# flower
**Repository Path**: frontxiang/flower
## Basic Information
- **Project Name**: flower
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-10-04
- **Last Updated**: 2022-04-03
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# Flower - A Friendly Federated Learning Framework
Website |
Blog |
Docs |
Conference |
Slack
[](https://github.com/adap/flower/blob/main/LICENSE)
[](https://github.com/adap/flower/blob/main/CONTRIBUTING.md)
[](https://flower.dev/join-slack)
Flower (`flwr`) is a framework for building federated learning systems. The
design of Flower is based on a few guiding principles:
* **Customizable**: Federated learning systems vary wildly from one use case to
another. Flower allows for a wide range of different configurations depending
on the needs of each individual use case.
* **Extendable**: Flower originated from a research project at the Univerity of
Oxford, so it was build with AI research in mind. Many components can be
extended and overridden to build new state-of-the-art systems.
* **Framework-agnostic**: Different machine learning frameworks have different
strengths. Flower can be used with any machine learning framework, for
example, [PyTorch](https://pytorch.org),
[TensorFlow](https://tensorflow.org), [Hugging Face Transformers](https://huggingface.co/), [PyTorch Lightning](https://pytorchlightning.ai/), [MXNet](https://mxnet.apache.org/), [scikit-learn](https://scikit-learn.org/), [JAX](https://jax.readthedocs.io/), [TFLite](https://tensorflow.org/lite/), or even raw [NumPy](https://numpy.org/)
for users who enjoy computing gradients by hand.
* **Understandable**: Flower is written with maintainability in mind. The
community is encouraged to both read and contribute to the codebase.
Meet the Flower community on [flower.dev](https://flower.dev)!
## Documentation
[Flower Docs](https://flower.dev/docs):
* [Installation](https://flower.dev/docs/installation.html)
* [Quickstart (TensorFlow)](https://flower.dev/docs/quickstart_tensorflow.html)
* [Quickstart (PyTorch)](https://flower.dev/docs/quickstart_pytorch.html)
* [Quickstart (Hugging Face [code example])](https://flower.dev/docs/quickstart_huggingface.html)
* [Quickstart (PyTorch Lightning [code example])](https://flower.dev/docs/quickstart_pytorch_lightning.html)
* [Quickstart (MXNet)](https://flower.dev/docs/example-mxnet-walk-through.html)
* [Quickstart (JAX [code example])](https://github.com/adap/flower/tree/main/examples/jax_from_centralized_to_federated)
* [Quickstart (scikit-learn)](https://github.com/adap/flower/tree/main/examples/sklearn-logreg-mnist)
* [Quickstart (TFLite on Android [code example])](https://github.com/adap/flower/tree/main/examples/android)
## Flower Baselines
Flower Baselines is a collection of community-contributed experiments that reproduce the experiments performed in popular federated learning publications. Researchers can build on Flower Baselines to quickly evaluate new ideas:
* [FedBN: Federated Learning on non-IID Features via Local Batch Normalization](https://arxiv.org/pdf/2102.07623.pdf):
* [Convergence Rate](https://github.com/adap/flower/tree/main/baselines/flwr_baselines/publications/fedbn/convergence_rate)
* [Adaptive Federated Optimization](https://arxiv.org/pdf/2003.00295.pdf)
* [CIFAR-10/100](https://github.com/adap/flower/tree/main/baselines/flwr_baselines/publications/adaptive_federated_optimization)
Check the Flower documentation to learn more: [Using Baselines](https://flower.dev/docs/using-baselines.html)
The Flower community loves contributions! Make your work more visible and enable others to build on it by contributing it as a baseline: [Contributing Baselines](https://flower.dev/docs/contributing-baselines.html)
## Flower Usage Examples
A number of examples show different usage scenarios of Flower (in combination
with popular machine learning frameworks such as PyTorch or TensorFlow). To run
an example, first install the necessary extras:
[Usage Examples Documentation](https://flower.dev/docs/examples.html)
Quickstart examples:
* [Quickstart (TensorFlow)](https://github.com/adap/flower/tree/main/examples/quickstart_tensorflow)
* [Quickstart (PyTorch)](https://github.com/adap/flower/tree/main/examples/quickstart_pytorch)
* [Quickstart (Hugging Face)](https://github.com/adap/flower/tree/main/examples/quickstart_huggingface)
* [Quickstart (PyTorch Lightning)](https://github.com/adap/flower/tree/main/examples/quickstart_pytorch_lightning)
* [Quickstart (MXNet)](https://github.com/adap/flower/tree/main/examples/quickstart_mxnet)
* [Quickstart (scikit-learn)](https://github.com/adap/flower/tree/main/examples/sklearn-logreg-mnist)
* [Quickstart (TFLite on Android)](https://github.com/adap/flower/tree/main/examples/android)
Other [examples](https://github.com/adap/flower/tree/main/examples):
* [Raspberry Pi & Nvidia Jetson Tutorial](https://github.com/adap/flower/tree/main/examples/embedded_devices)
* [Android & TFLite](https://github.com/adap/flower/tree/main/examples/android)
* [PyTorch: From Centralized to Federated](https://github.com/adap/flower/tree/main/examples/pytorch_from_centralized_to_federated)
* [MXNet: From Centralized to Federated](https://github.com/adap/flower/tree/main/examples/mxnet_from_centralized_to_federated)
* [JAX: From Centralized to Federated](https://github.com/adap/flower/tree/main/examples/jax_from_centralized_to_federated)
* [Advanced Flower with TensorFlow/Keras](https://github.com/adap/flower/tree/main/examples/advanced_tensorflow)
* [Single-Machine Simulation of Federated Learning Systems](https://github.com/adap/flower/tree/main/examples/simulation)
## Community
Flower is built by a wonderful community of researchers and engineers. [Join Slack](https://flower.dev/join-slack) to meet them, [contributions](#contributing-to-flower) are welcome.
## Citation
If you publish work that uses Flower, please cite Flower as follows:
```bibtex
@article{beutel2020flower,
title={Flower: A Friendly Federated Learning Research Framework},
author={Beutel, Daniel J and Topal, Taner and Mathur, Akhil and Qiu, Xinchi and Parcollet, Titouan and Lane, Nicholas D},
journal={arXiv preprint arXiv:2007.14390},
year={2020}
}
```
Please also consider adding your publication to the list of Flower-based publications in the docs, just open a Pull Request.
## Contributing to Flower
We welcome contributions. Please see [CONTRIBUTING.md](CONTRIBUTING.md) to get
started!