Name: Edge TPU live demo: Coral Dev Board & Microcontrollers (TF Dev Summit '19)
Uploaded: 2020-03-25T09:24:19.000Z
Duration: 15 min 53 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 I'm real excited to be here to talk about a new project

So TensorFlow Lite for microcontrollers--

So this all comes back to when I actually first joined Google

And as you can imagine, there were a whole bunch

of internal projects that I didn't actually

know about, as a member of the public, that

But one in particular came about when I actually

spoke to Raziel for the first time, and he explained.

And he was on the speech team at the time working

And he explained that they use neural network models

At that time I only really had experience with image networks.

So this idea of having a 13-kilobyte model

he told me why these models had to be so small.

They needed to run them on these DSPs and other embedded chips

So Android could listen out for wake words, like "Hey, Google,"

while the main CPU was powered off to save the battery.

had tens of kilobytes of RAM and flash storage.

So they simply couldn't fit anything larger.

They also couldn't rely on cloud connectivity

because the amount of power that would have been drained just

keeping a radio connection alive to send data over

So that really struck me, that conversation

and the continued work that we did with the speech team,

doing all sorts of different approaches with speech.

They'd spent a lot of time and a lot of energy experimenting.

of these embedded devices, neural networks

were better than any of the traditional methods they used.

be really useful for other embedded sensor applications

And it left me really wanting to see if we could actually

build support for these kind of devices into TensorFlow itself,

so that more people could actually get access.

At the time, only people in the speech community

really knew about the groundbreaking work that

So [LAUGHS] today, I'm pleased to announce

that we are releasing the first experimental support

for embedded platforms in TensorFlow Lite.

is a demonstration board that I actually have in my pocket.

And it has a Cortex-M4 processor with 384 kilobytes of RAM

And it was built by Ambiq to be extremely low power,

drawing less than one milliwatt in a lot of cases.

So it's able to run on a single coin battery like this

And I'm actually going to take my life in my hands

[LAUGHS] So let us see if this is actually--

is, by saying a particular word, and see if it actually lights

That's just telling me that it's running [INAUDIBLE]..

[LAUGHS] I knew I was taking my life into my hands here.

So I'm going to quickly move that out of the spotlight.

[LAUGHS] So as you can see, it's still far from perfect.

a job of recognizing when I say the word,

and not lighting up when there's unrelated conversations.

Well first, this is running entirely locally

So we don't need to have any internet connection.

So it's a good, useful first component of a voice interface

And the model itself isn't quite 13 kilobytes,

Subtitles ListPlay Video

Edge TPU live demo: Coral Dev Board & Microcontrollers (TF Dev Summit '19)

approach

bunch

recognize

extremely