介绍自动编码器实际上是一种人工神经网络,用于对以无监督方式提供的输入数据进行解压缩和压缩。解压缩和压缩操作是有损的且特定于数据的。数据特定意味着自动编码器将只能实际压缩已经训练过的数据。例如,如果你用狗的图像训练一个自动编码器,那么它会给猫带来糟糕的表现。自动编码器计划学习表示对整个数据集的编码。这可能会导致训练网络降低维数。重构部分也是通过这个学习的。
有损操作意味着重建图像的质量通常不如原始图像清晰或高分辨率,并且对于具有更大损失的重建,差异更大,这被称为有损操作。下图显示了如何使用特定损失因子对图像进行编码和解码。
自动编码器是一种特殊类型的前馈神经网络,输入应该与输出相似。因此,我们需要一种编码方法、损失函数和解码方法。最终目标是以最小的损失完美地复制输入。输入将通过一层编码器,它实际上是一个完全连接的神经网络,它也构成代码解码器,因此像 ANN 一样使用相同的代码进行编码和解码。代码实现通过反向传播训练的 ANN 的工作方式与自动编码器相同。在本文中,我们将讨论 3 种类型的自动编码器,如下所示:简单的自动编码器深度 CNN 自动编码器去噪自动编码器对于自动编码器的实现部分,我们将使用流行的 MNIST 数字数据集。
1． 简单的自动编码器我们首先导入所有必要的库:import all the dependencies
from keras．layers import Dense,Conv2D,MaxPooling2D,UpSampling2D
from keras import Input, Model
from keras．datasets import mnist
import numpy as np
import matplotlib．pyplot as plt
然后我们将构建我们的模型,我们将提供决定输入将被压缩多少的维度数。维度越小,压缩越大。encoding_dim = 15
input_img = Input(shape=(784,))
# encoded representation of input
encoded = Dense(encoding_dim, activation='relu')(input_img)
# decoded representation of code
decoded = Dense(784, activation='sigmoid')(encoded)
# Model which take input image and shows decoded images
autoencoder = Model(input_img, decoded)
然后我们需要分别构建编码器模型和解码器模型,以便我们可以轻松区分输入和输出。# This model shows encoded images
encoder = Model(input_img, encoded)
# Creating a decoder model
encoded_input = Input(shape=(encoding_dim,))
# last layer of the autoencoder model
decoder_layer = autoencoder．layers[-1]
# decoder model
decoder = Model(encoded_input, decoder_layer(encoded_input))
然后我们需要用ADAM优化器和交叉熵损失函数拟合来编译模型。autoencoder．compile(optimizer='adam', loss='binary_crossentropy')
然后你需要加载数据:(x_train, y_train), (x_test, y_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), np．prod(x_train．shape[1:])))
x_test = x_test．reshape((len(x_test), np．prod(x_test．shape[1:])))
print(x_train．shape)
print(x_test．shape)
输出 :(60000, 784)
(10000, 784)
如果你想查看数据的实际情况,可以使用以下代码行:plt．imshow(x_train[0]．reshape(28,28))
输出 :
然后你需要训练你的模型:autoencoder．fit(x_train, x_train,
epochs=15,
batch_size=256,
validation_data=(x_test, x_test))
输出 :Epoch 1/15
235/235 [==============================] - 14s 5ms/step - loss: 0．4200 - val_loss: 0．2263
Epoch 2/15
235/235 [==============================] - 1s 3ms/step - loss: 0．2129 - val_loss: 0．1830
Epoch 3/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1799 - val_loss: 0．1656
Epoch 4/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1632 - val_loss: 0．1537
Epoch 5/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1533 - val_loss: 0．1481
Epoch 6/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1488 - val_loss: 0．1447
Epoch 7/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1457 - val_loss: 0．1424
Epoch 8/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1434 - val_loss: 0．1405
Epoch 9/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1415 - val_loss: 0．1388
Epoch 10/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1398 - val_loss: 0．1374
Epoch 11/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1386 - val_loss: 0．1360
Epoch 12/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1373 - val_loss: 0．1350
Epoch 13/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1362 - val_loss: 0．1341
Epoch 14/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1355 - val_loss: 0．1334
Epoch 15/15
235/235 [==============================] - 1s 3ms/step - loss: 0．1348 - val_loss: 0．1328
训练后,你需要提供输入,你可以使用以下代码绘制结果:encoded_img = encoder．predict(x_test)
decoded_img = decoder．predict(encoded_img)
plt．figure(figsize=(20, 4))
for i in range(5):
# Display original
ax = plt．subplot(2, 5, i + 1)
