第3章 TensorFlow基础之——以逻辑回归拟合二维数组

使用神经网络归纳出y = 2x的模型
程序：

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

plotdata = {"batchsize":[],"lose":[]}
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)]

train_X = np.linspace(-1,1,100)
train_Y = 2*train_X+np.random.randn(*train_X.shape )* 0.3

plt.plot(train_X,train_Y,'ro',label = 'original data')
plt.legend()
plt.show()
# 创建模型
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')
# 前项结构
z = tf.multiply(W,X)+b   # multiply两个数相乘

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

# 初始化所有变量
init = tf.global_variables_initializer()
# 定义参数
training_epochs = 20
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)
    plotdata = {'batchsize':[],'loss':[]}             # 存放批次值和损失值
    # 向模型输入数据
    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))



# 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 = 'Fittedline')
    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()

    # 使用训练好的模型
print("x = 0.2,z=",sess.run(z,feed_dict={X: 0.2}))

结果：

Epoch: 1 cost= 0.25625253 W= [1.4087313] b= [0.11553277]
Epoch: 3 cost= 0.11751542 W= [1.8382502] b= [-0.00680665]
Epoch: 5 cost= 0.106281 W= [1.9539326] b= [-0.05048434]
Epoch: 7 cost= 0.1054758 W= [1.9839219] b= [-0.06198044]
Epoch: 9 cost= 0.10541014 W= [1.9916776] b= [-0.06495647]
Epoch: 11 cost= 0.105402686 W= [1.9936825] b= [-0.06572581]
Epoch: 13 cost= 0.105401404 W= [1.994201] b= [-0.06592486]
Epoch: 15 cost= 0.10540111 W= [1.994335] b= [-0.06597631]
Epoch: 17 cost= 0.10540103 W= [1.9943694] b= [-0.06598942]
Epoch: 19 cost= 0.10540103 W= [1.9943788] b= [-0.06599298]
Finished
cost= 0.10540102 W= [1.9943801] b= [-0.06599353]