Just like TensorFlow, TensorFlow.js has a bunch of ecosystem libraries. These libraries help us to build applications quickly and efficiently because some of them are designed to allow us to develop machine learning applications intuitively. In this chapter, we are going to introduce tools and libraries built on top of TensorFlow.js that we can use to accelerate the development of our application. Because these libraries are available as open source software, you can customize and contribute to them if necessary to meet your requirements.
The following topics will be covered in this chapter:
- Why high-level libraries?
- Using existing machine learning models
- MobileNet in tfjs-models
- Supported models by tfjs-models
- Image classification application
- Example applications in the community
- Loading the data from various kinds of storage
- Data sources
- Webcam
- Pose...