Serve ML model with Flask REST API - 2

train_model.py

normalizer = preprocessing.Normalization(axis=-1)
normalizer.adapt(np.array(train_features))

model = keras.Sequential(
    [
        normalizer,
        layers.Dense(64, activation="relu"),
        layers.Dense(64, activation="relu"),
        layers.Dense(1),
    ]
)

model.compile(loss="mean_absolute_error", optimizer=tf.keras.optimizers.Adam(0.001))

train_features, test_features, train_labels, test_labels = get_data()
model = get_model(train_features)
model.summary()
history = model.fit(
    train_features, train_labels, validation_split=0.2, verbose=2, epochs=100
)