Name: TensorFlow Lite for on-device ML (TensorFlow Meets) (TensorFlow Lite for on-device ML (TensorFlow Meets))
Uploaded: 2021-01-14T10:03:10.000Z
Duration: 7 min 24 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：

So, welcome to this episode of TensorFlow Meets,

to 不定詞

where I'm really delighted to welcome Razial

straight from his talk at the TensorFlow Dev Summit.

Can you tell us a little bit about you and what you do?

I'm an Engineering Lead at TensorFlow Lite.

I'm particularly focused on model optimization,

which the goal is change the models in certain ways

that can be smaller and faster to execute in edge devices.

Now, I have to say, I geek out about TensorFlow Lite.

If I have a favorite thing in TensorFlow, it's TF Lite.

I just love doing it, the demos are always great.

When I do talks, it's usually about that.

So, it's really fun to have you here to learn a little bit more.

Can you tell us what's going on with TensorFlow Lite right now?

we're really trying to make as easy as possible

because machine learning is moving from the server

And because of all of these characteristics

that you have on the Edge, it is challenging,

so we're trying to make that very, very easy.

Now, on the flip side, it also means that you have access to a lot of data,

it has a strong privacy-preserving component.

So, really, you can build products that otherwise wouldn't be possible

if you just rely on server-side execution.

So, the way I see our work is we're enabling the next generation

Now, to the people who may be familiar with TensorFlow Lite,

they would think about it as running on Android or iOS,

but you're also extending now into IoT devices.

Yeah, we're extending to a lot of places.

The Google Assistant is one example of that

where if you think the assistant is running on Android,

but it's also running in many other types of wearables.

They're really trying to push the boundaries

and learn about those use cases, and power those.

We also have this new project about micro-controllers.

because we're pushing now more to IoT devices.

Again, we're really trying to push machine learning everywhere.

So, one of my favorite scenarios of using it on a mobile device

Where it's like these plants in Tanzania, and you can diagnose them for disease

by just waving your phone over them like this.

So, it's just a really exciting scenario.

Do you see any other good, fun scenarios around TensorFlow Lite

or maybe even using it in embedded systems?

Yeah, like I said, one of the great things of machine learning on the device

is that you also do away with the requirements of connectivity.

This is very important for many different countries--

the connectivity, perhaps, comes at a challenge or is costly,

so we're trying to enable all those things.

we're trying to support more and more hardware

so you can execute better and larger and more complex models on these devices

and do even more exciting things with them.

and that's something we're really excited that we support it right now,

and we're working with them to make it even better and even faster.

we have this very nice slide of MobileNet.

MobileNet is a very common image recognition neural network,

and you can see the progress from executing in floating point in CPU

which is the baseline to be able to execute in CPU [quantized],

The GPU was already seven times faster than what you can get from a regular CPU.

And if you look at the numbers for the Edge TPU,

And this is really important because the quality of the model

is very much directly related to the size and the computation.

So, by enabling larger models, then we can also enable better quality

One of the things you were mentioning there about particularly complex models,

Now, it used to be that was part of the conversion process

when you're converting to TF Lite, but now you can do it beforehand?

Yes, we can do it before and we can do it after.

The nice thing of beforehand is that you can get even better quality.

So, typically, with all of these techniques,

you have a model, and you apply one of these techniques,

and it might affect your accuracy a little bit.

So, by doing it at training time, we're really trying to minimize that loss,

Now, the nice thing is also that being part of the TensorFlow,

as this really nice abstraction for neural network layers.

and if you look at other APIs that are coming very soon,

字幕リスト動画再生

TensorFlow Lite for on-device ML (TensorFlow Meets) (TensorFlow Lite for on-device ML (TensorFlow Meets))

episode

scenario

engage

experience