 | |
| Original author(s) | François Chollet |
|---|---|
| Developer(s) | ONEIROS |
| Initial release | 27 March 2015 |
| Stable release | 3.6.0[1]
/ 3 October 2024 |
| Repository | |
| Written in | Python |
| Platform | Cross-platform |
| Type | Frontend for TensorFlow, JAX or PyTorch (and more) |
| License | Apache 2.0 |
| Website | keras |
Keras is an open-source library that provides a Python interface for artificial neural networks. Keras was first independent software, then integrated into the TensorFlow library, and later supporting more. "Keras 3 is a full rewrite of Keras [and can be used] as a low-level cross-framework language to develop custom components such as layers, models, or metrics that can be used in native workflows in JAX, TensorFlow, or PyTorch — with one codebase."[2] Keras 3 will be the default Keras version for TensorFlow 2.16 onwards, but Keras 2 can still be used.[3]
- ^ "Release 3.6.0". 3 October 2024. Retrieved 22 October 2024.
- ^ "Keras: Deep Learning for humans". keras.io. Retrieved 2024-04-30.
- ^ "What's new in TensorFlow 2.16". Retrieved 2024-04-30.