Name: TensorFlowの内部: tf.Keras (その1) (Inside TensorFlow: tf.Keras (part 1))
Uploaded: 2021-01-14T10:04:33.000Z
Duration: 53 min 37 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 going to be talking about TensorFlow Keras.

about how to use the Keras API in TensorFlow

and how the Keras API is implemented under the hood.

So we'll cover another view of the Keras architecture.

We'll do a deep dive into the layer class and the model

We'll have an overview of the functional API

We'll look at how training and inference work.

And finally, we'll look at custom losses and metrics.

So this is the overview of the Keras architecture and all

the different submodules and the different classes

The core of the Keras implementation is the engine

the base layer class from which all layers inherit,

it's basically kind of modeled its directed acyclic graph

as well as the model class which basically takes the network

class but adds training and evaluation and sitting on top

of it, and also the sequential class, which is, again,

another type of model which just wraps a list of layers.

Then we have the layers module, where all the action

instances-- usable instances of layers go.

We have losses and metrics with a base class for each,

We have callbacks, optimizers, regularizers,

and constraints, which are much like the modules.

over what's going on in the Engine module, and also losses

and metrics, not so much callbacks, optimizers,

So I'm just going to focus on the most important information.

So the layer is the core abstraction in the Keras API.

I think if you want to have a simple API,

Everything in Keras pretty much is a layer or something

So a layer has a lot of responsibilities,

At its core, a layer is a container for some computation.

So it's in charge of transforming a batch of inputs

Very importantly, this is batchwise computation,

meaning that you expect N samples as inputs,

and you're going to be returning N output samples.

And so it's meant to work with eager execution, also

All the built-in layers in Keras support both.

But user-written layers could be only eager, potentially.

We support having layers that have two different modules--

AUDIENCE: So this would mean that using different layers

And typically, most layers are going to be supporting both.

So, yeah, so layers also support two modes-- so a training mode,

like dropout layer or the batch normalization layer.

There's a support for built-in masking, which

is about specifying certain features of timestamps

if you're doing sequence processing with sequences where

A layer is also container for state, meaning variable.

which is what parametrizes the computation of the layer

and that you update during back propagation;

could be anything else that is manually managed by the layer

that you can use to track losses and metrics that you define

字幕リスト動画再生

TensorFlowの内部: tf.Keras (その1) (Inside TensorFlow: tf.Keras (part 1))

specific

essentially

multiple

basically