变量初始化:tf.global_variables_initializer()
np.newaxis的作用是在这一个位置增加一个维
占位符:tf.placeholder()
feed有具体的满足要求。若有错误把填充进去的变量先运行:如:y_data = sess.run(y_data)
下面是一个简单的线性回归实例
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#使用numpy定义200个随机点,范围在[-0.5,0.5]
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
noise = np.random.normal(0,0.02,x_data.shape)
y_data = tf.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)
#定义神经网络输出层
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))
#使用梯度下降法训练
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
with tf.Session() as sess:
#变量初始化
sess.run(tf.global_variables_initializer())
#满足feed的条件要先执行Y_data
y_data=sess.run(y_data)
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})
#画散点图
plt.figure()
plt.scatter(x_data,y_data)
plt.plot(x_data,prediction_value,‘r-’,lw = 2)
plt.show()