The project will provide an in-depth discussion on how to build a custom TensorFlow Lite model that is able to perform recognition of plant species from images. The model will run on mobile devices and will be primarily used to recognize different plant species. The model uses a deep convolutional neural network (CNN) for image processing developed on the Keras API of TensorFlow. This chapter also introduces you to the usage of cloud-based APIs for performing image processing. The Cloud Vision API provided by Google Cloud Platform (GCP) has been taken as an example.
By the end of this chapter, you'll understand the importance of cloud-based services for deep learning (DL) applications as well as the benefits of on-device models for performing offline and instantaneous deep learning tasks on mobile devices.
In this chapter, we will cover the...