Name: TensorFlow.js 1.0 (TF Dev Summit '19) (TensorFlow.js 1.0 (TF Dev Summit '19))
Uploaded: 2021-01-14T10:34:51.000Z
Duration: 17 min 51 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：

My name's Nick, and this is my colleague, Yannick.

We're going to talk today about JavaScript and ML.

TensorFlow.js is a library we launched last year.

It's a library for training and deploying ML models

We want to showcase what you can do today with the platform

If you run it in the browser, you can get out-of-the-box GPU

The browser itself tends to be very interactive by nature,

And privacy is a very important part to the library.

You can run inference and training locally

on the client, which works around all sorts of privacy

issues you might have with doing server-side inference

And what can you do today with the library?

Well, we have a collection of pre-trained, off-the-shelf

models that you can use without any knowledge of ML.

We also have the ability to take existing Python models

and convert them and run them in TensorFlow.js.

We also have a full stack for training, inference,

And that runs in the browser and Node.js.

that JavaScript can run on outside of just the browser.

The first one is a bunch of pre-trained-- or off-the-shelf

They are image, audio, and text classification models.

You don't have to worry about converting images.

They're very high-level, easy-to-use APIs.

These are available on NPM for local application development.

Or we also have pre-compiled hosted scripts as well.

We'll also be working on this a lot in the upcoming year.

We'll have more and more models as we go forward.

We were actually showcasing this at our booth.

And I want to show you how easy it is to use this model.

So the first thing we need do is include the library

This can be done with our pre-compiled scripts.

So I have a picture of my toddler trying to do yoga.

isn't so much a human just like this and finding arms and legs.

He's trying to do something on the couch.

So the first thing to do is to load the BodyPix model--

And the next step is to call one of the methods we expose,

This returns a JavaScript object with the width and height

of the object or the image and a value for every pixel that

was in the image, if it's an arm, or a leg,

There's also a bunch of really easy-to-use methods for doing

Another model we just launched just a couple of weeks

It's a out-of-the-box text classification model.

Again, to use this model, we'll use the pre-hosted scripts--

some really lovely text, pretty PG-- you suck.

And I'll get a result back again as a JavaScript object

that has the seven labels that we identify

different types of toxic type text, and the probabilities,

We also have the ability to take pre-trained Python models

So if you have a pre-trained model today that's already

been trained in Python world, we have a command line tool

that makes it very easy to serialize the model as a JSON

object, and the weights, and distribute them

We support Saved Model, TFHub, and Keras models.

And we will be TensorFlow 2.0 compatible.

I want to walk through how simple it is to use this.

字幕リスト動画再生

TensorFlow.js 1.0 (TF Dev Summit '19) (TensorFlow.js 1.0 (TF Dev Summit '19))

bunch

community

industry

function