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
- Supplies pretrained Keras models and tokenization tools for image classification, language-model loading, pretraining pipelines, and text generation.
- How deep it goes
- Shows installation, preset loading, preprocessing, feature extraction, tokenization, and generation through working code rather than KerasHub implementation internals.
- Examples
- Uses Xception for dogs-versus-cats classification, RoBERTa tokenization, SentencePiece for mini-GPT, and Gemma prompt continuation.
- What you can do after
- Apply it via KerasHub presets to load matching pretrained components, extract image features, or generate text.
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 APIs for segmentation, language modeling, and text-to-image generation.
- How deep it goes
- Demonstrates preset loading, matching tokenizers, task-level generation, and backbone reuse; defers training effective text-to-image diffusion models from scratch.
- Examples
- Loads RoBERTa’s tokenizer and backbone and generates images with a Stable Diffusion 3 preset.
- What you can do after
- Apply it via KerasHub to load pretrained task models or backbones and generate text or images.
Read how Deep Learning with Python, Third Edition explains KerasHub →
Related concepts
- Gemmauses · Gemma is a family of open-weight generative AI models developed by Google.
- 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 that learns and applies subword tokenization directly to raw text without requiring whitespace-based pretokenization.
- pretrained modelproduces · A pretrained model is a machine-learning model whose parameters were learned through prior training before it is used or adapted for a subsequent task.
- causal language modelhas part · A causal language model predicts each token from preceding tokens and generates sequences autoregressively.
- preprocessinguses · Preprocessing is the preparation or transformation of data, content, or other inputs into a form suitable for a subsequent computational operation.
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.