Name: 在訓練中使用回調，在TF 2.0中入門，以及更多！(#AskTensorFlow)(#AskTensorFlow) (Using callbacks in training, getting started in TF 2.0, & more! (#AskTensorFlow))
Uploaded: 2021-01-14T10:34:47.000Z
Duration: 13 min 43 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。

to 不定詞

Exciting event so far, and it's great to see all the questions

Please keep asking them and putting #TensorFlow.

We're here today to answer them live on the live stream.

- I'm Laurence Moroney. - And I'm Paige Bailey,

Because we're the TensorFlow that you shall be asking.

Exactly, so we're here to try and answer as many questions as we can.

Sorry if we don't get to them all but we'll do our best.

So, one of the first questions that we're going to cover,

and it's one question I bet you've had it today,

I get it almost every time I meet a TensorFlower,

and like you'll usually do my training for a fixed number of epochs,

but what happens when I reach my desired accuracy metric,

Right, like it doesn't make any sense to keep using Compute

if you've already gotten to a point where your boss would say,

"Okay, cool, 99% accuracy-- that's fine for us today."

(Laurence) So shall we take a look at how we'd actually do that?

So, I've opened up a colab here that you can see

and callbacks are the way that you would actually achieve this.

So at the top of my colab here, you can see I have class myCallback,

and on this one then, when an epoch ends in training,

and if the accuracy log, for example, in this case,

- 'cause I have a really nice boss, - (Paige laughs)

(Laurence) he's really happy when my training's 60% accurate--

then I would actually cancel the training.

I'll just say I'm going to create an object called callbacks,

which is an instance of my callback class,

and I love the way in Colab when I Double Click,

it actually highlights, it's just a little thing that I like.

I'll just say callbacks equals callbacks.

And then when I actually do the training,

and you know what, I'm going to really show off

and I'm going to make my runtime type to be GPU so it goes nice and fast.

Let's do a little bit of training on Fashion-MNIST with this one.

And we're doing this live so I'm connecting up to the VM.

And here we go, now it's actually training.

- It's on the first epoch. - (Paige) It's showing you your RAM

(Laurence) We're on the first epoch. The first epoch is progressing away,

- (Paige) That's pretty good. - In just one epoch, right?

But we can see now that it actually reached 60% accuracy

So callbacks are your friends if you're doing this.

Certainly when you're learning, when you're experimenting,

I used to, before I learned about callbacks--

I would set something up to train for a hundred epochs

and then go and go to sleep, and then wake up the next morning

and find like after three epochs, it had done its job,

So, use callbacks, I think, would be the answer to that.

Absolutely, keras callbacks are incredibly valuable.

It doesn't just apply to accuracy either.

that could be useful for your particular workflow.

And this code also would work in TensorFlow 2.0.

- So it's keras-- - (Laurence) Absolutely.

- (Paige) Gosh I love keras-- - (Laurence) Keras, yes.

And actually one of the really neat things about keras that you may not realize,

and we've been talking about TensorFlow 2.0,

is that the same code that you write for TensorFlow 1.x

but what's going on behind the scenes is that it's executing equally in 2.0,

So even though this colab I think I'm running at 1.13,

this code will actually still run in 2.0, without you modifying the code.

Alright, so shall we take the next question?

So, our next question is from Twitter it looks like,

does the version 2.0 help them get started?"

So I just got finished talking to two of the folks

on the TensorFlow.js-- and you just pulled it up--

that they've seen arise from the community.

字幕列表影片播放

在訓練中使用回調，在TF 2.0中入門，以及更多！(#AskTensorFlow)(#AskTensorFlow) (Using callbacks in training, getting started in TF 2.0, & more! (#AskTensorFlow))

stuff

absolutely

incredibly

bunch