Name: ml5.js: Pose Classification with PoseNet and ml5.neuralNetwork()
Uploaded: 2020-03-28T18:26:50.000Z
Duration: 26 min 34 s
Description: Thousands of YouTube videos with English-Chinese subtitles! Now you can learn to understand native speakers, expand your vocabulary, and improve your pronunciation...

And welcome to another video using Posenet and ML5.js.

to do is take the output of the Posenet pre-trained model,

and feed that into an ML5 neural network to train,

I'm making certain motions like a y, and m, a c, and an a.

Before I begin coding, let me quickly mention

something I added between the last video and now.

I'm mirroring the image so that when I raise my left hand,

it's mirrored to me what I'm seeing on the screen in front

It makes it feel much more intuitive and natural to see

a specific function called Flip Image that will do it for you.

drawing all this other stuff, that it's easier for me

In other words, typically if I'm drawing an image, it's 00,

I'm drawing it right here, and the image gets painted across

it sets the x-axis going in the other direction.

And if I translate over to here and put 00 here and draw

the image this way, it will appear reversed-- inverted,

So that's what's happening in these three steps right here.

The two videos that I'm assuming are prerequisites

here are the previous one, where I covered

all of the code for this particular Posenet example

that you're seeing running right here in the web editor,

as well as this train your own neural network set

the ML5 neural network function works to train a model

to play musical notes based on where the user clicks

To get started, I could really begin with either one

For example, I could go and get my Posenet code

and bring it into this particular sketch.

Or I could take the neural network code from this sketch

I think I want to continue working from the Posenet sketch

is create an object to store the neural network.

And then after I initialize the Posenet model,

I'll say Brain is a new ML5 neural network.

an ML5 neural network, you can find on the documentation

I'm just starting with these four basic properties-- inputs,

So let's come over here to the whiteboard.

Now remember, we're starting with the Posenet machine

We're sending an image into that model as the input.

as to where all the key points are on the human body

And all of those points come in the form of xy pairs,

in as the input to my ML5 neural network.

ML5 neural network will take all these xy pairs

and classify them into a given pose that has a label.

It's a dab pose, or a Saturday Night Fever pose.

I don't know what kind of poses I'm going to make.

This now tells me how I want to configure my neural network.

And I want it to classify those 34 numbers

34 inputs, four outputs, the task is classification.

And I do want to see debugging as I'm training the model.

And I have to give those options to the ML5 neural network

This is where things get kind of complicated because I

Subtitles ListPlay Video

ml5.js: Pose Classification with PoseNet and ml5.neuralNetwork()

flip

confidence

previous

implement