常用的均方误差,作为损失函数
#coding:utf-8
"""
拟合出预测酸奶日销量的函数模型,
模拟真实场景数据,对y_增加噪声:-0.05~+0.05
"""
# 0.导入模块,生成数据集
import tensorflow as tf
import numpy as np
BATCH_SIZE = 8
# 随机种子SEED ,实际应用是不需要写的,我们模拟的随机数据和mooc课堂保持一致,方便debug
SEED = 2345
rdm = np.random.RandomState(SEED)
X = rdm.rand(32, 2)
# 模拟出来的数据 y_ 正确答案是两个输入集2特征之和,并且增加噪声
Y_ = [[x1+x2+(rdm.rand()/10.0-0.05)] for(x1, x2) in X]
# 1.定义神经网络的输入,参数和输出,定义向前传播过程
x = tf.placeholder(tf.float32, shape=(None, 2))
y_ = tf.placeholder(tf.float32, shape=(None, 1))
w1 = tf.Variable(tf.random_normal([2, 1], stddev=1,seed=1))
y = tf.matmul(x, w1)
# 2.定义损失函数以及反向传播方法
# 损失函数为MSE,反向传播方法为梯度下降
loss_mes = tf.reduce_mean(tf.square(y_-y))
train_step = tf.train.GradientDescentOptimizer(0.001).minimize(loss_mes)
# 3.生成会话,训练STEPS轮
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
STEPS = 20000
for i in range(STEPS):
start = (i * BATCH_SIZE) % 32
end = start + BATCH_SIZE
sess.run(train_step, feed_dict={x: X[start:end], y_: Y_[start:end]})
if i % 500==0:
print("After %d training steps,w1 is :\n" % i)
print(sess.run(w1))
print("final w1 is :\n", sess.run(w1))