Name: TensorFlow Hub: Making model discovery easy (TF Dev Summit '20)
Uploaded: 2020-03-25T08:13:34.000Z
Duration: 9 min 3 s
Description: Thousands of YouTube videos with English-Chinese subtitles! Now you can learn to understand native speakers, expand your vocabulary, and improve your pronunciation...

And I'm a product manager in the TensorFlow team.

I'm going to talk to you about TensorFlow Hub.

of my colleague Gus and our Europe-based TF Hub team.

So when you want to apply ML to solve a problem,

are published in research papers or in blog posts.

So let's say you read about one of these,

And you might find the model code repository somewhere.

Sometimes the pretrained model is right there.

Sometimes it is stored on some other storage.

Sometimes you may need to download and run a script

So as you do this, you have many questions.

This is where TensorFlow Hub comes in to help you.

So TFHub.dev is the place for all your TensorFlow model needs

to easily find the latest ready-to-use models

with documentation, code snippets, and much, much more.

So TensorFlow Hub's rich repository of models

covers a wide range of machine learning tasks for all

we have models for image classification, object

detection, image augmentation, and also image generation,

such as for slide style transfers and more.

For text, we have state-of-the-art models like

and many more embeddings that can support

a wide range of natural language understanding tasks,

such as question and answering, text classification,

which can help with video action recognition,

such as gestures, and also video generation.

And now we have recently added audio models

reusable for composing new models for transfer learning

be put into your TensorFlow 2 code for retraining

Now, this works whether you are using the high level DF.keras

This can also be used in your training pipelines

Recently, we have added support for models

that are ready to deploy on all platforms

prepared for a wide range of environments, which run

For example, you can use TensorFlow GS models

In TensorFlow Hub, you can also discover ready-to-use models

These devices combine TensorFlow Lite models

which helps companies create models that perform really

You can learn more about this platform at Coral.ai.

available with documentation, code snippets.

And for some of them, there are also simple demos

These models can be easily found by searching or exploring

that links directly to the model page, which

lets you play with the models with code examples

And this is all hosted on Google's infrastructure.

So you can be getting started with nothing to install.

So now that we have seen what TensorFlow Hub is,

let's take a look at a couple of examples

and see how it can help you solve your problems.

So the first example I'll show you is about style transfer.

So here, let's take a look at how TensorFlow Hub can

do artistic style transfer that can work on arbitrary painting

So let's say you have an image of this yellow labrador shown

And you would like to imagine it in the style

Subtitles ListPlay Video

TensorFlow Hub: Making model discovery easy (TF Dev Summit '20)

arbitrary

track

version

imagine