autoencoder_feedforward.py

import numpy as np
import keras
from keras.datasets import mnist
from keras.models import Sequential, Model
from keras.layers import Dense, Input
from keras import optimizers
from keras.optimizers import Adam

(x_train, y_train), (x_test, y_test) = mnist.load_data()
train_x = x_train.reshape(60000, 784) / 255
val_x = x_test.reshape(10000, 784) / 255

autoencoder = Sequential()
autoencoder.add(Dense(512,  activation='elu', input_shape=(784,)))
autoencoder.add(Dense(128,  activation='elu'))
autoencoder.add(Dense(10,    activation='linear', name="bottleneck"))
autoencoder.add(Dense(128,  activation='elu'))
autoencoder.add(Dense(512,  activation='elu'))
autoencoder.add(Dense(784,  activation='sigmoid'))
autoencoder.compile(loss='mean_squared_error', optimizer = Adam())
trained_model = autoencoder.fit(train_x, train_x, batch_size=1024, epochs=10, verbose=1, validation_data=(val_x, val_x))
encoder = Model(autoencoder.input, autoencoder.get_layer('bottleneck').output)
encoded_data = encoder.predict(train_x)  # bottleneck representation
decoded_output = autoencoder.predict(train_x)        # reconstruction
encoding_dim = 10

# return the decoder
encoded_input = Input(shape=(encoding_dim,))
decoder = autoencoder.layers[-3](encoded_input)
decoder = autoencoder.layers[-2](decoder)
decoder = autoencoder.layers[-1](decoder)
decoder = Model(encoded_input, decoder)