Keras
Deep Learning for humans
Keras is a high-level deep learning API designed for readability, simplicity, and rapid iteration. It supports multiple backends including JAX, TensorFlow, and PyTorch, allowing models to run seamlessly across frameworks. Keras also provides KerasHub, a library of pretrained model architectures for tasks like computer vision, NLP, and generative AI.
Keras provides a clean, human-friendly Python API that abstracts over JAX, TensorFlow, and PyTorch backends, letting developers define, train, and deploy neural networks with minimal boilerplate.
ML developers and researchers
Background.
- Status
- launched
- Business model
- open-source
- Company
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.