plt．imshow(x_test[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
# Display reconstruction
ax = plt．subplot(2, 5, i + 1 + 5)
plt．imshow(decoded_img[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
plt．show()
你可以分别清楚地看到编码和解码图像的输出,如下所示。
2． 深度 CNN 自动编码器由于这里的输入是图像,因此使用卷积神经网络或 CNN 确实更有意义。编码器将由一堆 Conv2D 和最大池化层组成,解码器将由一堆 Conv2D 和上采样层组成。代码 :model = Sequential()
# encoder network
model．add(Conv2D(30, 3, activation= 'relu', padding='same', input_shape = (28,28,1)))
model．add(MaxPooling2D(2, padding= 'same'))
model．add(Conv2D(15, 3, activation= 'relu', padding='same'))
model．add(MaxPooling2D(2, padding= 'same'))
#decoder network
model．add(Conv2D(15, 3, activation= 'relu', padding='same'))
model．add(UpSampling2D(2))
model．add(Conv2D(30, 3, activation= 'relu', padding='same'))
model．add(UpSampling2D(2))
model．add(Conv2D(1,3,activation='sigmoid', padding= 'same')) # output layer
model．compile(optimizer= 'adam', loss = 'binary_crossentropy')
model．summary()
输出 :Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 28, 28, 30) 300
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 14, 14, 30) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 14, 14, 15) 4065
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 7, 7, 15) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 7, 7, 15) 2040
_________________________________________________________________
up_sampling2d (UpSampling2D) (None, 14, 14, 15) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 14, 14, 30) 4080
_________________________________________________________________
up_sampling2d_1 (UpSampling2 (None, 28, 28, 30) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 28, 28, 1) 271
=================================================================
Total params: 10,756
Trainable params: 10,756
Non-trainable params: 0
_________________________________________________________________
现在你需要加载数据并训练模型(x_train, _), (x_test, _) = mnist．load_data()
x_train = x_train．astype('float32') / 255．
x_test = x_test．astype('float32') / 255．
x_train = np．reshape(x_train, (len(x_train), 28, 28, 1))
x_test = np．reshape(x_test, (len(x_test), 28, 28, 1))
model．fit(x_train, x_train,
epochs=15,
batch_size=128,
validation_data=(x_test, x_test))
输出 :Epoch 1/15
469/469 [==============================] - 34s 8ms/step - loss: 0．2310 - val_loss: 0．0818
Epoch 2/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0811 - val_loss: 0．0764
Epoch 3/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0764 - val_loss: 0．0739
Epoch 4/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0743 - val_loss: 0．0725
Epoch 5/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0729 - val_loss: 0．0718
Epoch 6/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0722 - val_loss: 0．0709
Epoch 7/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0715 - val_loss: 0．0703
Epoch 8/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0709 - val_loss: 0．0698
Epoch 9/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0700 - val_loss: 0．0693
Epoch 10/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0698 - val_loss: 0．0689
Epoch 11/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0694 - val_loss: 0．0687
Epoch 12/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0691 - val_loss: 0．0684
Epoch 13/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0688 - val_loss: 0．0680
Epoch 14/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0685 - val_loss: 0．0680
Epoch 15/15
469/469 [==============================] - 3s 7ms/step - loss: 0．0683 - val_loss: 0．0676
