Name: 最先端のTensorFlow：新技術（Google I/O'19 (Cutting Edge TensorFlow: New Techniques (Google I/O'19))
Uploaded: 2021-01-14T10:01:42.000Z
Duration: 37 min 32 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：

ELIE BURZSTEIN: If you are new to our session

on cutting edge TensorFlow, my name is Elie.

Then, Josh will talk about probability programming.

And finally, Sofien will show you how to use TensorFlow.

Let me start by telling you about Keras Tuner, which

is a framework we initially developed internally

to bring new [INAUDIBLE] model to faster to production.

Before getting started, let me ask you a question.

How many of you have ever spent time optimizing your model

This is not surprising because getting the best model

is hard because there are many parameters such as the learning

rate, the batch size, and the number of layers

Moreover, those parameters are interdependent,

which make finding the optimal combinations by hand

This is why we rely hypertuning to automatically find

the optimal performances, this begs the question,

This is why today I am happy to introduce

to Keras Tuner which is a tuning framework made for humans.

designed to make the life of AI practitioner

It also helps hypertuner algorithm creators and model

designers by providing them with a clean and easy to use API.

For AI practitioner, which is most of us,

Keras Tuner makes moving from a base model

Let me show you how this is done by converting a basic MNIST

We will only have to change a few lines of code.

Here's our basic MNIST model that is a TensorFlow

This is something I'm sure all of you have seen already.

As you can set on the side, all parameter are fixed.

For example, our learning rate is set to 0.001.

So let's transition it to a hypertunable model

First, we wrap up our model in a function.

for the parameter that we would like to optimize.

Here for example, we're going to optimize the learning

rate which is one of the most important parameters

Finally as the last step, we replace our fixed parameters

Besides offering an intuitive API Keras Tuner,

we'll also provide you with state of the art hypertuning

are ready to go, and an automatic experimental

recording which make it easy for you to analyze, share,

Originally, I started developing Keras Tuner to quickly try it

including the one we developed to protect Gmail

Band detection is one of the core building

block we need to protect your inbox against phishing email

This is why today, our [INAUDIBLE] example

would be to show you how to build a simple and yet

accurate brand logo classifier as logo identification is

one of the critical components to detect brand spoofing email.

The first thing we need to do is to load our dataset.

In that example, we have about the 150 icons

from various brands, including the ones displayed on the side.

such as batch size and the number of icons

Next, our data set is very small so we'll

rely on data augmentation to create enough training data.

This slide shows you a few examples of the augmented icons

we're going to feed to the classifier as training

We are going to save the real icon as our validation dataset

to make sure that our classifier degenerates well.

train a ResNet101v2 which is one of the most common and well

our model did converge but the actuality on real icon

字幕リスト動画再生

最先端のTensorFlow：新技術（Google I/O'19 (Cutting Edge TensorFlow: New Techniques (Google I/O'19))

perspective

sort

material

develop