Image classification application
Let's see how it works by creating an image classification application with the MobileNet model. As we have already seen, MobileNet is a lightweight model designed for image classification tasks on edge devices. The model was invented by Google in 2017. As it tries to solve the trade-off problem between efficiency and accuracy, it achieves optimal model fitting in resource-constrained environments such as mobile devices without losing much accuracy. TensorFlow.js is categorized as the framework running on the edge device. MobileNet matches the primary use cases of TensorFlow.js.
First, we need to install the model via npm. You can do this using npm install @tensorflow-models/mobilenet or yarn add @tensorflow-models/mobilenet ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access