tensorflow入门学习笔记 6.非线性回归

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

# 线性回归

# 随机生成200个点
x_data = np.linspace(-0.5, 0.5, 200)[:, np.newaxis]   # 在-0.5~0.5之间随机取200个点 并增加维度 200行1列
noise = np.random.normal(0, 0.02, x_data.shape)     # 生成随机噪点
y_data = np.square(x_data) +noise

# 创建占位符
x = tf.placeholder(tf.float32, [None, 1])   # 1列 不限行
y = tf.placeholder(tf.float32, [None, 1])   # 1列 不限行

# 定义神经网路中间层
Weights_L1 = tf.Variable(tf.random_normal([1, 10]))   # 随机数变量  1行10列
biases_L1 = tf.Variable(tf.zeros([1, 10]))
Wx_plus_b_L1 = tf.matmul(x, Weights_L1) + biases_L1     # 两个矩阵相乘再加一个
L1 = tf.nn.tanh(Wx_plus_b_L1)   # 双曲正切函数

# 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))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for _ in range(2000):
        sess.run(train_step, feed_dict={x: x_data, y: y_data})

    # 获得预测值
    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()