Tensorflow实现简单回归拟合问题

关键领会tensorflow中占位，sess.run()初始化，训练，和预测三个过程

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]   # 使得维度为[200,1]
noise = np.random.normal(0,0.02, x_data.shape) # 维度为[200,1]高斯分布的数据
y_data = np.square(x_data) + noise

# 定义两个占位符
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

# 定义神经网络的中间层
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)   # tanh 激活函数

# 定义神经网络的输出
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)   # tanh 激活函数

# 二次代价函数
loss = tf.reduce_mean(tf.square(y-prediction))

# 使用梯度下降法训练
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)  # 学习率为0.1

with tf.Session() as sess:
    # 变量的初始化
    sess.run(tf.global_variables_initializer())
    # 训练2000次
    for i in range(2000):
        sess.run(train_step,feed_dict={x:x_data, y:y_data})
        if i%100==0:
            print("step " + str(i))

    # 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()