Name: TensorFlow.jl.TensorFlowの世界へのJuliaフロントエンド (TF Dev Summit '19) (TensorFlow.jl: A Julia Front End to the TensorFlow World (TF Dev Summit '19))
Uploaded: 2021-01-14T10:03:17.000Z
Duration: 5 min 27 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：

未来進行形

about TensorFlow.jl, an interface between Julia

Some of you have probably never heard of it.

It's a really dynamic yet performant programming language

developed at MIT since around 10 years ago.

It's a fresh rethinking of what a scientific programming

And version 1.0 was finally realized last year

So I'm going to give you a whirlwind tour of what

Julia is and then talk to you about TensorFlow.jl.

can guess what this is doing, except this @show business,

I do machine learning by day and open source

For one thing, it's got an ultrafast just-in-time

So here I'm running an autoregressive process

using for loops, which I think is the most natural way

And why don't we just run that for 100 million iterations

And you can see the syntax looks pretty similar between them.

So anyone from a LISP background will appreciate this.

You can write a macro that takes in Julius syntax

that checks if a number is less than zero

it can print out the name of the variable

You can't really do that with a normal Python function.

And there's this really nice multiple dispatch system

where you can define multiple versions of a function,

on the types of all the arguments at runtime.

So here's a really cool rock-paper-scissor example

And what's nice is I can say that for any shape,

if shape A beats shape B, then shape B loses to shape A.

And I can encode that information with one line.

We've about doubled in GitHub stars in the last year alone.

It's clearly inspired by Keras and the whole Tensor 2.0 world.

We're now eager by default, but graph mode is available.

If you choose to use graph mode, macros will help you out.

So here a macro is transforming native Julia, the control flow,

with this while loop into a graph mode while loop.

And macros can do other nice things for you.

Here we're visualizing a program with TensorBoard.

are automatically inferred from the variable names, which

So Francois of Keras fame posted this really nice example

being this is really pretty, except why are there all these

And luckily, there's a Julia macro that will automatically

And you can benefit from really fast preprocessing.

and I can trust Julia's just-in-time compiler

in Python that goes over 100 million elements.

If you're worried about leaving Python, don't be.

We have lots of good scientific computing languages

If you need to use Python, we have a very good Python

字幕リスト動画再生

TensorFlow.jl.TensorFlowの世界へのJuliaフロントエンド (TF Dev Summit '19) (TensorFlow.jl: A Julia Front End to the TensorFlow World (TF Dev Summit '19))

eliminate

multiple

realize

audience