# Machine Learning and Optimization for Communications (MOKka)
(german: **M**aschinelles Lernen und **O**ptimierung für **K**ommuni**ka**tionssysteme)
This Python package is intended to provide signal and information processing blocks in popular machine learning frameworks.
Most of the functionality currently is provided for the PyTorch machine learning framework. Some parts are already implemented to interface with the Sionna Python package.
## Prerequisites
This package works best if it is installed in a Python virtualenvironment, either provided by `python -m venv` or `conda`.
To leverage GPU for training with PyTorch and/or latest features of the PyTorch nightly version follow https://pytorch.org/get-started/locally/ to
install PyTorch from the PyTorch repositories and avoid installing the PyPI provided general-purpose version of PyTorch.
## Installation
To install `mokka` with functionality to work with PyTorch clone this repository and install (in a virtual environment):
```
pip install '.[torch]'
```
Several more optional dependencies are provided to support Sionna (and tensorflow) `[tf]` or for formatting and more development tools `[dev]`.
The popular machine learning reporting and experiment tracking tool weights & biases can be installed with `[remotelog]`.
For all possible optional dependencies enabled e.g.:
```
pip install '.[torch,tf,dev,remotelog]'
```
## Usage
This package provides a range of modules, covering a range of functions within a communication system.
To access functionality within a specific module first `import mokka` and then access of modules is possible, e.g. `mokka.mapping.torch` provides
constellation mappers and demappers implemented with and compatible to the PyTorch framework.
Raw data
{
"_id": null,
"home_page": null,
"name": "mokka",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": "Andrej Rode <rode@kit.edu>, Shrinivas Chimmalgi <shrinivas.chimmalgi@kit.edu>, Benedikt Geiger <benedikt.geiger@kit.edu>",
"keywords": "communications engineering,machine learning",
"author": null,
"author_email": "Andrej Rode <rode@kit.edu>, Shrinivas Chimmalgi <shrinivas.chimmalgi@kit.edu>, Benedikt Geiger <benedikt.geiger@kit.edu>, Laurent Schmalen <laurent.schmalen@kit.edu>",
"download_url": "https://files.pythonhosted.org/packages/7c/da/9fc9845dce3438ef19c18a50f4f390ea60df0585a679c20151fbf9e38695/mokka-1.0.1.tar.gz",
"platform": null,
"description": "# Machine Learning and Optimization for Communications (MOKka) \n(german: **M**aschinelles Lernen und **O**ptimierung f\u00fcr **K**ommuni**ka**tionssysteme)\n\nThis Python package is intended to provide signal and information processing blocks in popular machine learning frameworks.\nMost of the functionality currently is provided for the PyTorch machine learning framework. Some parts are already implemented to interface with the Sionna Python package.\n\n## Prerequisites\n\nThis package works best if it is installed in a Python virtualenvironment, either provided by `python -m venv` or `conda`.\nTo leverage GPU for training with PyTorch and/or latest features of the PyTorch nightly version follow https://pytorch.org/get-started/locally/ to\ninstall PyTorch from the PyTorch repositories and avoid installing the PyPI provided general-purpose version of PyTorch.\n\n## Installation\n\nTo install `mokka` with functionality to work with PyTorch clone this repository and install (in a virtual environment):\n```\npip install '.[torch]'\n```\n\nSeveral more optional dependencies are provided to support Sionna (and tensorflow) `[tf]` or for formatting and more development tools `[dev]`.\nThe popular machine learning reporting and experiment tracking tool weights & biases can be installed with `[remotelog]`.\nFor all possible optional dependencies enabled e.g.:\n```\npip install '.[torch,tf,dev,remotelog]'\n```\n\n## Usage\n\nThis package provides a range of modules, covering a range of functions within a communication system.\nTo access functionality within a specific module first `import mokka` and then access of modules is possible, e.g. `mokka.mapping.torch` provides\nconstellation mappers and demappers implemented with and compatible to the PyTorch framework.\n",
"bugtrack_url": null,
"license": null,
"summary": "A machine learning toolbox for communications engineering",
"version": "1.0.1",
"project_urls": null,
"split_keywords": [
"communications engineering",
"machine learning"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "30f9aa221f55cda5d1a509595bc0f2835ea01d04684ccb0a9530515bd0905b37",
"md5": "47baa38fff00357250aa8da1b3c906a8",
"sha256": "843de1e246f8ca0d1be6ef4515423a85cb5d0189855c45b49ca0896230c56699"
},
"downloads": -1,
"filename": "mokka-1.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "47baa38fff00357250aa8da1b3c906a8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 41841,
"upload_time": "2023-05-31T13:49:12",
"upload_time_iso_8601": "2023-05-31T13:49:12.357371Z",
"url": "https://files.pythonhosted.org/packages/30/f9/aa221f55cda5d1a509595bc0f2835ea01d04684ccb0a9530515bd0905b37/mokka-1.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7cda9fc9845dce3438ef19c18a50f4f390ea60df0585a679c20151fbf9e38695",
"md5": "e9eb19be19c6dcfa75ca7fd2b76239be",
"sha256": "0657d76b6f921dae61dd2b0537cbb8539a3b1d4154d82168e9d17c7b06af5546"
},
"downloads": -1,
"filename": "mokka-1.0.1.tar.gz",
"has_sig": false,
"md5_digest": "e9eb19be19c6dcfa75ca7fd2b76239be",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 41286,
"upload_time": "2023-05-31T13:49:16",
"upload_time_iso_8601": "2023-05-31T13:49:16.704265Z",
"url": "https://files.pythonhosted.org/packages/7c/da/9fc9845dce3438ef19c18a50f4f390ea60df0585a679c20151fbf9e38695/mokka-1.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-05-31 13:49:16",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "mokka"
}
JSON