KerasHub
KerasHub is a Keras library providing reusable components, pretrained models, and utilities for machine-learning and generative-modeling tasks.
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
- BERTBERT (Bidirectional Encoder Representations from Transformers) is a pretrained Transformer encoder language model that produces contextual text representations using information from both directions.
- byte pair encodingByte-pair encoding is a subword tokenization method that builds a vocabulary by iteratively merging frequent adjacent symbols or tokens.
- convolutional neural networkA convolutional neural network is a neural-network architecture that processes structured inputs with convolutional operations, typically using learned local filters to capture patterns.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
Related concepts
- Gemmauses · Gemma is a family of open-weight generative artificial-intelligence models developed by Google, including language and multimodal variants.
- from_preset()uses · from_preset() is a constructor that loads a pretrained model and its associated configuration, weights, and tokenizer assets from a named preset.
- SentencePieceuses · SentencePiece is a language-independent software library for learning and applying subword tokenization directly to raw text without whitespace-based pretokenization.
- pretrained modelproduces · A pretrained model is a machine-learning model whose parameters were learned through prior training before it is used for inference or adapted to a later task.
- causal language modelhas part · A causal language model predicts each token from preceding tokens only, without access to future tokens, enabling autoregressive sequence generation.
- preprocessinguses · Preprocessing is the preparation or transformation of data or other inputs into a form suitable for subsequent processing, analysis, or execution.
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.

