tensorflow 控制流操作,条件判断和循环操作
Control flow operations: conditionals and loops
When building complex models such as recurrent neural networks you may need to control the flow of operations through conditionals and loops. In this section we introduce a number of commonly used control flow ops.
Let’s assume you want to decide whether to multiply to or add two given tensors based on a predicate. This can be simply implemented with tf.cond which acts as a python “if” function:
a = tf.constant(1)
b = tf.constant(2)
p = tf.constant(True)
x = tf.cond(p, lambda: a + b, lambda: a * b)
print(tf.Session().run(x))
Since the predicate is True in this case, the output would be the result of the addition, which is 3.
Most of the times when using TensorFlow you are using large tensors and want to perform operations in batch. A related conditional operation is tf.where, which like tf.cond takes a predicate, but selects the output based on the condition in batch.
a = tf.constant([1, 1])
b = tf.constant([2, 2])
p = tf.constant([True, False])
x = tf.where(p, a + b, a * b)
print(tf.Session().run(x))
This will return [3, 2].
Another widely used control flow operation is tf.while_loop. It allows building dynamic loops in TensorFlow that operate on sequences of variable length. Let’s see how we can generate Fibonacci sequence with tf.while_loops:
n = tf.constant(5)
def cond(i, a, b):
return i < n
def body(i, a, b):
return i + 1, b, a + b
i, a, b = tf.while_loop(cond, body, (2, 1, 1))
print(tf.Session().run(b))
This will print 5. tf.while_loops takes a condition function, and a loop body function, in addition to initial values for loop variables. These loop variables are then updated by multiple calls to the body function until the condition returns false.
Now imagine we want to keep the whole series of Fibonacci sequence. We may update our body to keep a record of the history of current values:
n = tf.constant(5)
def cond(i, a, b, c):
return i < n
def body(i, a, b, c):
return i + 1, b, a + b, tf.concat([c, [a + b]], 0)
i, a, b, c = tf.while_loop(cond, body, (2, 1, 1, tf.constant([1, 1])))
print(tf.Session().run(c))
Now if you try running this, TensorFlow will complain that the shape of the the fourth loop variable is changing. So you must make that explicit that it’s intentional:
i, a, b, c = tf.while_loop(
cond, body, (2, 1, 1, tf.constant([1, 1])),
shape_invariants=(tf.TensorShape([]),
tf.TensorShape([]),
tf.TensorShape([]),
tf.TensorShape([None])))
This is not only getting ugly, but is also somewhat inefficient. Note that we are building a lot of intermediary tensors that we don’t use. TensorFlow has a better solution for this kind of growing arrays. Meet tf.TensorArray. Let’s do the same thing this time with tensor arrays:
n = tf.constant(5)
c = tf.TensorArray(tf.int32, n)
c = c.write(0, 1)
c = c.write(1, 1)
def cond(i, a, b, c):
return i < n
def body(i, a, b, c):
c = c.write(i, a + b)
return i + 1, b, a + b, c
i, a, b, c = tf.while_loop(cond, body, (2, 1, 1, c))
c = c.stack()
print(tf.Session().run(c))
TensorFlow while loops and tensor arrays are essential tools for building complex recurrent neural networks. As an exercise try implementing beam search using tf.while_loops. Can you make it more efficient with tensor arrays?
更多教程:http://www.tensorflownews.com/
tensorflow 控制流操作,条件判断和循环操作的更多相关文章
- Python学习笔记——基础篇【第一周】——变量与赋值、用户交互、条件判断、循环控制、数据类型、文本操作
目录 Python第一周笔记 1.学习Python目的 2.Python简史介绍 3.Python3特性 4.Hello World程序 5.变量与赋值 6.用户交互 7.条件判断与缩进 8.循环控制 ...
- python自学-day2(变量、if条件判断、运算符操作)
1.变量 变量只是用于保存内存位置,将变量存储在内存中的作用,方便后面调用,这意味着,在创建变量时会在内存中开辟一个空间. 变量命名规则: 由字母.数字.下划线(_)组成 不能以数字开头 不能使用 P ...
