反向传播--->训练模型参数,在所有参数上用梯度下降,使NN模型再训练数据上的损失函数最小。
损失函数(loss):预测值(y)与已知答案(y_)的差距
均方误差MSE:
loss=tf.reduce_mean(tf.square(y,y_))
反向传播训练方法:以减小loss值为优化目标
train_step=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss) 梯度下降
train_step=tf.train.MomentumOptimizer(learning_rate,momentum).minimize(loss)momentum优化器
train_step=tf.train.AdamOptimizer(learning_rate).minimize(loss) adam优化
learining_rate 学习率:决定参数每次更新的幅度
参考代码:
#tf_3_3.py
#建立一个两层网络,输入层2,中间层3,输出层1
import tensorflow as tf
import numpy as np
BATCH_SIZE=10
seed=23455
#虚拟样本,基于seed生成随机数
rng=np.random.RandomState(seed)
#随机生成
X=rng.rand(80,2)
#生成标签 0、1
Y=[[int(x0+x1<1)] for (x0,x1) in X]
print("X:",X)
print("Y:",Y)
x=tf.placeholder(tf.float32)
y_=tf.placeholder(tf.float32)
w1=tf.Variable(tf.random_normal([2,3],stddev=1,seed=1))
w2=tf.Variable(tf.random_normal([3,3],stddev=1,seed=1))
w3=tf.Variable(tf.random_normal([3,1],stddev=1,seed=1))
a=tf.matmul(x,w1)
b=tf.matmul(a,w2)
y=tf.matmul(b,w3)
#定义loss和反向传播方法
learning_rate=0.001
loss=tf.reduce_mean(tf.square(y-y_))
train_step=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)
#train_step=tf.train.MomentumOptimizer(learning_rate,momentum=0.1).minimize(loss)
#train_step=tf.train.AdamOptimizer(learning_rate,beta1=0.9,beta2=0.999).minimize(loss)
with tf.Session() as sess:
init_op=tf.global_variables_initializer()
sess.run(init_op)
STEPS=3000
for i in range(STEPS):
start=(i*BATCH_SIZE)%80
end=start+BATCH_SIZE
sess.run(train_step,feed_dict={x:X[start:end],y_:Y[start:end]})
if i%300 == 0:
total_loss=sess.run(loss,feed_dict={x:X,y_:Y})
print("%d:loss:%g",i,total_loss)
总结:
搭建神经网络的八股:准备,前传,反传,迭代
1.准备: import
常量定义
生成数据集
2.前传:定义输入、参数、和输出
x=
y_=
w1=
w2=
w3
a
b
y
3.反向传播:定义损失函数、反向传播方法
loss=
train_step=
4.生成会话、训练steps轮
with tf.Session() as sess:
........