https://github.com/ipc-lab/kaira

A PyTorch-based toolkit for simulating communication systems

https://github.com/ipc-lab/kaira

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (16.1%) to scientific vocabulary

Keywords

5g 6g academic communication communication-systems communications deep-learning error-correction-codes joint-source-channel-coding machine-learning neural-networks open-source python pytorch research signal-processing simulation-toolkit torch wireless-communication wireless-communications
Last synced: 5 months ago · JSON representation

Repository

A PyTorch-based toolkit for simulating communication systems

Basic Info
Statistics
  • Stars: 53
  • Watchers: 4
  • Forks: 1
  • Open Issues: 25
  • Releases: 4
Topics
5g 6g academic communication communication-systems communications deep-learning error-correction-codes joint-source-channel-coding machine-learning neural-networks open-source python pytorch research signal-processing simulation-toolkit torch wireless-communication wireless-communications
Created almost 3 years ago · Last pushed 7 months ago
Metadata Files
Readme Changelog Contributing License Code of conduct Codeowners Security Roadmap

README.md

Kaira Framework Logo

Kaira - A PyTorch-based toolkit for simulating communication systems

Python CI Tests pre-commit Supported Platforms ReadTheDocs Status PyPI Version GitHub Release (Latest) PyPI - Python Version License Coverage Status Dependabot Updates

Build Better Communication Systems with Kaira. Kaira is an open-source toolkit for PyTorch designed to help you simulate and innovate in communication systems. Its name is inspired by Kayra (from Turkic mythology, meaning 'creator') and Kairos (a Greek concept for the 'opportune moment'). This reflects Kaira's core purpose: to empower engineers and researchers to architect (Kayra) advanced communication models and to ensure messages are transmitted effectively and at the right moment (Kairos). Kaira provides the tools to design, analyze, and optimize complex communication scenarios, making it an essential asset for research and development.

Kaira is built to accelerate your research. Its user-friendly, modular design allows for easy integration with existing PyTorch projects, facilitating rapid prototyping of new communication strategies. This is particularly beneficial for developing and testing advanced techniques, such as deep joint source-channel coding (DeepJSCC) and other deep learning-based approaches, as well as classical forward error correction with industry-standard LDPC, Polar, and algebraic codes. Kaira helps you bring your innovative communication concepts to life.

Note: Kaira is currently in beta. The API is subject to change as we refine the library based on user feedback and evolving research needs.

Documentation

Features

  1. Research-Oriented: Designed to accelerate communications research.
  2. Versatility: Compatible with various data types and neural network architectures.
  3. Ease of Use: User-friendly and easy to integrate with existing PyTorch projects.
  4. Open Source: Allows for community contributions and improvements.
  5. Well Documented: Comes with comprehensive documentation for easy understanding.

Example Code

Here's a simple example showing how to use Kaira's Bourtsoulatze2019 DeepJSCC model:

Kaira Example Code

Installation

The fastest way to install Kaira is directly from PyPI:

bash pip install pykaira

Quick Links

Support

Get help and connect with the Kaira community through these channels:

Contributors

Contributors

We thank all our contributors for their valuable input and efforts to make Kaira better!

How to Contribute

Contributions are welcome! Please see our Contributing Guide for more details on how to get started.

License

Kaira is distributed under the terms of the MIT License.

Citing Kaira

If you use Kaira in your research, please cite it using the following format:

bibtex @software{kaira2025, title = {Kaira: A {PyTorch}-based toolkit for simulating communication systems}, author = {{Kaira Contributors}}, year = {2025}, url = {https://github.com/ipc-lab/kaira}, version = {0.1.0} }

Owner

  • Name: ipc-lab
  • Login: ipc-lab
  • Kind: organization

GitHub Events

Total
  • Create event: 9
  • Issues event: 24
  • Release event: 4
  • Watch event: 42
  • Delete event: 5
  • Issue comment event: 19
  • Public event: 1
  • Push event: 105
  • Pull request review event: 13
  • Pull request review comment event: 13
  • Pull request event: 7
  • Fork event: 1
Last Year
  • Create event: 9
  • Issues event: 24
  • Release event: 4
  • Watch event: 42
  • Delete event: 5
  • Issue comment event: 19
  • Public event: 1
  • Push event: 105
  • Pull request review event: 13
  • Pull request review comment event: 13
  • Pull request event: 7
  • Fork event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 21
  • Total pull requests: 6
  • Average time to close issues: 13 days
  • Average time to close pull requests: about 2 months
  • Total issue authors: 3
  • Total pull request authors: 3
  • Average comments per issue: 0.38
  • Average comments per pull request: 0.5
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 1
Past Year
  • Issues: 21
  • Pull requests: 6
  • Average time to close issues: 13 days
  • Average time to close pull requests: about 2 months
  • Issue authors: 3
  • Pull request authors: 3
  • Average comments per issue: 0.38
  • Average comments per pull request: 0.5
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 1
Top Authors
Issue Authors
  • selimfirat (12)
  • dalonsoa (7)
  • tsmbland (2)
Pull Request Authors
  • selimfirat (3)
  • smeshk (1)
  • dependabot[bot] (1)
Top Labels
Issue Labels
enhancement (11) documentation (3) refactoring (2) help wanted (1)
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 32 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 4
  • Total maintainers: 1
pypi.org: pykaira

A PyTorch-based toolkit for simulating communication systems.

  • Versions: 4
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 32 Last month
Rankings
Dependent packages count: 9.2%
Average: 30.4%
Dependent repos count: 51.7%
Maintainers (1)
Last synced: 6 months ago

Dependencies

.github/workflows/ci.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • actions/upload-artifact v4 composite
  • codecov/codecov-action v5 composite
.github/workflows/pre-commit.yml actions
  • actions/cache v4 composite
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
.github/workflows/stale.yml actions
  • actions/stale v9 composite
.github/workflows/tests.yml actions
  • actions/cache v4 composite
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • codecov/codecov-action v5 composite
pyproject.toml pypi
requirements-dev.txt pypi
  • black >=23.0.0 development
  • coverage >=7.0.0 development
  • flake8 >=6.0.0 development
  • graphviz >=0.20.1 development
  • isort >=5.12.0 development
  • matplotlib >=3.3.0 development
  • mypy >=1.0.0 development
  • myst-parser * development
  • pillow >=8.0.0 development
  • pre-commit * development
  • pydata-sphinx-theme * development
  • pytest >=7.0.0 development
  • pytest-cov >=4.0.0 development
  • sphinx * development
  • sphinx-design >=0.3.0 development
  • sphinx-gallery >=0.11.1 development
  • sphinx-hoverxref * development
  • sphinx-rtd-theme >=1.0.0 development
  • sphinxcontrib-bibtex * development
requirements.txt pypi
  • compressai *
  • joblib *
  • torch >=1.8.0
  • torchaudio *
  • torchmetrics *
  • torchvision *
setup.py pypi