How to train MobileNet from scratch?

[smitshilu]

Hello, I want to train MobileNet from scratch. I have all the image data available but I am not sure about input and output layers of MobileNet. I am using something like this but not sure whether it is right or not?

model = MobileNet()
x = model.output
# let's add a fully-connected layer
x = Dense(1024, activation='relu')(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(1, activation='softmax')(x)

# this is the model we will train
model = Model(inputs=model.input, outputs=predictions)
model.compile(loss='binary_crossentropy',
              optimizer='Adam',
              metrics=['accuracy'])

Can you please help me with an example MobileNet training?

Thank you