Code

Let explain the code..

We start to create our HTML file and add our tensorflow js library and posenet model.

<html>
    <head>
    <!-- Load TensorFlow.js and Posenet Library-->
        <meta charset="utf-8"/>
        <script src="https://unpkg.com/@tensorflow/tfjs"></script>
        <script src="https://unpkg.com/@tensorflow-models/posenet"></script>
    </head>

We define an image or a video input so it could be load in our ponsenet function.

We also need to define some parameters such as: imageScaleFactor, outputStride, flipHorizontal.

<body>
        <img id="people" src="C:\Users\REY1GA\Documents\single.jpg" style="width: 600px; height: 600px;">
    </body>

    <script>
        var imageScaleFactor = 0.5;
        var outputStride = 16;
        var flipHorizontal = false;

        var imageElement = document.getElementById('people')

        posenet.load().then(function(net){
        return net.estimateSinglePose(imageElement,imageScaleFactor,flipHorizontal,outputStride)
        }).then(function(pose){
         console.log(pose);
        })
    </script>
</html>

Our output we could see and mode developer in the console. Something like this:

If we want to make a multipose detection we need to make some changes on our function.

PreviousPose EstimationNextBest-fit line approximation

Last updated

Was this helpful?