Name: TF 2.x on Kaggle (TF Dev Summit '20) (TF 2.x on Kaggle (TF Dev Summit '20))
Uploaded: 2021-01-14T09:59:15.000Z
Duration: 5 min 33 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：

I'm speaking today about using TensorFlow 2.0 on Kaggle.

This is based on work led by Phil Culliton.

to participate in machine learning competitions,

practice data science, build portfolios, and share

My job at Kaggle is to run machine learning competitions.

Right now, we have 17 running, including deep fake detection

in videos, image classification, an abstraction and reasoning

"The Measure Of Intelligence," it's really amazing.

Basically, if you're interested in data or machine learning,

we'll likely have a competition that'll excite you.

TensorFlow is really heavily used in our competitions.

It's actually currently being used in all 17 of them.

But in the past few months, we've run two

and a new competition for image classification

We have tens of thousands of people using TensorFlow 2.1

Three of the top solutions for the question and answering

competition actually used TensorFlow and TPUs.

If you'd like to check out TensorFlow 2.1,

especially with a GPU or TPU, Kaggle makes it super easy.

that we've eliminated a lot of the obstacles

to making TensorFlow 2.1 build your models fast

No provisioning the right kind of VM, no setup--

data sets that are ready to go and a weekly amount

of TPU and GPU time allotted to users for no cost.

that'll build a model on Kaggle for a competition

to classify flowers on CPU, GPU, and TPU with no changes.

Import TensorFlow in the Kaggle data sets library.

The rest of the code here does a little bit of magic.

is attached to your VM and automatically parallelizes

whether you're using a V3 TPU or a simple CPU VM.

The rest of the code is entirely accelerator-agnostic.

So normally, outside of Kaggle and Collab,

you need to provision this TPU for usage.

Just select the TPU in the dropdown, and go!

Now we'll load up our competition data set.

It's provided in a sharded TF record format for fast loading.

We set some parameters for our training and validation sets,

shuffling our training set, batching them

for optimal performance, setting our training set to repeat,

And in the end, we have nice out of memory data

sets ready to run in our accelerator of choice.

Here, we load up a VGG-16 for some transfer learning,

compile our model, and start training and validating.

We're using a standard distribution strategy

that was made possible by that previous code

that automated the strategy based on the accelerator used.

That's basically saying, hey, whichever type

Now, our model will be built and trained on the accelerator.

Making some flower predictions is really easy after this.

We load up our test set, run model.predict,

and write our predictions out in a format that Kaggle can read.

with some of the fun flowers that our model made predictions

If you're interested in seeing TensorFlow 2.1 at work

字幕リスト動画再生

TF 2.x on Kaggle (TF Dev Summit '20) (TF 2.x on Kaggle (TF Dev Summit '20))

eliminate

strategy

basically

integrate