现在你需要提供输入并绘制以下结果的输出pred = model．predict(x_test)
plt．figure(figsize=(20, 4))
for i in range(5):
# Display original
ax = plt．subplot(2, 5, i + 1)
plt．imshow(x_test[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
# Display reconstruction
ax = plt．subplot(2, 5, i + 1 + 5)
plt．imshow(pred[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
plt．show()
输出 :
3． 去噪自动编码器现在我们将看到模型如何处理图像中的噪声。我们所说的噪声是指模糊的图像、改变图像的颜色,甚至是图像上的白色标记。noise_factor = 0．7
x_train_noisy = x_train + noise_factor * np．random．normal(loc=0．0, scale=1．0, size=x_train．shape)
x_test_noisy = x_test + noise_factor * np．random．normal(loc=0．0, scale=1．0, size=x_test．shape)
x_train_noisy = np．clip(x_train_noisy, 0．, 1．)
x_test_noisy = np．clip(x_test_noisy, 0．, 1．)
Here is how the noisy images look right now．
plt．figure(figsize=(20, 2))
for i in range(1, 5 + 1):
ax = plt．subplot(1, 5, i)
plt．imshow(x_test_noisy[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
plt．show()
输出 :
现在图像几乎无法识别,为了增加自动编码器的范围,我们将修改定义模型的层以增加过滤器,使模型性能更好,然后拟合模型。model = Sequential()
# encoder network
model．add(Conv2D(35, 3, activation= 'relu', padding='same', input_shape = (28,28,1)))
model．add(MaxPooling2D(2, padding= 'same'))
model．add(Conv2D(25, 3, activation= 'relu', padding='same'))
model．add(MaxPooling2D(2, padding= 'same'))
#decoder network
model．add(Conv2D(25, 3, activation= 'relu', padding='same'))
model．add(UpSampling2D(2))
model．add(Conv2D(35, 3, activation= 'relu', padding='same'))
model．add(UpSampling2D(2))
model．add(Conv2D(1,3,activation='sigmoid', padding= 'same')) # output layer
model．compile(optimizer= 'adam', loss = 'binary_crossentropy')
model．fit(x_train_noisy, x_train,
epochs=15,
batch_size=128,
validation_data=(x_test_noisy, x_test))
输出 :Epoch 1/15
469/469 [==============================] - 5s 9ms/step - loss: 0．2643 - val_loss: 0．1456
Epoch 2/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1440 - val_loss: 0．1378
Epoch 3/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1373 - val_loss: 0．1329
Epoch 4/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1336 - val_loss: 0．1305
Epoch 5/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1313 - val_loss: 0．1283
Epoch 6/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1294 - val_loss: 0．1268
Epoch 7/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1278 - val_loss: 0．1257
Epoch 8/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1267 - val_loss: 0．1251
Epoch 9/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1259 - val_loss: 0．1244
Epoch 10/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1251 - val_loss: 0．1234
Epoch 11/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1241 - val_loss: 0．1234
Epoch 12/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1239 - val_loss: 0．1222
Epoch 13/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1232 - val_loss: 0．1223
Epoch 14/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1226 - val_loss: 0．1215
Epoch 15/15
469/469 [==============================] - 4s 8ms/step - loss: 0．1221 - val_loss: 0．1211
训练结束后,我们将提供输入并编写绘图函数以查看最终结果。pred = model．predict(x_test_noisy)
plt．figure(figsize=(20, 4))
for i in range(5):
# Display original
ax = plt．subplot(2, 5, i + 1)
plt．imshow(x_test_noisy[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
# Display reconstruction
ax = plt．subplot(2, 5, i + 1 + 5)
plt．imshow(pred[i]．reshape(28, 28))
plt．gray()
ax．get_xaxis()．set_visible(False)
ax．get_yaxis()．set_visible(False)
plt．show()
输出 :
尾注我们已经了解了自动编码器工作的结构,并使用了 3 种类型的自动编码器。自动编码器有多种用途,如降维图像压缩、电影和歌曲推荐系统等。模型的性能可以通过训练更多的 epoch 或增加我们网络的维度来提高。
