Tensorflow例程

Tensorflow例程

1.创建图

import  tensorflow as tf

 

m1=tf.constant([[3,3]])

m2=tf.constant([[4],[4]])

product=tf.matmul(m1,m2)

printf(product)

//输出一个tensor  shapw=(1,1),dtype=int32

 

sess=tf.Session()

result=sess.run.(product)

print(result)

sess.close()

//或者

with tf.Session() as sess:

result=sess.run.(product)

print(result)

 

2.变量操作

import  tensorflow as tf

 

x=tf.Variable([1,2])

a=tf.constant([3,3])

sub=tf.subtract(x,a)

add=tf.add(x,sub)

init=tf.global_variables_initializer()

with tf.Session() as sess:

sess.run.(init)

print(sess.run.(sub))

print(sess.run.(add))

 

state=tf.Variable(0,name='counter')

new_value=tf.add(state,1)

update=tf.assign(state,new_value)

init=tf.global_variables_initializer()

with tf.Session() as sess:

sess.run.(init)

print(sess.run.(state))

for _in range(5):

sess.run(update)

print(sess.run.(state))

 

3.fetch and feed

import  tensorflow as tf

 

input1=tf.constant(3,0)

input2=tf.constant(2,0)

input3=tf.constant(1,0)

add=tf.add(input2,input3)

mul=tf.multiply(input1,add)

 

with tf.Session() as sess:

result=sess.run([mul,add])//fetch可以运行多个op

print(result)

input1=tf.placeholder(tf.float32)

input2=tf.placeholder(tf.float32)

output=tf.multiply(input1,input2)

with tf.Session() as sess:

print(sess.run(output,feed_dict={input1:[3.],input2:[4.]}))//feed的数据以字典的形式传入

4.线性模型

import  tensorflow as tf

import numpy as np

x_data=np.random.rand(100)

y_data=x_data*0.1+0.8

b=tf.Variable(0.)

k=tf.Variable(0.)

y=  k*x_data+b

loss=tf.reduce_mean(tf.square(y_data-y))

optimizer=tf.train.GradientDescentOptimizer(0.01)

train=optimizer.minimize(loss)//最小化代价函数

init=tf.global_variables_initializer()

with tf.Session() as sess:

sess.run(init)

for step in range(201)

sess.run(train)

if step%20==0:

print(step,sess.run([k,b]))