Keras

Spec sheet

Purpose

Keras is a Python deep learning API designed to make model development concise, readable, and easier to debug.Read 30 Sep 2026 · keras.io

Product

Keras is a Python deep learning API focused on readable, maintainable code and fast model iteration.Read 30 Sep 2026 · keras.io

Intended users

Keras describes its audience as machine learning engineers and presents guides and examples for model development across common ML use cases.Read 30 Sep 2026 · keras.io

Support

The Keras site directs users to its Google Group for questions and development discussion, and GitHub issues for bug reports and feature requests.Read 30 Sep 2026 · keras.io

Founded

2015Read 28 Sep 2026 · keras.io

Backends

Keras 3 runs on JAX, TensorFlow, and PyTorch, and offers an OpenVINO backend for inference.Read 30 Sep 2026 · keras.io

Community support

Keras provides a Google Group, community meetings, Discord, and a Google AI Forum for discussion and updates.Read 30 Sep 2026 · keras.io

Compatibility limit

The Keras distribution API supports model parallelism through JAX; TensorFlow and PyTorch support is described as coming soon on the Keras 3 launch page.Read 30 Sep 2026 · keras.io

Contributions

The Keras site invites code, ideas, and feedback and links to its roadmap, contribution guide, and GitHub repository.Read 30 Sep 2026 · keras.io

Data inputs

Keras 3 training, evaluation, and prediction routines support tf.data.Dataset, PyTorch DataLoader, NumPy arrays, and Pandas dataframes.Read 30 Sep 2026 · keras.io

Data integrations

Keras models can use NumPy arrays, Pandas dataframes, TensorFlow tf.data datasets, PyTorch DataLoaders, and Keras PyDataset objects.Read 30 Sep 2026 · keras.io

Distribution

The distribution API supports data and model parallelism and is currently implemented for the JAX backend.Read 30 Sep 2026 · keras.io

Examples

The getting-started page offers over 150 example notebooks covering computer vision, natural language processing, and generative AI.Read 30 Sep 2026 · keras.io

Frameworks

Keras 3 runs on JAX, TensorFlow, or PyTorch, and supports OpenVINO for inference only.Read 30 Sep 2026 · keras.io

Hyperparameter tuning

KerasTuner includes Bayesian Optimization, Hyperband, and Random Search algorithms and can be extended with new search algorithms.Read 30 Sep 2026 · keras.io

Installation

Keras installs from PyPI with pip install --upgrade keras; using Keras 3 also requires installing a backend framework.Read 30 Sep 2026 · keras.io

Model building

Developers can build models with the Sequential API, the Functional API, or model subclassing.Read 30 Sep 2026 · keras.io

Model interoperability

Keras 3 models can be used as PyTorch modules, exported as TensorFlow SavedModels, or instantiated as stateless JAX functions.Read 30 Sep 2026 · keras.io

Model portability

Keras 3 models can be used as PyTorch modules, exported as TensorFlow SavedModels, or instantiated as stateless JAX functions.Read 30 Sep 2026 · keras.io

Pretrained models

KerasHub provides implementations of popular model architectures and pretrained checkpoints from Kaggle Models for training and inference.Read 30 Sep 2026 · keras.io

Requirement

Keras 3 requires a separately installed backend framework, and the backend must be configured before importing Keras.Read 30 Sep 2026 · keras.io

Security and compliance

The Keras pages reviewed do not state security certifications or compliance claims.Read 30 Sep 2026 · keras.io

Training

Keras provides built-in fit, evaluate, and predict workflows for training, evaluation, and inference.Read 30 Sep 2026 · keras.io

Where Specifiction places it

• Deep Learning Software#19 of 357.5