您的位置: 首页  >  文章  >  深度学习——模块化神经网络搭建八股

深度学习——模块化神经网络搭建八股

分类: 文章 • 2025-05-09 18:35:22

 opt4_8_generateds.py

#coding:utf-8
#0 导入模块，生成模拟数据集
import numpy as np
import matplotlib.pyplot as plt
seed = 2
def generateds():
	#基于seed生成随机数
	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)
	Y_= [int(x0*x0+x1*x1 < 2) for (x0,x1) in X]
	Y_c = [['red' if y else 'blue'] for y in Y_]
	
	X = np.vstack(X).reshape(-1,2)
	Y_= np.vstack(Y_).reshape(-1,1)

	return X,Y_,Y_c

opt4_8_forward.py

#coding:utf-8
#0 导入模块，生成模拟数据集
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):
	w = tf.Variable(tf.random_normal(shape),dtype=tf.float32)
	tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(regularizer)(w))
	return w

def get_bias(shape):
	b = tf.Variable(tf.constant(0.01,shape=shape))
	return b

def forward(x,regularizer):
	w1 = get_weight([2,11],regularizer)
	b1 = get_bias([11])
	y1 = tf.nn.relu(tf.matmul(x,w1)+b1)

	w2 = get_weight([11,1],regularizer)
	b2 = get_bias([1])
	y = tf.matmul(y1,w2)+b2

	return y

opt4_8_backward.py

#coding:utf-8
#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 os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
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

def backward():
	x = tf.placeholder(tf.float32,shape = (None, 2))
	y_= tf.placeholder(tf.float32, shape = (None,1))
	X, Y_, Y_c = opt4_8_generateds.generateds()
	y = opt4_8_forward.forward(x, REGULARIZER)
	global_step = tf.Variable(0,trainable=False)
	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
	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：包含正则化
	train_step = tf.train.AdamOptimizer(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:
				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]
		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：python opt4_8_backward.py

结果：

深度学习——模块化神经网络搭建八股

深度学习——模块化神经网络搭建八股

# 搭建模块化的神经网络八股：
# 前向传播就是搭建网络。设计网络结构(forword.py)
 
 
def forward(x, regularizer):
    w =
    b =
    y =
    return y
 
 
def get_weight(shape, regularizer):
    w = tf.Variable()
    tf.add_to_collection('losses', tf.contrib.l2_regularizer(regularizer)(w))
    return w
 
# shape表示b的形状，就是某层中b的个数
 
 
def get_bias(shape):
    b = tf.Variable()
    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()
    y_ = tf.placeholder()
    y = forward.forward(x, REGULARIZER)
    # 轮数计数器
    global_step = tf.Variable(0, trainable=False)
    loss =
 
 
'''
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_))
    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，则还要加上:
    loss = y与y_的差距 + tf.add_n(tf.get_collection('losses'))
'''
# 若使用，指数衰减学习率，则加上:
learning_rate = tf.train.exponential_decay(
    LEARNING_RATE_BASE,
    global_step,
    数据样本数/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(MOVlNG_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')
 
 
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:
            print()
 
# 判断python运行的文件是否是主文件，若是主文件，则执行backward()函数
if __name__ == '__main__':
    backward()

 

相关推荐