Book Image

Hands-On Machine Learning with TensorFlow.js

By : Kai Sasaki
Book Image

Hands-On Machine Learning with TensorFlow.js

By: Kai Sasaki

Overview of this book

TensorFlow.js is a framework that enables you to create performant machine learning (ML) applications that run smoothly in a web browser. With this book, you will learn how to use TensorFlow.js to implement various ML models through an example-based approach. Starting with the basics, you'll understand how ML models can be built on the web. Moving on, you will get to grips with the TensorFlow.js ecosystem to develop applications more efficiently. The book will then guide you through implementing ML techniques and algorithms such as regression, clustering, fast Fourier transform (FFT), and dimensionality reduction. You will later cover the Bellman equation to solve Markov decision process (MDP) problems and understand how it is related to reinforcement learning. Finally, you will explore techniques for deploying ML-based web applications and training models with TensorFlow Core. Throughout this ML book, you'll discover useful tips and tricks that will build on your knowledge. By the end of this book, you will be equipped with the skills you need to create your own web-based ML applications and fine-tune models to achieve high performance.
Table of Contents (17 chapters)
Free Chapter
1
Section 1: The Rationale of Machine Learning and the Usage of TensorFlow.js
5
Section 2: Real-World Applications of TensorFlow.js
12
Section 3: Productionizing Machine Learning Applications with TensorFlow.js

Questions

  1. What is the serialization format used by the model definition file of SavedModel?
  2. What kind of file format does the Keras API export?
  1. Let's assume we want to convert the following model. Please describe the options for converting it using tfjs-converter:
    1. SavedModel
    2. The model tag is my_mobilenet1
    3. The output node name is y
  2. Write code to import a pretrained MobileNet into TensorFlow.js. The model is uploaded to TensorFlow Hub: https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/classification/3.
  3. What is the recommended model size to import a model into web browsers in general? Do you think you can optimize the memory footprint of the SavedModel or Keras model?
  4. In order to achieve the best performance when loading the model via HTTP, how big should each shard of the weight variable file be in the web format?