Google AutoML: Cloud Vision
Ekaba Bisong · Apress eBooks · 2019
Google Cloud AutoML Vision facilitates the creation of custom vision models for image recognition use cases. This managed service works with the concepts of transfer learning and neural architecture search under the hood to find the best network architecture and the optimal hyper-parameter configuration of that architecture that minimizes the loss function of the model. This chapter will go through a sample project of building a custom image recognition model using Google Cloud AutoML Vision. In this chapter, we will build an image model to recognize select cereal boxes.