机器学习系列-tensorflow-02-基本操作运算

Posted 2021-01-16 brightyuxl

tensorflow常数操作

import tensorflow as tf
# 定义两个常数，a和b
a = tf.constant(2)
b = tf.constant(3)
# 执行默认图运算
with tf.Session() as sess:
    print("a=2, b=3")
    print("Addition with constants: %i" % sess.run(a+b))
    print("Multiplication with constants: %i" % sess.run(a*b))

结果
a=2, b=3
Addition with constants: 5
Multiplication with constants: 6

---

tensorflow变量操作

变量作为图形输入，构造器的返回值作为变量的输出，在运行会话时，传入变量的值，在进行运算。

import tensorflow as tf
# 定义两个变量
a = tf.placeholder(tf.int16)
b = tf.placeholder(tf.int16)

# 定义加法和乘法运算
add = tf.add(a, b)
mul = tf.multiply(a, b)

# 启动默认图进行运算
with tf.Session() as sess:
    # 传入变量值，进行运算
    print("Addition with variables: %i" % sess.run(add, feed_dict={a: 2, b: 3}))
    print("Multiplication with variables: %i" % sess.run(mul, feed_dict={a: 2, b: 3}))

结果
Addition with variables: 5
Multiplication with variables: 6

---

tensorflow矩阵常量操作

import tensorflow as tf
# 创建一个1X2的常数矩阵
matrix1 = tf.constant([[3., 3.]])
# 创建一个2X1的常数矩阵
matrix2 = tf.constant([[2.],[2.]])
# 定义矩阵乘法运算multiplication
product = tf.matmul(matrix1, matrix2)
# 启动默认图进行运算
with tf.Session() as sess:
    result = sess.run(product)
    print(result)

结果
[[12.]]

简单例子

import tensorflow as tf
hello = tf.constant('Hello, TensorFlow!')
sess = tf.Session()
print(sess.run(hello))

结果
b‘Hello, TensorFlow!‘

---

参考：
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/