-
前向传播就是搭建网络,设计网络结构(forward.py)
- 完成网络结构的设计,给出从输入到输出的数据通路。两个参数,x是输入,regularizer表示正则化权重
def forward(x, regularizer):
w =
b =
y =
return y
- 与参数w有关,两个参数分别是w的shape,以及正则化权重
def get_weight(shape, regularizer):
w = tf.Variable() #给w赋初值
tf.add_to_collection("losses", tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
- 与参数b有关,参数表示b的形状(个数)
def get_bias(shape):
b = tf.Variabel() #赋初值
return b
-
反向传播就是训练网络,优化网络参数(backward.py)
def backward():
x = tf.placeholder () #占位
y_ = tf.placeholder()
y = forward.forward(x,REGULARIZER) #复现前向传播结构,求y
global_step = tf.Variable(0,trainable = False)
loss =
#损失函数,正则化
#loss可以是:(均方误差)
y与y_的差距(loss_mse) = tf.reduce_mean(tf.square(y-y_))
#也可以是:(交叉熵)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = y,labels = tf.argmax(y_,1))
y与y_的差距(cem) = tf.reduce_mean(ce)
#加入正则化后:
loss = y与y_的差距+tf.add_n(tf.get_collection("losses"))
#指数衰减学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,数据集总样本数/BATCH_SIZE,LEARNING_RATE_DECAY,staircase = True)
train_step =tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step = global_step)
#滑动平均
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step,ema_op]):
trian_op = tf.no_op(name = "train")
with tf.Session() as sess:
init.run(init_op)
for i in range(STEPS):
sess.run(train_step,feed_dict = {x:, y:})
if i % 轮数 == 0 :
print()
if __name__ = "__main__": #判断Python运行的文件是否是主文件,如果是主文件,就执行backward这个函数
对上节课正则化代码模块化:
opt4_8_generateds.py
#coding:utf-8
#版本信息:ubuntu18.04 python3.6.8 tensorflow 1.14.0
#作者:九除以三还是三哦 如有错误,欢迎评论指正!!
#生成模拟数据集
import numpy as np
import matplotlib.pyplot as plt
seed = 2
def generateds():
#基于seed产生随机数
rdm = np.random.RandomState(seed)
#随机数返回300行2列的矩阵,表示300组坐标点(x0,x1)作为输入数据集
X = rdm.randn(300,2)
#从X这个300行2列的矩阵中取出一行,判断如果两个坐标的平方和小于2,给Y赋值1,其余赋值0
#作为输入数据集的标签(正确答案)
Y_ = [int(x0*x0 + x1*x1 <2) for (x0,x1) in X]
#遍历Y中的每个元素,1赋值'red'其余赋值'blue',这样可视化显示时人可以直观区分
Y_c = [['red' if y else 'blue'] for y in Y_]#对应颜色Y_c
#对数据集X和标签Y进行形状整理,第一个元素为-1表示跟随第二列计算,第二个元素表示多少列,可见X为两列,Y为1列
X = np.vstack(X).reshape(-1,2)#整理形状
Y_ = np.vstack(Y_).reshape(-1,1)#整理形状
return X, Y_, Y_c
#print (X)
#print (Y_)
#print (Y_c)
#用plt.scatter画出数据集X各行中第0列元素和第1列元素的点即各行的(x0,x1),用各行Y_c对应的值表示颜色(c是color的缩写)
#plt.scatter(X[:,0], X[:,1], c=np.squeeze(Y_c))
#plt.show()
opt4_8_backward.py
#coding:utf-8
#版本信息:ubuntu18.04 python3.6.8 tensorflow 1.14.0
#0导入模块 ,生成模拟数据集
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import opt4_8_generateds
import opt4_8_forward
STEPS = 40000
BATCH_SIZE = 30
LEARNING_RATE_BASE = 0.001
LEARNING_RATE_DECAY = 0.999
REGULARIZER = 0.01#正则化
def backward():#反向传播
x = tf.compat.v1.placeholder(tf.float32, shape=(None, 2))#占位
y_ =tf.compat.v1.placeholder(tf.float32, shape=(None, 1))#占位
#X:300行2列的矩阵。Y_:坐标的平方和小于2,给Y赋值1,其余赋值0
X, Y_, Y_c = opt4_8_generateds.generateds()
y = opt4_8_forward.forward(x, REGULARIZER)#前向传播计算后求得输出y
global_step = tf.Variable(0,trainable=False)#轮数计数器
#指数衰减学习率
learning_rate = tf.compat.v1.train.exponential_decay(
LEARNING_RATE_BASE,#学习率
global_step,#计数
300/BATCH_SIZE,
LEARNING_RATE_DECAY,#学习衰减lü
staircase=True)#选择不同的衰减方式
#定义损失函数
loss_mse = tf.reduce_mean(tf.square(y-y_))#均方误差
loss_total = loss_mse + tf.add_n(tf.compat.v1.get_collection('losses'))#正则化
#定义反向传播方法:包含正则化
train_step = tf.compat.v1.train.AdamOptimizer(learning_rate).minimize(loss_total)
with tf.compat.v1.Session() as sess:
init_op = tf.global_variables_initializer()#初始化
sess.run(init_op)#初始化
for i in range(STEPS):
start = (i*BATCH_SIZE) % 300
end = start + BATCH_SIZE#3000轮
sess.run(train_step, feed_dict={x: X[start:end], y_:Y_[start:end]})
if i % 2000 == 0:
loss_v = sess.run(loss_total, feed_dict={x:X,y_:Y_})
print("After %d steps, loss is: %f" %(i, loss_v))
xx, yy = np.mgrid[-3:3:.01, -3:3:.01]#网格坐标点
grid = np.c_[xx.ravel(), yy.ravel()]
probs = sess.run(y, feed_dict={x:grid})
probs = probs.reshape(xx.shape)
plt.scatter(X[:,0], X[:,1], c=np.squeeze(Y_c)) #画点
plt.contour(xx, yy, probs, levels=[.5])#画线
plt.show()#显示图像
if __name__=='__main__':
backward()
opt4_8_forward.py
#coding:utf-8
#版本信息:ubuntu18.04 python3.6.8 tensorflow 1.14.0
import tensorflow as tf
#定义神经网络的输入、参数和输出,定义前向传播过程
def get_weight(shape, regularizer):#(shape:W的形状,regularizer正则化)
w = tf.Variable(tf.random.normal(shape), dtype=tf.float32)#赋初值,正态分布权重
tf.compat.v1.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))#把正则化损失加到总损失losses中
return w#返回w
#tf.compat.v1.add_to_collection(‘list_name’, element):将元素element添加到列表list_name中
def get_bias(shape): #偏执b
b = tf.Variable(tf.constant(0.01, shape=shape)) #偏执b=0.01
return b#返回值
def forward(x, regularizer):#前向传播
w1 = get_weight([2,11], regularizer)#设置权重
b1 = get_bias([11])#设置偏执
y1 = tf.nn.relu(tf.matmul(x, w1) + b1)#计算图
w2 = get_weight([11,1], regularizer)#设置权重
b2 = get_bias([1])#设置偏执
y = tf.matmul(y1, w2) + b2 #计算图
return y#返回值
- 运行代码
python3 opt4_8_generateds.py
python3 opt4_8_backward.py