AutoEncoder_v1

# build encoder model
def encoder_model(inputs):
    x1 = Dense(intermediate_dim_1, activation='relu')(inputs)
    x2 = Dense(intermediate_dim_2, activation='relu')(x1)
    x3 = Dense(intermediate_dim_3, activation='relu')(x2)
    encoded = Dense(latent_dim)(x3)
    encoder = Model(inputs, encoded, name='encoder')
    return encoder

# build decoder model
def decoder_model():
    latent_inputs = Input(shape=(latent_dim,), name='z_space')
    x3 = Dense(intermediate_dim_3, activation='relu')(latent_inputs)
    x2 = Dense(intermediate_dim_2, activation='relu')(x3)
    x1 = Dense(intermediate_dim_1, activation='relu')(x2)
    decoded = Dense(original_dim)(x1)

    # instantiate decoder model
    decoder = Model(latent_inputs, decoded, name='decoder')
    return decoder



if __name__ == '__main__':


    x_trn,x_val,y_trn,y_val = train_test_split(Cp_inputs, X_all, test_size=0.2,shuffle=True,random_state=0)
    original_dim = x_trn.shape[1]
    x_trn = np.reshape(x_trn, [-1, original_dim])
    x_val = np.reshape(x_val, [-1, original_dim])


    input_shape = (original_dim, )
    inputs = Input(shape=input_shape, name='encoder_input')

    # Define Intermediate Layer Dimension and Latent layer Dimension
    intermediate_dim_1 = 256
    intermediate_dim_2 = 128
    intermediate_dim_3 = 64
    latent_dim = 3

    # Define batch_size / epochs
    epochs = 200
    batch_size = 128

    encoder = encoder_model(inputs)
    decoder = decoder_model()
    # instantiate VAE model
    outputs = decoder(encoder(inputs))
    ae = Model(inputs, outputs, name='ae_mlp')

    reconstruction_loss = mse(inputs, outputs)

#     reconstruction_loss = binary_crossentropy(inputs, outputs)
    ae.add_loss(reconstruction_loss)
    opt = tf.keras.optimizers.Adam(lr=0.001)
    ae.compile(optimizer=opt, loss='mse')
    history = ae.fit(x_trn, x_trn, epochs=epochs, batch_size=batch_size, validation_data=(x_val, x_val))