Project Statement:

Marina Pier Inc. is leveraging technology to automate their operations on the San Francisco port.

The company’s management has set out to build a bias-free/ corruption-free automatic system that reports & avoids faulty situations caused by human error. Examples of human error include misclassifying the correct type of boat. The type of boat that enters the port region is as follows.

Buoy Cruise_ship Ferry_boat Freight_boar Gondola Inflatable_boat Kayak Paper_boat Sailboat Marina Pier wants to use Deep Learning techniques to build an automatic reporting system that recognizes the boat. The company is also looking to use a transfer learning approach of any lightweight pre-trained model in order to deploy in mobile devices.

As a deep learning engineer, your task is to:

Build a CNN network to classify the boat. Build a lightweight model with the aim of deploying the solution on a mobile device using transfer learning. You can use any lightweight pre-trained model as the initial (first) layer. MobileNetV2 is a popular lightweight pre-trained model built using Keras API.