神经网络模块搭建（代码详解）
模块搭建
前向传播（forward()）：搭建网络，设计网络结构
def forward(x,regularizer):
w=
b=
y=
return y
#正则化权重
def get_weight(shape,regularizer):
w=tf.Variable()
tf.add_to_collection('losses',tf.contrib.layers.l1_regularizer(regularizer)(w))#正则化缓解过拟合
return w
def get_bais(shape):
b = tf.Variable()
return b反向传播（backward()）：训练网络，优化网络参数
def backward():
x = tf.placeholder()
y_ = tf.placeholder()
y = forward(x,REGULARIZER)
global_step = tf.Variable(0,trainable=False)
loss=
#正则化
loss可以是：
y与y_的差距（loss_mse）=tf.reduce_mean(tf.square(tf.square(y-y_))
也可以是：
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,
数据及总样本/BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
#定义训练过程
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]):
train_op=tf.no_op(name='train')
#会话
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
for i in range(STEPS):
sess.run(train_step,feed_dict={x:,y_:})
if i%轮数 == 0:#每多少轮，打印出当前的loss值
print()
if __name__=='__main__':
backward()完整代码及详解
import tensorflow as tf
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
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，否则为0
#作为输入数据的标签
Y_ = [int(x0*x0+x1*x1<2)for (x0,x1) in X]
#遍历Y中的每一个元数，1赋值‘red'其余赋值‘blue’，这样可视化显示时人可以直观区别
Y_c = [['red'if y else 'blue']for y in Y_]
#对数据集X和标签Y进行形状整理，第一个元素为-1表示跟随第二例计算，第二个元素表示多少列，可见X为两列，Y为一列
X = np.vstack(X).reshape(-1,2)
Y_ = np.vstack(Y_).reshape(-1,1)
return X,Y_,Y_c
#定义神经网络的输出，参数的输出，定义前向传播过程
def get_weight(shape,regularizer):
w = tf.Variable(tf.random_normal(shape),dtype=tf.float32)
tf.add_to_collection('losses',tf.contrib.layers.l1_regularizer(regularizer)(w))#正则化缓解过拟合
return w
def get_bais(shape):
b = tf.Variable(tf.constant(0.01,shape=shape))
return b
def forward(x,regularizer):
w1 = get_weight([2,11],regularizer)
b1 = get_bais([11])
y1 = tf.nn.relu(tf.matmul(x,w1)+b1)
w2 = get_weight([11, 1],regularizer)
b2 = get_bais([1])
y = tf.matmul(y1,w2)+b2
return y
STEPS = 60000
BATCH_SIZE = 50
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARIZER = 0.001
def backward():
x = tf.placeholder(tf.float32,shape=(None,2))
y_ = tf.placeholder(tf.float32,shape=(None,1))
X,Y_,Y_c = generateds()
y = forward(x,REGULARIZER)
global_step = tf.Variable(0,trainable=False)
#指数衰减学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,
global_step,
300/BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
#定义损失函数,引入正则化的损失函数
loss_mse = tf.reduce_mean(tf.square(y-y_))
loss_total = loss_mse + tf.add_n(tf.get_collection('losses'))
#定义反向传播方法，包括正则化
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss_total)
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
for i in range(STEPS):
start = (i*BATCH_SIZE)%300
end = start+BATCH_SIZE
sess.run(train_step,feed_dict={x:X[start:end],y_:Y_[start:end]})
if i%2000 == 0:#每2000轮，打印出当前的loss值
loss_v = sess.run(loss_total,feed_dict={x:X,y_:Y_})
print("After %d steps,loss is:%f"%(i,loss_v))
#画图
xx,yy = np.mgrid[-3:3:.01,-3:3:.01]
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))
plt.contour(xx,yy,probs,levels=[.5])
plt.show()
if __name__=='__main__':
backward()运行结果
