© Juan De Dios Santos Rivera 2020
J. D. D. S. RiveraPractical TensorFlow.jshttps://doi.org/10.1007/978-1-4842-6273-3_5

5. Making a game with PoseNet, a pose estimator model

Juan De Dios Santos Rivera1 
(1)
San Juan, PR, USA
 

Time for a fun application! Are you ready to pose? I hope so, because in this exercise your movements are the test dataset.

In this chapter, you will implement a game that features the model known as PoseNet. PoseNet is a neural network capable of doing real-time human pose estimation in images and videos. In this context, estimating a pose refers to the task of identifying where a person’s body joints and other parts appear in a frame. For example, Figure 5-1 is a screenshot from the app, and on the canvas located at the center, ...

Get Practical TensorFlow.js: Deep Learning in Web App Development now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.