Name: TensorFlow.js (TF Dev Summit '20)
Uploaded: 2020-03-31T06:56:32.000Z
Duration: 4 min 47 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...

I'm Ewa Matejska, and I'm a technical program

I'm a developer advocate on the TensorFlow.js team.

EWA MATEJSKA: So I hear you'll be telling us

And that's actually in many places, such as in the web

on React Native for mobile apps, and even

on Internet of Things, such as a Raspberry Pi.

EWA MATEJSKA: So why would I use it instead of, let's say,

So essentially, we have several superpowers

so be it on the server side or on the client side.

Now, on the client side, one of the key features is privacy.

So that allows you to do all the inference on the client

machine, not having to send that data to a remote server

somewhere, which might be critical for certain types

Now, linked to that, we also have lower latency

And then, of course, moving on from there, is cost.

you don't have to have a GPU running 24/7 just

I mean, the final point there is reach and scale.

Because anyone with a web browser can simply go to a link

and open it up, it just works out of the box.

So there's no need to install a complex Linux environment.

We have all the CUDA drivers, and everything else.

And this is particularly important for maybe researchers

because they could actually then utilize everyone in the world

to try out their model they've just launched

and see the performance and those edge cases

that they may have not detected when doing it just

EWA MATEJSKA: Do you have any demos for me?

JASON MAYES: So in addition to the existing demos that

such as object detection and [INAUDIBLE] estimation and body

segmentation, we are going to launch three new ones

And as you can see, it's running in real time

As I move my face around, it's tracking it pretty well,

And if I bring you in as well at the same time,

And so this is actually tracking 468 unique points

on each of our faces, and then rendering it to the screen.

And we're even showing that in 3D on the right-hand side

So we can actually represent a 3D model of your face

EWA MATEJSKA: How is it getting such awesome performance?

One key thing with TensorFlow.js on the client side

is that it supports multiple back ends to execute on.

we can run on the CPU, of course, which is the fail-safe.

can actually leverage WebGL to do all that mathematics for you

on the graphics card at high performance.

And we recently released WebAssembly support as well

across maybe older mobile devices on the CPU as well.

track my hands in much the same way we're

doing the face earlier, but this time with my hand.

And this can track 21 unique points on my hand.

this for something like gesture or maybe even sign language.

The choice is yours, whatever creative ideas