本套视频基于: https://www.bilibili.com/video/av20542427?p=4
一. 02-1 创建图,启动图
# coding: utf-8
# In[4]:
import tensorflow as tf
# In[6]:
#创建一个常量op
m1 = tf.constant([[3,4]])
#创建一个常量op
m2 = tf.constant([[1],[5]])
#创建一个矩阵乘法op,把m1和m2传入
product = tf.matmul(m1,m2)
print(product)
# In[8]:
#定义一个会话,启动默认图
sess = tf.Session()
#调用sess的run方法来执行矩阵乘法op
#run(producy)触发了图中的3个op
result = sess.run(product)
print(result)
sess.close()
# In[9]:
#或者以下方法也可以,并且这样的方法,可以不用.close()
with tf.Session() as sess:
#调用sess的run方法来执行矩阵乘法op
#run(producy)触发了图中的3个op
result = sess.run(product)
print(result)
二. 02-2 变量
# coding: utf-8
# In[1]:
import tensorflow as tf
# In[2]:
x = tf.Variable([1,2])
a = tf.constant([3,3])
#增加一个减法op
sub = tf.subtract(x,a)
#增加一个加法op
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))
# In[9]:
#创建一个变量,初始化为0
state = tf.Variable(0,name='counter')
#创建一个op,作用是使state加1
new_value = tf.add(state,1)
#tensorflow中不能直接用等号赋值,而要调用这个方法。
update = tf.assign(state,new_value)
#变量初始化
#并且这一步只能在变量已经声明之后
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))
三. 02-3 Fetch and Feed
# coding: utf-8
# In[6]:
import tensorflow as tf
# In[7]:
#Fetch
input1 = tf.constant(3.0)
input2 = tf.constant(2.0)
input3 = tf.constant(5.0)
add = tf.add(input2,input3)
mul = tf.multiply(input1,add)
with tf.Session() as sess:
result = sess.run([mul,add])
print(result)
# In[8]:
#Feed
#创建占位符
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.multiply(input1,input2)
with tf.Session() as sess:
#feed的数据以字典的形式传入
print(sess.run(output,feed_dict={input1:[7.],input2:[2.]}))
四. 02-4 tensorflow简单示例
# coding: utf-8
# In[1]:
import tensorflow as tf
import numpy as np
# In[5]:
#使用numpy生成100个随机点
x_data = np.random.rand(100)
y_data = x_data * 0.1 +0.2
#构造一个线性模型
b = tf.Variable(0.)
k = tf.Variable(0.)
y = k*x_data + b
#二次代价函数
loss = tf.reduce_mean(tf.square(y_data-y))
#定义一个梯度下降法来进行训练的优化器
optimizer = tf.train.GradientDescentOptimizer(0.2)
#最小化代价函数
train = optimizer.minimize(loss)
#初始化变量
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]))