1.2简单的tensorflow神经网络

---

前言

使用的版本tensorflow1.0，2.0部分做了改动要改改语法，用一个200X1，1X10，10X1的神经网络预测一个二次函数，抛物线

---

提示：以下是本篇文章正文内容，下面案例可供参考

一、以一个简单5X1神经网络为例

5X1=>1X3=>3X1=>1

二、代码和结果

代码如下（示例）：

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

x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
print(x_data)

noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data)+noise

#plt.figure()
#plt.scatter(x_data,y_data)
#plt.show()


x = tf.placeholder(tf.float32, [None, 1])#占位符

y = tf.placeholder(tf.float32, [None, 1])
#hide 10
w_l1 = tf.Variable(tf.random.normal([1,10]))
b_l1 = tf.Variable(tf.random.normal([1,10]))
w_b_l1 = tf.matmul(x,w_l1)+b_l1

L1 = tf.nn.tanh(w_b_l1)

#out 
Weights_L2 = tf.Variable(tf.random.normal([10, 1]))

Biases_L2 = tf.Variable(tf.random.normal([1, 1]))

Wx_plus_b_L2 = tf.matmul(L1, Weights_L2) + Biases_L2

pred = tf.nn.tanh(Wx_plus_b_L2)

# 损失函数

loss = tf.reduce_mean(tf.square(y - pred))

# 训练

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

with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)

    for i in range(1000):
        sess.run(train,feed_dict={x:x_data,y:y_data})#feed投喂数据
        print("第{0}次，loss = {1}".format(i, sess.run(loss,feed_dict={x: x_data, y: y_data})))
    pred_vaule = sess.run(pred, feed_dict={x: x_data})

    plt.figure()

    plt.scatter(x_data, y_data)

    plt.plot(x_data, pred_vaule, 'r-', lw=5)
plt.show()