Name: 機器學習在你的設備上。選項（Google I/O'19 (Machine Learning on Your Device: The Options (Google I/O'19))
Uploaded: 2021-01-14T10:37:13.000Z
Duration: 38 min 32 s
Description: 【看影片學英語】數萬部 YouTube 影片，搭配英漢字典即點即查，輕鬆掌握單字發音與用法，長久累積看電影不必再看字幕。

DANIEL SITUNAYAKE: And we have an awesome talk

the keynote, because there's just been so much stuff

to be talking about today, which is running machine

that you can do if you're running ML at the edge

But there are a ton of options that developers have

And it can be a little bit hard to navigate.

So we decided to put this session together

We're going to be showing you all the options,

walking you through some code, and showing you

So first, we're going to walk through using TensorFlow

to train models and then export saved models, which

you can then convert to deploy on devices.

We're then going to see a number of different ways

that you can deploy to Android and iOS devices.

some new and super exciting hardware devices that you

an overview of some different technologies and the device

which is designed to make it super easy to deploy

We then have TensorFlow.js, which basically

lets you target any device that has a JavaScript interpreter,

whether that's in browser or through Node.js.

So that even supports embedded platforms.

high performance inference across any device or embedded

talk a little bit about TensorFlow itself.

So TensorFlow is Google's tool chain for absolutely everything

And as you can see, there are TensorFlow tools

for basically every part of the ML workflow,

from loading data through to building models

and then deploying them to devices and servers.

going to focus on building a model with TensorFlow

and then deploying it as a TensorFlow Lite model.

There are actually tons of ways to get up

So the quickest way is to try out our demo apps and sample

And we also have a big library of pretrained models

that you can drop into your apps that are ready to use.

based on your own data using transfer learning.

based on distributed data across a pool of devices.

And you can finally build models from scratch,

which is what Laurence is now going to show off.

How many of you have ever built a machine learn model?

So hopefully, this isn't too basic for you,

of building a model and some of the stops

that you can then do to prepare that model

to run on the mobile devices that Daniel was talking about.

Wave them like this if you need it bigger.

OK, some do, or you just want to stretch.

So I'm just going to show some very basic TensorFlow

So for those of you who've never built something in machine

learning or have never built a machine learn model,

字幕列表影片播放

機器學習在你的設備上。選項（Google I/O'19 (Machine Learning on Your Device: The Options (Google I/O'19))

complex

relationship

function

neural