问在Keras中使用数值数据集的自动编码器

EN

from keras.layers import Input,Dense
from keras.models import Model

# number of neurons in the encoding hidden layer
encoding_dim = 5
# input placeholder
input_data = Input(shape=(6,)) # 6 is the number of features/columns
# encoder is the encoded representation of the input
encoded = Dense(encoding_dim, activation ='relu')(input_data)
# decoder is the lossy reconstruction of the input
decoded = Dense(6, activation ='sigmoid')(encoded) # 6 again number of features and should match input_data


# this model maps an input to its reconstruction
autoencoder = Model(input_data, decoded)




# this model maps an input to its encoded representation
encoder = Model(input_data, encoded)
# model optimizer and loss
autoencoder = Model(input_data, decoded)

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

# train test split
from sklearn.model_selection import train_test_split
x_train, x_test, = train_test_split(data, test_size=0.1, random_state=42)


# train the model
autoencoder.fit(x_train,
                x_train,
                epochs=50,
                batch_size=256,
                shuffle=True)

autoencoder.summary()

# predict after training
# note that we take them from the *test* set
encoded_data = encoder.predict(x_test)