由于我是微调范例的初学者，因此我正在对该玩具数据集进行练习时，我为mnist数据集开发了3层深度自动编码器模型
以下是代码
from keras import layers
from keras.layers import Input, Dense
from keras.models import Model,Sequential
from keras.datasets import mnist
import numpy as np
# Deep Autoencoder
# this is the size of our encoded representations
encoding_dim = 32 # 32 floats -> compression factor 24.5, assuming the input is 784 floats
# this is our input placeholder; 784 = 28 x 28
input_img = Input(shape=(784, ))
my_epochs = 100
# "encoded" is the encoded representation of the inputs
encoded = Dense(encoding_dim * 4, activation='relu')(input_img)
encoded = Dense(encoding_dim * 2, activation='relu')(encoded)
encoded = Dense(encoding_dim, activation='relu')(encoded)
# "decoded" is the lossy reconstruction of the input
decoded = Dense(encoding_dim * 2, activation='relu')(encoded)
decoded = Dense(encoding_dim * 4, activation='relu')(decoded)
decoded = Dense(784, activation='sigmoid')(decoded)
# this model maps an input to its reconstruction
autoencoder = Model(input_img, decoded)
# Separate Encoder model
# this model maps an input to its encoded representation
encoder = Model(input_img, encoded)
# Separate Decoder model
# create a placeholder for an encoded (32-dimensional) input
encoded_input = Input(shape=(encoding_dim, ))
# retrieve the layers of the autoencoder model
decoder_layer1 = autoencoder.layers[-3]
decoder_layer2 = autoencoder.layers[-2]
decoder_layer3 = autoencoder.layers[-1]
# create the decoder model
decoder = Model(encoded_input, decoder_layer3(decoder_layer2(decoder_layer1(encoded_input))))
# Train to reconstruct MNIST digits
# configure model to use a per-pixel binary crossentropy loss, and the Adadelta optimizer
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
# prepare input data
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# normalize all values between 0 and 1 and flatten the 28x28 images into vectors of size 784
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:])))
# Train autoencoder for 50 epochs
autoencoder.fit(x_train, x_train, epochs=my_epochs, batch_size=256, shuffle=True, validation_data=(x_test, x_test),
verbose=2)
# after 100 epochs the autoencoder seems to reach a stable train/test lost value
# Visualize the reconstructed encoded representations
# encode and decode some digits
# note that we take them from the *test* set
encodedTrainImages=encoder.predict(x_train)
encoded_imgs = encoder.predict(x_test)
decoded_imgs = decoder.predict(encoded_imgs)
# From here I want to fine tune just the encoder model
model=Sequential()
model=Sequential()
for layer in encoder.layers:
model.add(layer)
model.add(layers.Flatten())
model.add(layers.Dense(20, activation='relu'))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(10, activation='softmax'))
以下是我要微调的编码器模型。
encoder.summary()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 784) 0
_________________________________________________________________
dense_1 (Dense) (None, 128) 100480
_________________________________________________________________
dense_2 (Dense) (None, 64) 8256
_________________________________________________________________
dense_3 (Dense) (None, 32) 2080
=================================================================
Total params: 110,816
Trainable params: 110,816
Non-trainable params: 0
_________________________________________________________________
问题：1
建立自动编码器模型后，我只想使用编码器模型并对mnist数据集中的分类任务进行微调，但会出错。
错误：
Traceback (most recent call last):
File "C:\Users\samer\Anaconda3\envs\tensorflow-gpu\lib\site-packages\IPython\core\interactiveshell.py", line 3267, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-15-528c079e5325>", line 3, in <module>
model.add(layers.Flatten())
File "C:\Users\samer\Anaconda3\envs\tensorflow-gpu\lib\site-packages\keras\engine\sequential.py", line 181, in add
output_tensor = layer(self.outputs[0])
File "C:\Users\samer\Anaconda3\envs\tensorflow-gpu\lib\site-packages\keras\engine\base_layer.py", line 414, in __call__
self.assert_input_compatibility(inputs)
File "C:\Users\samer\Anaconda3\envs\tensorflow-gpu\lib\site-packages\keras\engine\base_layer.py", line 327, in assert_input_compatibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer flatten_4: expected min_ndim=3, found ndim=2
问题2：
类似地，我稍后将使用预训练模型，其中每个自动编码器将以贪婪的方式进行训练，然后对最终模型进行微调。有人可以指导我如何在这两个任务中继续进行吗？
致谢
答案 0 :(得分：1)
问题是，您试图展平已经平坦的图层：编码器由一维Desnse图层组成，其形状为(batch_size, dim)。
Flatten层期望至少有2D输入，即具有3维形状(batch_size, dim1, dim2)（例如Conv2D层的输出），通过将其删除，模型将正确构建：
encoding_dim = 32
input_img = layers.Input(shape=(784, ))
encoded = layers.Dense(encoding_dim * 4, activation='relu')(input_img)
encoded = layers.Dense(encoding_dim * 2, activation='relu')(encoded)
encoded = layers.Dense(encoding_dim, activation='relu')(encoded)
encoder = Model(input_img, encoded)
[...]
