Name: ジャカード日常のオブジェクトにMLをシームレスに埋め込む (TF Dev Summit '20) (Jacquard: Embedding ML seamlessly into everyday objects (TF Dev Summit '20))
Uploaded: 2021-01-14T10:04:08.000Z
Duration: 10 min 15 s
Description: VoiceTubeの動画で発音を聞きながら英語表現を覚えよう！学べる英語：

程度の副詞

We've just heard from the TensorFlow Light Team

how it's getting even easier to place machine

And I'm sure this got many of you thinking,

embed machine learning directly into everyday objects.

me tell you a little bit about Jacquard platform.

that extends everyday objects with extraordinary powers.

At the core of the Jacquard platform is the Jacquard tag.

can be seamlessly integrated into everyday objects,

like your favorite jacket, backpack, or pair of shoes.

The tag features a small embedded ARM processor

that allows us to run ML models directly on the tag with only

being emitted via BLE to your phone when detected.

What's interesting is that the tag has a modular design, where

on the tag as a standalone unit or via additional low-power

compute modules that can be attached along

with other sensors, custom LEDs, or haptic motors.

A great example of this is the Levi's Trucker Jacket

So if we can switch over to the overhead camera,

so here I can take Jacquard tag and add it

to a specifically designed sensor module which

What happens now is that this talks to an M0 processor that's

is talking to some integrated sensor lines in the jacket.

The M0 processor not only reads data from the sensor lines,

but it also allows us to run ML directly on the tag.

This allows us to do gestures, for example, on the jacket

So for example, I can do a double tap gesture,

Or I can use a cover gesture to silence it.

Users can also use swipe in and swipe out gestures

to control their music, drop pins on maps,

What's important here is that all of the gesture recognition

This means that we can run these models at super low power,

sending only the events to the user's phone via the Jacquard

So I'm sure many of you are wondering how we're actually

that you can go to your Levi's store and buy today.

So as most of you know, there are three big on-device ML

challenges that need to be addressed to enable platforms

So first is how can we train high-quality ML models that

Second, let's assume we've solved problem one and have

a TensorFlow model that's small enough to fit within our memory

on low compute embedded devices for real-time inference?

And third, even if we solve problems one and two,

it's not going to be a great user experience

if the user has to keep charging their jackets

So how can we ensure the ML model's always

when needed while still providing multi-day experiences

Specifically for Jacquard, these challenges have mapped

to deploy models as small as 20 kilobytes,

or running ML models on low-compute microprocessors,

like a Cortex-M0+, which is what's embedded here

To show you how we've addressed these challenges for Jacquard,

I'm going to walk you through a specific case study for one

of our most recent products, so recent, in fact, that it

First, I'll describe the product at a high level,

and then we can review how we've trained and deployed

ML models that in this case fit in your shoe.

So the latest Jacquard-enabled product is called GMR.

being built in collaboration between Google, Adidas,

With gamer GMR, you can insert the same tag that's

inserted in your jacket into an Adidas insole

So you can see here where the tag inserts at the back.

The ML models in the tag will be able to detect

字幕リスト動画再生

ジャカード日常のオブジェクトにMLをシームレスに埋め込む (TF Dev Summit '20) (Jacquard: Embedding ML seamlessly into everyday objects (TF Dev Summit '20))

multiple

specifically

cortex

reward