取自于TensorFlow实战
import tensorflow as tf import sklearn.preprocessing as prep import matplotlib.pyplot as plt import numpy as np #定义tensorfl的CPU运算优先级 import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #导入MNIST手写数字集数据 from tensorflow.examples.tutorials.mnist import input_data #定义Xavier初始化器 def xavier_init(fan_in,fan_out,constant=1): factor=constant*np.sqrt(6.0/(fan_in+fan_out)) return tf.random_uniform((fan_in,fan_out),minval=-factor,maxval=factor,dtype=tf.float32) #定义加高斯噪声的自编码器 class AdditiveGaussianNoiseAutoencode(object): def __init__(self,n_input,n_hidden,transfer_function=tf.nn.softplus,optimizer=tf.train.AdamOptimizer(),scale=0.1): #初始化变量 self.n_input=n_input self.n_hidden=n_hidden self.transfer=transfer_function self.scale = tf.placeholder(tf.float32) self.training_scale=scale network_weights=self._initialize_weights() self.weights=network_weights #定义输入占位符 self.x=tf.placeholder(tf.float32,[None,self.n_input]) #定义隐藏层(降维特征层),激活函数为softplus self.hidden=self.transfer(tf.add(tf.matmul(self.x+scale*tf.random_normal((n_input,)),self.weights['w1']),self.weights['b1'])) #定义重构层 self.reconstruction=tf.add(tf.matmul(self.hidden,self.weights['w2']),self.weights['b2']) #定义损失函数 self.cost=0.5*tf.reduce_sum(tf.pow(tf.subtract(self.reconstruction,self.x),2.0)) #定义训练器,亚当求解器, self.optimizer=optimizer.minimize(self.cost) #初始化计算图 init=tf.global_variables_initializer() self.sess=tf.Session() self.sess.run(init) #定义权重,偏置 def _initialize_weights(self): all_weights=dict() all_weights['w1']=tf.Variable(xavier_init(self.n_input,self.n_hidden)) all_weights['b1']=tf.Variable(tf.zeros([self.n_hidden]),dtype=tf.float32) all_weights['w2'] = tf.Variable(tf.zeros([self.n_hidden,self.n_input]), dtype=tf.float32) all_weights['b2'] = tf.Variable(tf.zeros([ self.n_input]), dtype=tf.float32) return all_weights #定义部分拟合,返回cost def partial_fit(self,x): cost,_=self.sess.run((self.cost,self.optimizer),feed_dict={self.x:x,self.scale:self.training_scale}) return cost #不触发训练运算,返回cost def calc_total_cost(self,x): return self.sess.run(self.cost,feed_dict={self.x:x,self.scale:self.training_scale}) #返回隐藏层(特征层 def transform(self,x): return self.sess.run(self.hidden,feed_dict={self.x:x,self.scale:self.training_scale}) #由隐藏层计算输出层 def generate(self,hidden=None): if hidden==None: hidden=np.random.normal(size=self.weights['b1']) return self.sess.run(self.reconstruction,feed_dict={self.hidden:hidden}) #由输出计算输出 def reconstruct(self,x): return self.sess.run(self.reconstruction,feed_dict={self.x:x,self.scale:self.training_scale}) #计算权重偏置 def get_weights(self): return self.sess.run(self.weights['w1']) def get_biases(self): return self.sess.run(self.weights['b1']) #导入手写数据集 mnist=input_data.read_data_sets('MNIST_data/',one_hot=True) #标准化数据集,(没有也可以算) def standard_scale(x_train,x_test): preprocessor=prep.StandardScaler().fit(x_train) x_train=preprocessor.transform(x_train) x_test=preprocessor.transform(x_test) return x_train,x_test #随机获取mini——batch def get_random_block_from_data(data,batch_size): start_index=np.random.randint(0,len(data)-batch_size) return data[start_index:(start_index+batch_size)] #标准化数据集 x_train,x_test=standard_scale(mnist.train.images,mnist.test.images) #定义模型超参 n_samples=int(mnist.train.num_examples) training_epoch=20 batch_size=128 display_step=1 #定义类 autoencode=AdditiveGaussianNoiseAutoencode(n_input=784,n_hidden=200, transfer_function=tf.nn.softplus, optimizer=tf.train.AdamOptimizer(learning_rate=0.001), scale=0.01) #定义训练过程 for epoch in range(training_epoch): avg_cost=0 total_batch=int(n_samples/batch_size) for i in range(total_batch): batch_x=get_random_block_from_data(mnist.train.images,batch_size) cost=autoencode.partial_fit(batch_x) avg_cost+=cost/n_samples*batch_size if epoch%display_step==0: print('Epoch:{:4d},cost={:.9f}'.format(epoch+1,avg_cost)) print('total cost:',autoencode.calc_total_cost(mnist.train.images)) #显示前四个数据的自编码结果 input=mnist.test.images[:4] output=autoencode.reconstruct(input) fig,ax=plt.subplots(2,4) for i,data in enumerate(input.reshape(4,28,28)): ax[0,i].imshow(data,'gray') ax[0,i].axis('off') for i,data in enumerate(output.reshape(4,28,28)): ax[1,i].imshow(data,'gray') ax[1,i].axis('off') plt.show()