- 5-3 bash脚本编程之二 条件判断
1. 条件测试的表达式 1. [ expression ] :注意这个中括号的前后都有一个空格 2. [[ expression ]] 3. test expression 2.条件判断的类型 1. ...
- python Django教程 之模板渲染、循环、条件判断、常用的标签、过滤器
python3.5 manage.py runserver python Django教程 之模板渲染.循环.条件判断.常用的标签.过滤器 一.Django模板渲染模板 1. 创建一个 zqxt_tm ...
- shell 条件判断语句整理
常用系统变量 1) $0 当前程式的名称 2) $n 当前程式的第n个参数,n=1,2,…9 3) $* 当前程式的任何参数(不包括程式本身) 4) ...
- python基础-编码_if条件判断
一.第一句Python代码 在 /home/dev/ 目录下创建 hello.py 文件,内容如下: [root@python-3 scripts]# cat hello.py #!/usr/bin/ ...
- oracle触发器加条件判断
oracle触发器加条件判断,如果某个字段,isnode=0,那么不执行下面的方法,数据如下: create or replace trigger tr_basestation_insert_emp ...
- bash脚本编程之二 条件判断and 逻辑运算
1.条件测试结构 1) if/then结构: 判断命令列表的退出码是否为0,0为成功. 如果if和then在条件判断的同一行上的话, 必须使用分号来结束if表达式: if和then都是关键字. 关键字 ...
- [Shell]条件判断与流程控制:if, case, for, while, until
---------------------------------------------------------------------------------------------------- ...
随机推荐
- CSS的五种定位方式
CSS中一共有五种定位: position:static:默认值 position:absolute:绝对定位 position:relative:相对对定位 position:fixed:固定定位 ...
- xshell6使用的命令
我们进入Xshell的界面之后连接上Linux服务器 常用命令: (1)命令ls——列出文件 ls -la 给出当前目录下所有文件的一个长列表,包括以句点开头的“隐藏”文件 ls a* 列出当前目录下 ...
- 【算法记事本#NLP-1】最大匹配算法分词
本文地址:https://www.cnblogs.com/oberon-zjt0806/p/12409536.html #NLP-1 最大匹配算法(MM) 最大匹配算法(Maximum Matchin ...
- No CPU/ABI system image available for this target
在创建AVD设备的时候无法正常创建虚拟设备,CPU选项不能选择. 下面报错:No CPU/ABI system image available for this target 是因为SDK里面缺少了s ...
- Hibernate入门之注解@Column详解
前言 上一节我们讲解了Hibernate的主键生成策略,本节我们继续来讲讲Hibernate中针对列的映射即@Column注解,文中若有错误之处,还望指正. @Column注解详解 我们看到如上针对列 ...
- css自定义 range radio select的样式滑轮,按钮,选择框
写在前面: 之前踩坑css的时候,遇到滑轮,按钮,选择框这类型的东西,为了页面效果,总是需要自定义他们的样式,而不使用他们的默认样式.当时写的时候,我也是蛮头疼的,弄了个demo,链接在下面.对此做个 ...
- Slog64_项目上线之ArthurSlog个人网站上线3
ArthurSlog SLog-64 Year·1 Guangzhou·China September 9th 2018 ArthurSlog Page GitHub NPM Package Page ...
- SpringCloud第二代实战系列:一文搞定Nacos实现服务注册与发现
一.背景:SpringCloud 生态圈 在正式开始本篇文章之前我们先岔开来讲一下SpringCloud的生态圈. SpringCloud大家都比较熟悉了,它制定了分布式系统的标准规范,做了高度抽象和 ...
- 利用Python爬取OPGG上英雄联盟英雄胜率及选取率信息
一.分析网站内容 本次爬取网站为opgg,网址为:” http://www.op.gg/champion/statistics” 由网站界面可以看出,右侧有英雄的详细信息,以Garen为例,胜率为53 ...
- c++作业22题
一.单选题(共22题,100.0分) 1 已知int i=5,下列do-while循环语句的循环次数是 do{ cout<<i - -<<endl; i - -; }while ...