隐藏层在哪里？

Question

我对自动编码器有点陌生。我有来自 Keras (https://blog.keras.io/building-autoencoders-in-keras.html) 的这段代码。我想知道我在此处代码中的注释是否正确？

input_img = keras.Input(shape=(784,)) # input
encoded = layers.Dense(128, activation='relu')(input_img) # is it hidden layer???
encoded = layers.Dense(64, activation='relu')(encoded) # is it hidden layer???
encoded = layers.Dense(32, activation='relu')(encoded) # is it hidden layer???

decoded = layers.Dense(64, activation='relu')(encoded) # is it hidden layer???
decoded = layers.Dense(128, activation='relu')(decoded) # is it hidden layer???
decoded = layers.Dense(784, activation='sigmoid')(decoded) # output

如果可以的话，你们能再解释一下吗？谢谢！

Answer 1

隐藏层是位于输入层和输出层之间的任何层 (ref)。因此，所有这些都是您网络中的隐藏层：

encoded = layers.Dense(128, activation='relu')(input_img)
encoded = layers.Dense(64, activation='relu')(encoded)
encoded = layers.Dense(32, activation='relu')(encoded)
decoded = layers.Dense(64, activation='relu')(encoded)
decoded = layers.Dense(128, activation='relu')(decoded)

在自动编码器中，有一个特别有趣的隐藏层：网络中的“瓶颈”隐藏层，它强制对原始输入进行压缩知识表示。在您的示例中，它是 784 到 32 压缩，瓶颈隐藏层为：

encoded = layers.Dense(32, activation='relu')(encoded)

source

隐藏层在哪里？

Where are the hidden layers?

keras

neural-network

nlp

keras-layer

autoencoder