fine_tuning_network.py

# Load the MobileNetV2 model but exclude the classification layers
EXTRACTOR = MobileNetV2(weights="imagenet", include_top=False,
  input_shape=(224, 224, 3))

# We will set it to both True and False
EXTRACTOR.trainable = True

# Construct the head of the model that will be placed on top of the
# the base model
class_head = EXTRACTOR.output
class_head = GlobalAveragePooling2D()(class_head)
class_head = Dense(512, activation="relu")(class_head)
class_head = Dropout(0.5)(class_head)
class_head = Dense(5, activation="softmax")(class_head)

# Create the new model
classifier = Model(inputs=EXTRACTOR.input, outputs=class_head)

# Compile and return the model
classifier.compile(loss="sparse_categorical_crossentropy", 
    optimizer="adam",
    metrics=["accuracy"])