[TF进阶] 线性回归

实例1：从一组看似混乱的数据中找出?≈2?的规律

使用神经网络找出其中的规律

1. 准备数据

y=2x + noise

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


plotdata = { "batchsize":[], "loss":[] }
def moving_average(a, w=10):
    if len(a) < w: 
        return a[:]    
    return [val if idx < w else sum(a[(idx-w):idx])/w for idx, val in enumerate(a)]


#生成模拟数据
train_X = np.linspace(-1, 1, 100)
train_Y = 2 * train_X + np.random.randn(*train_X.shape) * 0.3 # y=2x，但是加入了噪声
#显示模拟数据点
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.legend()
plt.show()

2. 搭建模型

• placeholder占位符X,Y
• W,b初始化随机[-1,1]参数

# 创建模型
# 占位符
X = tf.placeholder("float")
Y = tf.placeholder("float")
# 模型参数
W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.zeros([1]), name="bias")

# 前向结构
z = tf.multiply(X, W)+ b

• 反向传播

#反向优化
cost =tf.reduce_mean( tf.square(Y - z))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent

• 训练模型

# 初始化变量
init = tf.global_variables_initializer()
# 训练参数
training_epochs = 20
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        #显示训练中的详细信息
        if epoch % display_step == 0:
            loss = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
            print ("Epoch:", epoch+1, "cost=", loss,"W=", sess.run(W), "b=", sess.run(b))
            if not (loss == "NA" ):
                plotdata["batchsize"].append(epoch)
                plotdata["loss"].append(loss)

    print (" Finished!")
    print ("cost=", sess.run(cost, feed_dict={X: train_X, Y: train_Y}), "W=", sess.run(W), "b=", sess.run(b))
    #print ("cost:",cost.eval({X: train_X, Y: train_Y}))

• 可视化

    #图形显示
    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()
    
    plotdata["avgloss"] = moving_average(plotdata["loss"])
    plt.figure(1)
    plt.subplot(211)
    plt.plot(plotdata["batchsize"], plotdata["avgloss"], 'b--')
    plt.xlabel('Minibatch number')
    plt.ylabel('Loss')
    plt.title('Minibatch run vs. Training loss')
     
    plt.show()

Epoch: 1 cost= 0.7557078 W= [0.7214475] b= [0.35542127]
Epoch: 3 cost= 0.1474243 W= [1.6094706] b= [0.11747434]
Epoch: 5 cost= 0.09202065 W= [1.8502718] b= [0.02679843]
Epoch: 7 cost= 0.08676976 W= [1.9127239] b= [0.00286189]
Epoch: 9 cost= 0.08602997 W= [1.9288754] b= [-0.00333569]
Epoch: 11 cost= 0.08588005 W= [1.9330516] b= [-0.00493819]
Epoch: 13 cost= 0.08584406 W= [1.9341311] b= [-0.00535254]
Epoch: 15 cost= 0.08583492 W= [1.9344107] b= [-0.00545979]
Epoch: 17 cost= 0.08583256 W= [1.9344833] b= [-0.00548763]
Epoch: 19 cost= 0.08583197 W= [1.9345018] b= [-0.00549479]
FInished!
cost= 0.08583186 W= [1.934505] b= [-0.00549596]

    print ("x=0.2，z=", sess.run(z, feed_dict={X: 0.2}))

x=0.2, z= [0.38140503]

完整代码

# -*- coding: utf-8 -*-
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


plotdata = { "batchsize":[], "loss":[] }
def moving_average(a, w=10):
    if len(a) < w: 
        return a[:]    
    return [val if idx < w else sum(a[(idx-w):idx])/w for idx, val in enumerate(a)]


#生成模拟数据
train_X = np.linspace(-1, 1, 100)
train_Y = 2 * train_X + np.random.randn(*train_X.shape) * 0.3 # y=2x，但是加入了噪声
#显示模拟数据点
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.legend()
plt.show()




# 创建模型
# 占位符
X = tf.placeholder("float")
Y = tf.placeholder("float")
# 模型参数
W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.zeros([1]), name="bias")

# 前向结构
z = tf.multiply(X, W)+ b

#反向优化
cost =tf.reduce_mean( tf.square(Y - z))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent

# 初始化变量
init = tf.global_variables_initializer()
# 训练参数
training_epochs = 20
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        #显示训练中的详细信息
        if epoch % display_step == 0:
            loss = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
            print ("Epoch:", epoch+1, "cost=", loss,"W=", sess.run(W), "b=", sess.run(b))
            if not (loss == "NA" ):
                plotdata["batchsize"].append(epoch)
                plotdata["loss"].append(loss)

    print (" Finished!")
    print ("cost=", sess.run(cost, feed_dict={X: train_X, Y: train_Y}), "W=", sess.run(W), "b=", sess.run(b))
    #print ("cost:",cost.eval({X: train_X, Y: train_Y}))

    #图形显示
    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()
    
    plotdata["avgloss"] = moving_average(plotdata["loss"])
    plt.figure(1)
    plt.subplot(211)
    plt.plot(plotdata["batchsize"], plotdata["avgloss"], 'b--')
    plt.xlabel('Minibatch number')
    plt.ylabel('Loss')
    plt.title('Minibatch run vs. Training loss')
     
    plt.show()

    print ("x=0.2，z=", sess.run(z, feed_dict={X: 0.2}))
    

---

实例2： 通过字典类型定义输入节点

# 创建模型
# 占位符

inputdict = {
    'x': tf.placeholder("float"),
    'y': tf.placeholder("float")
}

