import keras
from keras import backend as K
from keras.layers.core import Dense, Activation
from keras.optimizers import Adam
from keras.metrics import mean_squared_error
from keras.preprocessing.image import ImageDataGenerator
from keras.preprocessing import image
from keras.models import Model
from keras.applications import imagenet_utils
from keras.layers import Dense, GlobalAveragePooling2D
from keras.applications import MobileNetV2
from keras.applications.mobilenet import preprocess_input
import numpy as np
from IPython.display import Image
from keras.optimizers import Adam

# imports the mobilenet model and discards the last 1000 neuron layer.
base_model = MobileNetV2(weights='imagenet', include_top=False)

x = base_model.output
x = GlobalAveragePooling2D()(x)
# we add dense layers so that the model can learn more complex functions and classify for better results.
x = Dense(512, activation='relu')(x)  # dense layer 3
preds = Dense(1, activation='relu')(x)  # final layer with softmax activation

base_model.compile(optimizer='Adam', loss='mean_squared_error')
base_model.summary()

# https://towardsdatascience.com/transfer-learning-using-mobilenet-and-keras-c75daf7ff299