Tensorflow | 基本函数介绍

努力在北京混出人样

发布于 2019-02-18 15:53:25

5320

发布于 2019-02-18 15:53:25

文章被收录于专栏：祥子的故事

这次来总结下这几天学习tensorflow的心得，包含了一些基本的函数，例如，加减乘除等，下面来一一介绍，并给出具体的例子。

两个小的tips

我的版本：anaconda 4.2 tensorflow 0.12.1
若是你不知道如何在windows下安装tensorflow，可以依照我的博客：https://cloud.tencent.com/developer/article/1122014 ，遵循上面的顺序来做；若是安装过程中遇到问题，可以在博客下方留言，看到后会及时回答。

数值乘法mul

例如：a=3，b=3，a*b = 9

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.mul(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 3, b: 3}))

结果：9.0

数值和add

例如: a = 3, b=3 ,a+b = 6

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.add(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 3, b: 3}))

结果：6.0

数值减法sub

例如：a=3,b=3,a-b = 0

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.sub(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 3, b: 3}))

结果： 0.0

数值除法div

例如: a=3,b=3,a/b = 1.0

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.div(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 3, b: 3}))

结果: 1.0

数值取模mod

例如:a=3,b=3,a mod b = 0

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.mod(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 3, b: 3}))

结果: 0.0

数值绝对值abs

例如:a=-3, abs (a) = 3

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.abs(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3}))

结果： 3.0

数值非负值neg

例如:a=-3, neg (a) = 3

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.neg(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3}))

结果： 3.0

数值符号函数sign

例如:a=-3, neg (a) = 3

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.neg(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3}))

结果： 3.0

数值符号函数sign

例如: a=-3,sign(a) = -1

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.sign(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3}))

结果: -1.0

数值倒数inv

例如: a=-3,sign(a) = -1

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.sign(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3}))

结果: -1.0

数值平方square

例如: a=-3,square(a) = 9

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.square(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3}))

结果: 9.0

数值最近的整数round

例如: a=-3.6,round(a) = -4.0

import tensorflow as tf
y = tf.round(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3.6}))

结果: -4.0

例如: a=-3.3,round(a) = -3.0

import tensorflow as tf
y = tf.round(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3.3}))

结果：-3.0

数值平方根sqrt

例如: a=4,sqrt(a) = 2

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.sqrt(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 4}))

结果: 2.0

数值幂次pow

例如: a=2,b=3,pow(a,b) = 8

import tensorflow as tf
a = tf.placeholder(tf.float64)
b = tf.placeholder(tf.float64)
y = tf.pow(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 2, b: 3}))

结果: 8.0

数值最近的整数exp

例如: a=2,exp(a) = 7.38906

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.exp(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 2}))

结果: 7.38906

数值取对数log

例如: a=-3.6,round(a) = -4.0

import tensorflow as tf
a = tf.placeholder(tf.float32)
y = tf.log(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 2}))

结果: 0.69314718056

数值取最大值maximum

例如: a=-3.6, b = 2,maximum(a,b)=2

import tensorflow as tf
a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
y = tf.maximum(a,b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: -3.6,b: 2}))

结果: 2.0

数值最小值minimum

例如: a=2,b=3minimum(a) = 3

import tensorflow as tf
a = tf.placeholder(tf.float64)
b = tf.placeholder(tf.float64)
y = tf.minimum(a, b)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 2, b: 3}))

结果: 2.0

数值余弦函数cos

例如: a=2,cos(a) = -0.416146836547

import tensorflow as tf
a = tf.placeholder(tf.float64)
y = tf.cos(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 2}))

结果: -0.416146836547

数值正弦函数sin

例如: a=2,sin(a) = -0.416146836547

import tensorflow as tf
a = tf.placeholder(tf.float64)
y = tf.sin(a)
sess = tf.Session() 
print (sess.run(y, feed_dict={a: 2}))

结果: 0.909297426826

本文参与腾讯云自媒体同步曝光计划，分享自作者个人站点/博客。

原始发表：2017年01月18日，如有侵权请联系 cloudcommunity@tencent.com 删除

tensorflow

对象存储

本文分享自作者个人站点/博客前往查看

如有侵权，请联系 cloudcommunity@tencent.com 删除。

本文参与腾讯云自媒体同步曝光计划，欢迎热爱写作的你一起参与！

tensorflow

对象存储

登录后参与评论

0 条评论

热度