Name: TensorFlow Lite (TensorFlow @ O'Reilly AI Conference, San Francisco '18) (TensorFlow Lite (TensorFlow @ O’Reilly AI Conference, San Francisco '18))
Uploaded: 2021-01-14T10:03:24.000Z
Duration: 17 min 41 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：

ANDREW SELLE: So today I'm going to talk about TensorFlow Lite,

and I'll give you an intro to what that is.

I'm a software engineer down in Google in Mountain View land.

We're going to be talking about machine learning on-device.

So how many of you are interested on running

So you already know that machine learning on-device

So I'm going to give you a scenario that's

perhaps a little bit out of the ordinary.

So I want to hang my cell phone on the outside of my tent

so that if I'm in the middle of the night

and the bear is coming for me, I'll know.

but that's a great example of what you do with on-device ML.

So you basically want to have low latency.

You don't want to wait for the bear to already be upon you.

You want to make sure it works without a data connection.

The data can stay on the device and you have access

So there's a lot more kind of practical and important use

And so people are, of course, doing a lot more ML on-device.

So that's why we started TensorFlow Lite.

So in short, TensorFlow Lite is our solution

So here's an example of what TensorFlow Lite can do.

Well, I know what they are, but I want my phone

In the bottom you see kind of the confidence.

It can do kind of ordinary office objects,

but also important objects like TensorFlow logos.

So here we have it running on an Android phone and an IOS phone.

We can also do things like this Android Things Toolkit.

And there is going to be a couple more later, which

let's talk a little bit more about what TensorFlow Lite is.

It has tight memory constraints, you need to be low energy,

and you don't have as much computation as you do available

that are going to sort of deal with these problems.

So the first one is it needs to be portable.

You know, normal PCs we run on, but we also

run on mobile phones, we run on Raspberry Pi, or other Linux

And we also want to go to much smaller devices

Well, we'll skip that slide, whatever that was.

But in any case, basically, this portability

is achieved through the TensorFlow Lite file format.

So once you have a trained TensorFlow model, like you

you could author it with Python, whatever you do,

you produce a saved model in a graph form.

The serialized form is then converted to TensorFlow Lite

format, which then is your gateway to running on all

if you want to target IOS in this especially way.

The second property is that it's optimizable.

We have model compression, we have quantization,

to ensure that we have the best performance, as well

And this is achieved through the architecture.

So we have a converter, which we already talked about,

字幕リスト動画再生

TensorFlow Lite (TensorFlow @ O'Reilly AI Conference, San Francisco '18) (TensorFlow Lite (TensorFlow @ O’Reilly AI Conference, San Francisco '18))

basically

experience

achieve

random