You are part of a data science team at an auto insurance company tasked with developing a proof-of-concept machine learning application. The application aims to use images of damaged vehicles to identify damaged parts. Your team has assembled a set of annotated images from the company's damage claim documents database. Each image is annotated with bounding boxes indicating the damaged parts and their respective names. You have sufficient budget and access to Google Cloud services to train your models. Given the need for quick initial model development, what should you do?