keras-team/keras
Deep Learning for humans
Keras 3 helps machine learning practitioners quickly build and train deep learning models for tasks like computer vision, natural language processing, and time-series forecasting. You input your data and model architecture, and it outputs a trained model ready for predictions. This tool is for data scientists, ML engineers, and researchers who need to efficiently develop robust deep learning solutions.
63,968 stars. Used by 81 other packages. Actively maintained with 146 commits in the last 30 days. Available on PyPI.
Use this if you need to rapidly develop and deploy deep learning models while having the flexibility to choose the best backend (like JAX for speed or TensorFlow for a mature ecosystem) for your specific needs.
Not ideal if you prefer to work exclusively with low-level API calls for maximum granular control within a single deep learning framework.
Stars
63,968
Forks
19,732
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
146
Dependencies
8
Reverse dependents
81
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/keras-team/keras"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related frameworks
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
rwth-i6/returnn
The RWTH extensible training framework for universal recurrent neural networks