keras自动编码器实现系列之卷积自动编码器操作

图片的自动编码很容易就想到用卷积神经网络做为编码-解码器。在实际的操作中,

也经常使用卷积自动编码器去解决图像编码问题,而且非常有效。

下面通过**keras**完成简单的卷积自动编码。 编码器有堆叠的卷积层和池化层(max pooling用于空间降采样)组成。 对应的解码器由卷积层和上采样层组成。

@requires_authorization
# -*- coding:utf-8 -*-

from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras import backend as K
import os

## 网络结构 ##
input_img = Input(shape=(28,28,1)) # Tensorflow后端, 注意要用channel_last
# 编码器部分
x = Conv2D(16, (3,3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2,2), padding='same')(x)
x = Conv2D(8,(3,3), activation='relu', padding='same')(x)
x = MaxPooling2D((2,2), padding='same')(x)
x = Conv2D(8, (3,3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2,2), padding='same')(x)

# 解码器部分
x = Conv2D(8, (3,3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3,3), activation='relu', padding='same')(x) 
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')

# 得到编码层的输出
encoder_model = Model(inputs=autoencoder.input, outputs=autoencoder.get_layer('encoder_out').output)

## 导入数据, 使用常用的手写识别数据集
def load_mnist(dataset_name):
'''
load the data
'''
  data_dir = os.path.join("./data", dataset_name)
  f = np.load(os.path.join(data_dir, 'mnist.npz'))
  train_data = f['train'].T
  trX = train_data.reshape((-1, 28, 28, 1)).astype(np.float32)
  trY = f['train_labels'][-1].astype(np.float32)
  test_data = f['test'].T
  teX = test_data.reshape((-1, 28, 28, 1)).astype(np.float32)
  teY = f['test_labels'][-1].astype(np.float32)

  # one-hot 
  # y_vec = np.zeros((len(y), 10), dtype=np.float32)
  # for i, label in enumerate(y):
  #   y_vec[i, y[i]] = 1
  # keras.utils里带的有one-hot的函数, 就直接用那个了
  return trX / 255., trY, teX/255., teY

# 开始导入数据
x_train, _ , x_test, _= load_mnist('mnist')

# 可视化训练结果, 我们打开终端, 使用tensorboard
# tensorboard --logdir=/tmp/autoencoder # 注意这里是打开一个终端, 在终端里运行

# 训练模型, 并且在callbacks中使用tensorBoard实例, 写入训练日志 http://0.0.0.0:6006
from keras.callbacks import TensorBoard
autoencoder.fit(x_train, x_train,
        epochs=50,
        batch_size=128,
        shuffle=True,
        validation_data=(x_test, x_test),
        callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])

# 重建图片
import matplotlib.pyplot as plt 
decoded_imgs = autoencoder.predict(x_test)
encoded_imgs = encoder_model.predict(x_test)
n = 10
plt.figure(figsize=(20, 4))
for i in range(n):
  k = i + 1
  # 画原始图片
  ax = plt.subplot(2, n, k)
  plt.imshow(x_test[k].reshape(28, 28))
  plt.gray()
  ax.get_xaxis().set_visible(False)
  # 画重建图片
  ax = plt.subplot(2, n, k + n)
  plt.imshow(decoded_imgs[i].reshape(28, 28))
  plt.gray()
  ax.get_xaxis().set_visible(False)
  ax.get_yaxis().set_visible(False)
plt.show()

# 编码得到的特征
n = 10
plt.figure(figsize=(20, 8))
for i in range(n):
  k = i + 1
  ax = plt.subplot(1, n, k)
  plt.imshow(encoded[k].reshape(4, 4 * 8).T)
  plt.gray()
  ax.get_xaxis().set_visible(False)
  ax.get_yaxis().set_visible(False)
plt.show()        

补充知识:keras搬砖系列-单层卷积自编码器

考试成绩出来了,竟然有一门出奇的差,只是有点意外。

觉得应该不错的,竟然考差了,它估计写了个随机数吧。

头文件

from keras.layers import Input,Dense
from keras.models import Model 
from keras.datasets import mnist
import numpy as np 
import matplotlib.pyplot as plt 

导入数据

(X_train,_),(X_test,_) = mnist.load_data()
 
X_train = X_train.astype('float32')/255.
X_test = X_test.astype('float32')/255.
X_train = X_train.reshape((len(X_train),-1))
X_test = X_test.reshape((len(X_test),-1))

这里的X_train和X_test的维度分别为(60000L,784L),(10000L,784L)

这里进行了归一化,将所有的数值除上255.

