How do I create the decoder part of the Autoencoder?

Question

I am trying to copy the layers from the Encoder to create the decoder but I'm getting "Index Error".

input_img =Input(25425,)

encoded1 = Dense(75,activation=tf.nn.relu)(input_img)

encoded = Dense(50,activation=tf.nn.relu)(encoded1)

decoded = Dense(25425, activation='sigmoid')(encoded)

autoencoder = Model(input_img, encoded1, decoded)

encoder = Model(input_img, encoded)

encoded_input = Input(shape=(50,))


decoder_layer1 = autoencoder.layers[1](encoded_input)

decoder_layer2 = autoencoder.layers[0](decoder_layer1)

decoder = Model(encoded_input, decoder_layer1, decoder_layer2)

autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')

autoencoder.fit(X, X,
            epochs=50,
            shuffle=True)

I expect the decoder to have the same layers ans the encoder just reversed but I'm not able to copy the layers over. I am getting this Error:

Traceback (most recent call last):
File "C:\Users\dalto\Documents\geo4\train.py", line 36, in <module>
decoder_layer1 = autoencoder.layers[1](encoded_input)
IndexError: list index out of range

Answer 1

You have several mistakes in you code. See my comments in the working snippet:

# Random input for testing purposes
X = np.random.rand(10, 25425)

input_img =tf.keras.layers.Input(25425,)
encoded1 = tf.keras.layers.Dense(75,activation=tf.nn.relu)(input_img)
encoded2 = tf.keras.layers.Dense(50,activation=tf.nn.relu)(encoded1)
decoded = tf.keras.layers.Dense(25425, activation='sigmoid')(encoded2)
# The input of the autoencoder is the image (input_img), and the output is the decoder layer (decoded)
autoencoder = tf.keras.Model(input_img, decoded)

encoder = tf.keras.Model(input_img, encoded2)

encoded_input = tf.keras.layers.Input(shape=(50,))
# The decoded only consists of the last layer
decoder_layer = autoencoder.layers[-1](encoded_input)
# The input to the decoder is the vector of the encoder which will be fed (using encoded_input), the output is the last layer of the network (decoder_layer)
decoder = tf.keras.Model(encoded_input, decoder_layer)

autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(X, X, epochs=50, shuffle=True)