liveBook · Manning

KerasHub

KerasHub is a Keras library providing reusable components, pretrained models, and utilities for machine-learning and generative-modeling tasks.

How 2 Manning books explain it

Deep Learning with R, Third Edition

KerasHub is a library that provides reusable components and utilities for working with pretrained and generative machine-learning models in Keras.

How it is used
Uses pretrained models and tokenization utilities for image classification and language-model workflows.
How deep it goes
Demonstrates installation, preset loading, preprocessing, freezing, tokenization, and generation rather than implementing pretrained architectures from scratch.
Examples
Uses Xception for dogs-versus-cats features, RoBERTa for text processing, SentencePiece for mini-GPT, and Gemma for generation.
What you can do after
Applies pretrained models via KerasHub presets and task APIs for feature extraction and text generation.

Read how Deep Learning with R, Third Edition explains KerasHub →

Deep Learning with Python, Third Edition

A Keras-hosted library providing pretrained models and high-level tasks such as Stable Diffusion and TextToImage.

How it is used
Provides pretrained Keras models and task interfaces for segmentation, language modeling, and image generation.
How deep it goes
Demonstrates preset loading and task generation while avoiding model reimplementation and text-to-image training from scratch.
Examples
Uses RoBERTa tokenizer and backbone presets and a Stable Diffusion prompt with a negative prompt.
What you can do after
Apply it via KerasHub to load pretrained models and generate text or images with high-level tasks.

Read how Deep Learning with Python, Third Edition explains KerasHub →

What to know first

Related concepts

Questions about KerasHub

What is KerasHub?

KerasHub is a Keras library providing reusable components, pretrained models, and utilities for machine-learning and generative-modeling tasks.

Which Manning books explain KerasHub?

Deep Learning with R, Third Edition and Deep Learning with Python, Third Edition.

What should I know before learning KerasHub?

Manning books that teach KerasHub usually introduce BERT, byte pair encoding, convolutional neural network and language model first.

What are the parts of KerasHub?

KerasHub includes causal language model.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.