设定编码的维数与输入数据的维数

encoding_dim = 32

input_img = Input(shape=(784,))

构建模型

encoded = Dense(encoding_dim,activation='relu')(input_img)
decoded = Dense(784,activation='relu')(encoded)
 
autoencoder = Model(inputs = input_img,outputs=decoded)
encoder = Model(inputs=input_img,outputs=encoded)
 
encoded_input = Input(shape=(encoding_dim,))
decoder_layer = autoencoder.layers[-1]
deconder = Model(inputs=encoded_input,outputs = decoder_layer(encoded_input))

模型编译

autoencoder.compile(optimizer='adadelta',loss='binary_crossentropy')

模型训练

autoencoder.fit(X_train,X_train,epochs=50,batch_size=256,shuffle=True,validation_data=(X_test,X_test))

预测

encoded_imgs = encoder.predict(X_test)

decoded_imgs = deconder.predict(encoded_imgs)

数据可视化

n = 10
for i in range(n):
 ax = plt.subplot(2,n,i+1)
 plt.imshow(X_test[i].reshape(28,28))
 plt.gray()
 ax.get_xaxis().set_visible(False)
 ax.get_yaxis().set_visible(False)
 
 ax = plt.subplot(2,n,i+1+n)
 plt.imshow(decoded_imgs[i].reshape(28,28))
 plt.gray()
 ax.get_xaxis().set_visible(False)
 ax.get_yaxis().set_visible(False)
plt.show()

完成代码

from keras.layers import Input,Dense
from keras.models import Model 
from keras.datasets import mnist
import numpy as np 
import matplotlib.pyplot as plt 
 
(X_train,_),(X_test,_) = mnist.load_data()
 
X_train = X_train.astype('float32')/255.
X_test = X_test.astype('float32')/255.
X_train = X_train.reshape((len(X_train),-1))
X_test = X_test.reshape((len(X_test),-1))
 
encoding_dim = 32
input_img = Input(shape=(784,))
 
encoded = Dense(encoding_dim,activation='relu')(input_img)
decoded = Dense(784,activation='relu')(encoded)
 
autoencoder = Model(inputs = input_img,outputs=decoded)
encoder = Model(inputs=input_img,outputs=encoded)
 
encoded_input = Input(shape=(encoding_dim,))
decoder_layer = autoencoder.layers[-1]
deconder = Model(inputs=encoded_input,outputs = decoder_layer(encoded_input))
 
autoencoder.compile(optimizer='adadelta',loss='binary_crossentropy')
autoencoder.fit(X_train,X_train,epochs=50,batch_size=256,shuffle=True,validation_data=(X_test,X_test))
 
encoded_imgs = encoder.predict(X_test)
decoded_imgs = deconder.predict(encoded_imgs)
 
##via
n = 10
for i in range(n):
 ax = plt.subplot(2,n,i+1)
 plt.imshow(X_test[i].reshape(28,28))
 plt.gray()
 ax.get_xaxis().set_visible(False)
 ax.get_yaxis().set_visible(False)
 
 ax = plt.subplot(2,n,i+1+n)
 plt.imshow(decoded_imgs[i].reshape(28,28))
 plt.gray()
 ax.get_xaxis().set_visible(False)
 ax.get_yaxis().set_visible(False)
plt.show()

以上这篇keras自动编码器实现系列之卷积自动编码器操作就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持呐喊教程。

声明:本文内容来源于网络,版权归原作者所有,内容由互联网用户自发贡献自行上传,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任。如果您发现有涉嫌版权的内容,欢迎发送邮件至:notice#nhooo.com(发邮件时,请将#更换为@)进行举报,并提供相关证据,一经查实,本站将立刻删除涉嫌侵权内容。