import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#使用numpy生成200個隨機點,范圍從-0.5到0.5均勻分布,增加一個維度得到200行1列的數據(生成二維數據)
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
#生成隨機噪聲,形狀和x_data相同
noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data)+noise
#定義連個placeholder,行不確定,列為1
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])
#定義神經網絡中間層
#權值隨機數,1行(輸入層1個神經元),10列(中間層10個神經元)
Weights_L1 = tf.Variable(tf.random_normal([1,10]))
#10個偏置值
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)
#定義神經網絡輸出層
Weights_L2 = tf.Variable(tf.random_normal([10,1]))
#1個偏置值
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)
#二次代價函數
loss = tf.reduce_mean(tf.square(y-prediction))
#梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
with tf.Session() as sess:
#變量初始化
sess.run(tf.global_variables_initializer())
#訓練2000次,使用placeholder往x,y 傳入x_data,y_data
for _ in range(2000):
sess.run(train_step,feed_dict={x:x_data,y:y_data})
#獲得預測值
prediction_value = sess.run(prediction,feed_dict={x:x_data})
#畫圖
plt.figure()
#散點圖
plt.scatter(x_data,y_data)
#紅色的實線,寬度為5
plt.plot(x_data,prediction_value,'r-',lw=5)
plt.show()