keras自动编码器实现系列之卷积自动编码器操作

@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()        

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))

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))

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()

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()