加到全局的collection中

     (3)符号式的:创建时没有具体,运行时才传入


 

二、   代码

1 、定义神经网络的相关参数和变量

    

技术分享
 1 # -*- coding: utf-8 -*-
 2 # version:python 3.5
 3 import tensorflow as tf
 4 from numpy.random import RandomState
 5 
 6 batch_size = 8
 7 x = tf.placeholder(tf.float32, shape=(None, 2), name="x-input")
 8 y_ = tf.placeholder(tf.float32, shape=(None, 1), name=y-input)
 9 w1= tf.Variable(tf.random_normal([2, 1], stddev=1, seed=1))
10 y = tf.matmul(x, w1)
View Code

 

2、设置自定义的损失函数

     

技术分享
1 # 定义损失函数使得预测少了的损失大,于是模型应该偏向多的方向预测。
2 loss_less = 10
3 loss_more = 1
4 loss = tf.reduce_sum(tf.where(tf.greater(y, y_), (y - y_) * loss_more, (y_ - y) * loss_less))
5 train_step = tf.train.AdamOptimizer(0.001).minimize(loss)
View Code

 

3、生成模拟数据集

 

技术分享
1 rdm = RandomState(1)
2 X = rdm.rand(128,2)
3 Y = [[x1+x2+rdm.rand()/10.0-0.05] for (x1, x2) in X]
View Code

 

4、训练模型

 

技术分享
 1 with tf.Session() as sess:
 2     init_op = tf.global_variables_initializer()
 3     sess.run(init_op)
 4     STEPS = 5000
 5     for i in range(STEPS):
 6         start = (i*batch_size) % 128
 7         end = (i*batch_size) % 128 + batch_size
 8         sess.run(train_step, feed_dict={x: X[start:end], y_: Y[start:end]})
 9         if i % 1000 == 0:
10             print("After %d training step(s), w1 is: " % (i))
11             print sess.run(w1), "\n"
12     print "Final w1 is: \n", sess.run(w1)
View Code

结果:

After 0 training step(s), w1 is: 
[[-0.81031823]
 [ 1.4855988 ]] 

After 1000 training step(s), w1 is: 
[[ 0.01247112]
 [ 2.1385448 ]] 

After 2000 training step(s), w1 is: 
[[ 0.45567414]
 [ 2.17060661]] 

After 3000 training step(s), w1 is: 
[[ 0.69968724]
 [ 1.8465308 ]] 

After 4000 training step(s), w1 is: 
[[ 0.89886665]
 [ 1.29736018]] 

Final w1 is: 
[[ 1.01934695]
 [ 1.04280889]]

 

 

5、重新定义损失函数,使得预测多了的损失大,于是模型应该偏向少的方向预测

 

技术分享
 1 loss_less = 1
 2 loss_more = 10
 3 loss = tf.reduce_sum(tf.where(tf.greater(y, y_), (y - y_) * loss_more, (y_ - y) * loss_less))
 4 train_step = tf.train.AdamOptimizer(0.001).minimize(loss)
 5 
 6 with tf.Session() as sess:
 7     init_op = tf.global_variables_initializer()
 8     sess.run(init_op)
 9     STEPS = 5000
10     for i in range(STEPS):
11         start = (i*batch_size) % 128
12         end = (i*batch_size) % 128 + batch_size
13         sess.run(train_step, feed_dict={x: X[start:end], y_: Y[start:end]})
14         if i % 1000 == 0:
15             print("After %d training step(s), w1 is: " % (i))
16             print sess.run(w1), "\n"
17     print "Final w1 is: \n", sess.run(w1)
View Code

结果:

 

After 0 training step(s), w1 is: 
[[-0.81231821]
 [ 1.48359871]] 

After 1000 training step(s), w1 is: 
[[ 0.18643527]
 [ 1.07393336]] 

After 2000 training step(s), w1 is: 
[[ 0.95444274]
 [ 0.98088616]] 

After 3000 training step(s), w1 is: 
[[ 0.95574027]
 [ 0.9806633 ]] 

After 4000 training step(s), w1 is: 
[[ 0.95466018]
 [ 0.98135227]] 

Final w1 is: 
[[ 0.95525807]
 [ 0.9813394 ]]


以上是关于深度学习之tensorflow 的主要内容,如果未能解决你的问题,请参考以下文章

分享《深度学习之TensorFlow:入门原理与进阶实战》PDF+源代码

分享《深度学习之TensorFlow:入门原理与进阶实战》PDF+源代码

深度学习之卷积神经网络CNN及tensorflow代码实现示例

深度学习之TensorFlow:入门原理与进阶实战

深度学习之tensorflow

Tensorflow深度学习之十二:基础图像处理之二