Name: Swift for TensorFlow: 次世代の機械学習フレームワーク (TF Dev Summit '19) (Swift for TensorFlow: The Next-Generation Machine Learning Framework (TF Dev Summit '19))
Uploaded: 2021-01-14T10:35:00.000Z
Duration: 31 min 22 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：

And we're super excited to tell you about a new approach

And we've learned a lot over the last few years

And we've incorporated most of that all into TensorFlow 2.

But, here, we're looking a little bit further

Well, eager mode makes it really easy to train a dynamic model.

But deploying it still requires you take that and then write

Similarly, some researchers are interested in taking machine

learning models and integrating them into larger applications.

That also often requires writing C++ code.

We always want more flexible and expressive autodifferentiation

is being able to define reusable types that

And we always love improving your developer workflow.

by taking errors in your code and bringing them

to your source and also by just improving your iteration time.

is lift TensorFlow to entirely new heights.

And to do that, we need to be able to innovate

This includes the compiler and the language.

And that's what Swift for TensorFlow is all about.

We think that applying new solutions to old problems

can help push machine learning even further than before.

Swift is a modern and cross-platform programming

language that's designed to be easy to learn and use.

And also, they encourage good API design.

Now, Swift uses type inference, so it's really easy to use

But it's also open source and has an open language evolution

process, which allows us to change the language

and make it better for machine learning which is really great.

This is how you define a simple model in Swift for TensorFlow.

As you can see, we're laying out our layers here.

And then we can find a forward function, which composes them

You've probably noticed that this looks a lot like Keras.

We want you to be able to take what you know about Keras

and bring it forward into this world as well.

Now, once we have a simple model, let's train it.

pick an optimizer and some random input data,

One of the reasons we like writing by hand

is that it gives you the maximum flexibility

to play with different kinds of constructs.

And you can do whatever you want, which is really great.

But some of the major advantages of Swift for TensorFlow

And so instead of telling you about it, what do you think,

All right, the team has thought long and hard

about what's the easiest way for people to get started

And what could be easier than just opening up a browser tab?

This is Google Colab, hosted Jupyter notebooks.

And it comes with Swift for TensorFlow built right in.

that Chris just showed you a couple of slides ago.

And we're going to run it using some random training

We're going to use the stochastic gradient descent SGD

Swift for TensorFlow in our browser on some training data

Now, we can see the training loss is decreasing over time.

But if you're ever like me and whenever I try and use

字幕リスト動画再生

Swift for TensorFlow: 次世代の機械学習フレームワーク (TF Dev Summit '19) (Swift for TensorFlow: The Next-Generation Machine Learning Framework (TF Dev Summit '19))

context

arbitrary

bias

applause