model = Sequential()
for layer in encoder.layers:
print(layer.name)
model.add(layer)
model.add(layers.Dense(20, activation='relu'))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(10, activation='softmax'))
model.summary()
哪些产出：
input_1
dense_1
dense_2
dense_3
Model: "sequential_1"
________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 128) 100480
_________________________________________________________________
dense_2 (Dense) (None, 64) 8256
_________________________________________________________________
dense_3 (Dense) (None, 32) 2080
_________________________________________________________________
dense_4 (Dense) (None, 20) 660
_________________________________________________________________
dropout_1 (Dropout) (None, 20) 0
_________________________________________________________________
dense_5 (Dense) (None, 10) 210
=================================================================
Total params: 111,686
Trainable params: 111,686
Non-trainable params: 0
_________________________________________________________________
___
问：我如何确定新模型将使用与先前训练的编码器相同的权重？
A：在您的代码中，您正在执行的操作是遍历编码器内部包含的各层，然后将它们分别传递到model.add()。您在这里所做的是直接将引用传递给每个层，因此，您在新模型中将具有相同的层。这是使用图层名称的概念证明：
encoding_dim = 32
input_img = Input(shape=(784, ))
encoded = Dense(encoding_dim * 4, activation='relu')(input_img)
encoded = Dense(encoding_dim * 2, activation='relu')(encoded)
encoded = Dense(encoding_dim, activation='relu')(encoded)
decoded = Dense(encoding_dim * 2, activation='relu')(encoded)
decoded = Dense(encoding_dim * 4, activation='relu')(decoded)
decoded = Dense(784, activation='sigmoid')(decoded)
autoencoder = Model(input_img, decoded)
print("autoencoder first Dense layer reference:", autoencoder.layers[1])
encoder = Model(input_img, encoded)
print("encoder first Dense layer reference:", encoder.layers[1])
new_model = Sequential()
for i, layer in enumerate(encoder.layers):
print("Before: ", layer.name)
new_model.add(layer)
if i != 0:
new_model.layers[i-1].name = "new_model_"+layer.name
print("After: ", layer.name)
哪个输出：
autoencoder first Dense layer reference: <keras.layers.core.Dense object at
0x7fb5f138e278>
encoder first Dense layer reference: <keras.layers.core.Dense object at
0x7fb5f138e278>
Before: input_1
Before: dense_1
After: new_model_dense_1
Before: dense_2
After: new_model_dense_2
Before: dense_3
After: new_model_dense_3
如您所见，编码器和自动编码器中的图层参考相同。而且，通过更改新模型内部的层名称，我们还可以更改编码器相应层内部的层名称。有关通过引用传递的python参数的更多详细信息，请查看此answer。
问：我是否需要对数据进行一次热编码？如果可以，那么如何？
A：由于要处理多标签分类问题，因此确实需要使用一键编码。只需使用方便的keras函数即可完成编码：
from keras.utils import np_utils
one_hot = np_utils.to_categorical(y_train)
这里是documentation的链接。
___
关于第二个问题，您的目标不是很清楚，但是在我看来，您想要构建一个包含多个并行自动编码器的体系结构，这些并行编码器专门处理不同的任务，然后将其串联通过添加一些最终的通用层来输出。
无论如何，到目前为止，我只能建议您看一下这个guide，它说明了如何构建多输入和多输出模型并将其用作开始的基线您的自定义实现。
___
关于贪婪训练任务，该方法是通过在添加新内容时冻结先前的所有内容来一次训练一层。这是一个3（+1）贪婪训练层网络的示例，该网络后来被用作新模型的基础：
(x_train, y_train), (x_test, y_test) = mnist.load_data()
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
x_train = np.reshape(x_train, (x_train.shape[0], -1))
x_test = np.reshape(x_test, (x_test.shape[0], -1))
model = Sequential()
model.add(Dense(256, activation="relu", kernel_initializer="he_uniform", input_shape=(28*28,)))
model.add(Dense(10, activation="softmax"))
model.compile(optimizer=SGD(lr=0.01, momentum=0.9), loss="categorical_crossentropy", metrics=["accuracy"])
model.fit(x_train, y_train, batch_size=64, epochs=50, verbose=1)
# Remove last layer
model.pop()
# 'Freeze' previous layers, so to single-train the new one
for layer in model.layers:
layer.trainable = False
# Append new layer + classification layer
model.add(Dense(64, activation="relu", kernel_initializer="he_uniform"))
model.add(Dense(10, activation="softmax"))
model.fit(x_train, y_train, batch_size=64, epochs=50, verbose=0)
# Remove last layer
model.pop()
# 'Freeze' previous layers, so to single-train the new one
for layer in model.layers:
layer.trainable = False
# Append new layer + classification layer
model.add(Dense(32, activation="relu", kernel_initializer="he_uniform"))
model.add(Dense(10, activation="softmax"))
model.fit(x_train, y_train, batch_size=64, epochs=50, verbose=0)
# Create new model which will use the pre-trained layers
new_model = Sequential()
# Discard the last layer from the previous model
model.pop()
# Optional: you can decide to set the pre-trained layers as trainable, in
# which case it would be like having initialized their weights, or not.
for l in model.layers:
l.trainable = True
new_model.add(model)
new_model.add(Dense(20, activation='relu'))
new_model.add(Dropout(0.5))
new_model.add(Dense(10, activation='softmax'))
new_model.compile(optimizer=SGD(lr=0.01, momentum=0.9), loss="categorical_crossentropy", metrics=["accuracy"])
new_model.fit(x_train, y_train, batch_size=64, epochs=100, verbose=1)
大致如此，但是我必须说贪心层训练可能不再是一种合适的解决方案：如今，ReLU，Dropout和其他正则化技术使贪心层训练成为过时且耗时的权重初始化，因此您可能需要在进行贪婪训练之前，还要看看其他可能性。
___