一、线性回归
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#使用numpy生成100个随机点
x_data = np.random.rand(100)
y_data = x_data*0.1 + 0.2 #真实值
#构建一个线性模型
b = tf.Variable(0.)
k = tf.Variable(0.)
y = k*x_data + b #预测值
#定义一个二次代价函数
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)
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('当前步数:%s, k = %f ,b = %f' % (step, sess.run(k), sess.run(b)))
prediction_value = sess.run(y)
#画图
plt.figure()
plt.scatter(x_data, y_data)
plt.plot(x_data, prediction_value, 'r-', lw=1)
plt.show()
二、非线性回归
首先使用numpy
生成200个随机点
x_data = np.linspace(-0.5, 0.5, 200)
print(x_data.shape)
输出:这样只有一个维度
(200,)
生成2维数组
x_data = np.linspace(-0.5, 0.5, 200)[:, np.newaxis]
print(x_data.shape)
输出:
(200, 1)
完整代码:
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#使用numpy生成200个随机点
x_data = np.linspace(-0.5, 0.5, 200)[:, np.newaxis] #200行1列
noise = np.random.normal(0, 0.02, x_data.shape) #创建干扰信号
y_data = np.square(x_data) + noise #样本真是值
#定义两个placeholder
x = tf.placeholder(tf.float32, [None, 1])
y = tf.placeholder(tf.float32, [None, 1])
#定义一神经网络中间层
Weights_L1 = tf.Variable(tf.random_normal([1, 10]))
biases_L1 = tf.Variable(tf.zeros([1, 10]))
Wx_plus_b_L1 = tf.matmul(x, Weights_L1) + biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)
#定义神经网络输出层
Weights_L2 = tf.Variable(tf.random.normal([10, 1]))
biases_L2 = tf.Variable(tf.zeros([1, 1]))
Wx_plus_b_L2 = tf.matmul(L1, Weights_L2) + biases_L2
prediction = tf.nn.tanh(Wx_plus_b_L2)
#二次代价函数
loss = tf.reduce_mean(tf.square(y - prediction))
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
with tf.Session() as sess:
#变量初始化
sess.run(tf.global_variables_initializer())
for _ in range(2000):
sess.run(train_step, feed_dict={x:x_data, y:y_data})
#获取预测值
prediction_value = sess.run(prediction, feed_dict={x:x_data})
#画图
plt.figure()
plt.scatter(x_data, y_data)
plt.plot(x_data, prediction_value, 'r-', lw=5)
plt.show()
得出: