在许多时期之后，简单的自动编码器不会收敛

Question

我正在开发CIFA10数据集的自动编码器，而不会在输入处添加噪声（这是第二个目标）。

基于Convnet的自动编码器没有收敛：任何建议

input_img=Input(shape=(32,32,3))

x=Conv2D(16,(3,3),padding='same',activation='relu')(input_img)
x=MaxPooling2D((2,2),padding='same')(x)
x=Conv2D(8,(3,3),padding='same',activation='relu')(x)
x=MaxPooling2D((2,2),padding='same')(x)
x=Conv2D(8,(3,3),padding='same',activation='relu')(x)
encoded=MaxPooling2D((2,2),padding='same')(x)
x=Conv2D(8,(3,3),padding='same',activation='relu')(encoded)
x=UpSampling2D((2,2))(x)
x=Conv2D(8,(3,3),padding='same',activation='relu')(x)
x=UpSampling2D((2,2))(x)
x=Conv2D(16,(3,3),padding='same',activation='relu')(x) 
x=UpSampling2D((2,2))(x)
decoded=Conv2D(3,(3,3),padding='same',activation='sigmoid')(x)
autoencoder=Model(input_img,decoded)
(x_train,_),(x_test,_)=cifar10.load_data()
x_train=x_train.astype('float32')/255
x_test=x_test.astype('float32')/255
x_train=x_train.reshape(len(x_train),32,32,3)
x_test=x_test.reshape(len(x_test),32,32,3)

autoencoder.compile(optimizer='Adam',loss='binary_crossentropy')
autoencoder.fit(x_train, x_train,
            epochs=50,
            batch_size=64,
            shuffle=True,
            validation_data=(x_test, x_test))

即使对于大时期，我也会得到损失的平台

我尝试使用模型64-32-16-8：8-16-32-64，带有CIFAR-10的灰度图像，但我仍然存在相同的收敛问题，网络给出了模糊输出以及显示的输出网络模糊

Answer 1

不确定您的意思。如果我是您，我会尝试更深入的模型以提高性能。例如，模型提出的波纹管（或更深层）

input_img=Input(shape=(32,32,3))
x=Conv2D(8,(3,3),padding='same',activation='relu')(input_img)
x=Conv2D(8,(3,3),padding='same',activation='relu')(x)
x=MaxPooling2D((2,2),padding='same')(x)
x=Conv2D(16,(3,3),padding='same',activation='relu')(x)
x=Conv2D(16,(3,3),padding='same',activation='relu')(x)
x=MaxPooling2D((2,2),padding='same')(x)
x=Conv2D(32,(3,3),padding='same',activation='relu')(x)
x=Conv2D(32,(3,3),padding='same',activation='relu')(x)
encoded=MaxPooling2D((2,2),padding='same')(x)
x=Conv2D(32,(3,3),padding='same',activation='relu')(encoded)
x=Conv2D(32,(3,3),padding='same',activation='relu')(x)
x=UpSampling2D((2,2))(x)
x=Conv2D(16,(3,3),padding='same',activation='relu')(x)
x=Conv2D(16,(3,3),padding='same',activation='relu')(x)
x=UpSampling2D((2,2))(x)
x=Conv2D(8,(3,3),padding='same',activation='relu')(x) 
x=Conv2D(8,(3,3),padding='same',activation='relu')(x) 
x=UpSampling2D((2,2))(x)
decoded=Conv2D(3,(3,3),padding='same',activation='sigmoid')(x)
autoencoder=Model(input_img,decoded)