完整代码

# -*- coding: utf-8 -*-
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


plotdata = { "batchsize":[], "loss":[] }
def moving_average(a, w=10):
    if len(a) < w: 
        return a[:]    
    return [val if idx < w else sum(a[(idx-w):idx])/w for idx, val in enumerate(a)]


#生成模拟数据
train_X = np.linspace(-1, 1, 100)
train_Y = 2 * train_X + np.random.randn(*train_X.shape) * 0.3 # y=2x，但是加入了噪声
#图形显示
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.legend()
plt.show()




# 创建模型
# 占位符

inputdict = {
    'x': tf.placeholder("float"),
    'y': tf.placeholder("float")
}


# 模型参数
W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.zeros([1]), name="bias")
# 前向结构
z = tf.multiply(inputdict['x'], W)+ b

#反向优化
cost =tf.reduce_mean( tf.square(inputdict['y'] - z))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent

# 初始化变量
init = tf.global_variables_initializer()
#参数设置
training_epochs = 20
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={inputdict['x']: x, inputdict['y']: y})

        #显示训练中的详细信息
        if epoch % display_step == 0:
            loss = sess.run(cost, feed_dict={inputdict['x']: train_X, inputdict['y']:train_Y})
            print ("Epoch:", epoch+1, "cost=", loss,"W=", sess.run(W), "b=", sess.run(b))
            if not (loss == "NA" ):
                plotdata["batchsize"].append(epoch)
                plotdata["loss"].append(loss)

    print (" Finished!")
    print ("cost=", sess.run(cost, feed_dict={inputdict['x']: train_X, inputdict['y']: train_Y}), "W=", sess.run(W), "b=", sess.run(b))

    #图形显示
    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()
    
    plotdata["avgloss"] = moving_average(plotdata["loss"])
    plt.figure(1)
    plt.subplot(211)
    plt.plot(plotdata["batchsize"], plotdata["avgloss"], 'b--')
    plt.xlabel('Minibatch number')
    plt.ylabel('Loss')
    plt.title('Minibatch run vs. Training loss')
     
    plt.show()

    print ("x=0.2，z=", sess.run(z, feed_dict={inputdict['x']: 0.2}))

---

实例3：直接定义输入节点

# -*- coding: utf-8 -*-
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt




#生成模拟数据
train_X =np.float32( np.linspace(-1, 1, 100))
train_Y = 2 * train_X + np.random.randn(*train_X.shape) * 0.3 # y=2x，但是加入了噪声
#图形显示
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.legend()
plt.show()


# 创建模型

# 模型参数
W = tf.Variable(tf.random_normal([1]), name="weight")
b = tf.Variable(tf.zeros([1]), name="bias")
# 前向结构
z = tf.multiply(W, train_X)+ b

#反向优化
cost =tf.reduce_mean( tf.square(train_Y - z))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent

# 初始化变量
init = tf.global_variables_initializer()
#参数设置
training_epochs = 20
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer)

        #显示训练中的详细信息
        if epoch % display_step == 0:
            loss = sess.run(cost)
            print ("Epoch:", epoch+1, "cost=", loss,"W=", sess.run(W), "b=", sess.run(b))


    print (" Finished!")
    print ("cost=", sess.run(cost), "W=", sess.run(W), "b=", sess.run(b))

---

实例4：通过字典类型定义学习参数

# -*- coding: utf-8 -*-
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


plotdata = { "batchsize":[], "loss":[] }
def moving_average(a, w=10):
    if len(a) < w: 
        return a[:]    
    return [val if idx < w else sum(a[(idx-w):idx])/w for idx, val in enumerate(a)]


#生成模拟数据
train_X = np.linspace(-1, 1, 100)
train_Y = 2 * train_X + np.random.randn(*train_X.shape) * 0.3 # y=2x，但是加入了噪声
#图形显示
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.legend()
plt.show()




# 创建模型
# 占位符
X = tf.placeholder("float")
Y = tf.placeholder("float")
# 模型参数

paradict = {
    'w': tf.Variable(tf.random_normal([1])),
    'b': tf.Variable(tf.zeros([1]))
}


# 前向结构
z = tf.multiply(X, paradict['w'])+ paradict['b']

#反向优化
cost =tf.reduce_mean( tf.square(Y - z))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent

# 初始化变量
init = tf.global_variables_initializer()
#参数设置
training_epochs = 20
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        #显示训练中的详细信息
        if epoch % display_step == 0:
            loss = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
            print ("Epoch:", epoch+1, "cost=", loss,"W=", sess.run(paradict['w']), "b=", sess.run(paradict['b']))
            if not (loss == "NA" ):
                plotdata["batchsize"].append(epoch)
                plotdata["loss"].append(loss)

    print (" Finished!")
    print ("cost=", sess.run(cost, feed_dict={X: train_X, Y: train_Y}), "W=", sess.run(paradict['w']), "b=", sess.run(paradict['b']))

    #图形显示
    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(paradict['w']) * train_X + sess.run(paradict['b']), label='Fitted line')
    plt.legend()
    plt.show()
    
    plotdata["avgloss"] = moving_average(plotdata["loss"])
    plt.figure(1)
    plt.subplot(211)
    plt.plot(plotdata["batchsize"], plotdata["avgloss"], 'b--')
    plt.xlabel('Minibatch number')
    plt.ylabel('Loss')
    plt.title('Minibatch run vs. Training loss')
     
    plt.show()

    print ("x=0.2，z=", sess.run(z, feed_dict={X: 0.2}))