tensorflow2-构造全连接神经网络

整体描述：

          使用随机数，生成样本数据，作为输入，然后经过中间的隐藏层，对数据进行拟合。

网络结构：

          1个输入单元，10个隐含单元，1个输出单元。

y# -*- coding: utf-8 -*-
"""
Created on Thu May 16 10:49:34 2019

@author: 666
"""
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

#生成200个在-0.5到0.5等距分布的点
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
noise = np.random.normal(0.0,0.02,x_data.shape)
y_data = np.square(x_data)+noise

#定义两个占位的,x,y行不确定，一列的数据
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

#定义神经网络中间层 1个神经元作为输入，中间10个神经元作为中间层
Weight_L1 = tf.Variable(tf.random_normal([1,10]))
Biases_L1 = tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1 = tf.matmul(x,Weight_L1) + Biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)

#定义输出层
Weight_L2 = tf.Variable(tf.random_normal([10,1]))
Biases_L2 = tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weight_L2) + Biases_L2
prediction = tf.nn.tanh(Wx_plus_b_L2)

#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)


init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for step in range(2000):
        sess.run(train_step,feed_dict = {x:x_data,y:y_data})
        if step%20 == 0:
            print(step,sess.run([Weight_L1,Biases_L1]))
    
    #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()

结果：