| Name | remin JSON |
| Version |
0.2.7
JSON |
| download |
| home_page | |
| Summary | PINN solver implemented in Pytorch |
| upload_time | 2023-09-01 14:50:30 |
| maintainer | |
| docs_url | None |
| author | |
| requires_python | >=3.7 |
| license | |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
setuptools
wheel
build
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# remin: Residual Minimizer - Physics Informed Neural Networks
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/release/python-360/)
[](https://pytorch.org/)
**remin** is a Python module that provides a framework for developing Physics Informed Neural Networks (PINNs) using PyTorch. This module integrates PyTorch for model creation and training, Latin-Hypercube sampling for geometry creation, and also includes a small, user-friendly module for creating geometries.
## Key Features
- Implementation of Physics Informed Neural Networks (PINNs) using PyTorch.
- Support for creating geometries using Latin-Hypercube sampling.
- Intuitive module for defining and creating complex geometries.
- Command-line interface (CLI) for simultaneous training of multiple models.
## Installation
### Prerequisites
Before using `remin`, you will need to install the following packages:
* PyTorch (version 2.0.0 or later)
* NumPy
* pyDOE (version 0.3.8 or later)
You can install all the requirements using pip, the Python package installer. To install PyTorch, run the following command or follow the instructions on their [website](https://pytorch.org/get-started/locally/) to install with GPU support:
```
pip install torch>=2.0.0
```
To install NumPy, run the following command:
```
pip install numpy
```
To install pyDOE, run the following command:
```
pip install pyDOE>=0.3.8
```
Alternatively, you can install these packages using conda or any other package manager of your choice.
Once you have installed these packages, `remin` can be installed using pip([PyPi](https://pypi.org/project/remin/)):
```
pip install remin
```
---
## Usage
To use **remin** in your Python project, import the necessary modules as follows:
```
import remin.geometry as rd
import remin.func as rf
import remin.solver.residual_loss as rl
from remin.solver import Solver, make_trainer
from remin.residual import Residual, make_loader
```
*Will be extended in future.*
---
## Contributing
If you want to contribute to **remin**, feel free to submit a pull request or open an issue on [GitHub](https://github.com/SalihTasdelen/remin).
## License
This project is licensed under the [MIT License](https://github.com/SalihTasdelen/remin/blob/main/LICENSE).
## Contact
For any questions, suggestions, or feedback, please feel free to contact the maintainer at [salih.tasdelen@metu.edu.tr].
Thank you for using **remin**!
Raw data
{
"_id": null,
"home_page": "",
"name": "remin",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "",
"author": "",
"author_email": "Salih Ta\u015fdelen <salih.tasdelen@hotmail.com>",
"download_url": "https://files.pythonhosted.org/packages/c8/8b/166fa0e35dc8411d2d01bf77f45d65a7412c30cff1c820e21bb738c625cf/remin-0.2.7.tar.gz",
"platform": null,
"description": "# remin: Residual Minimizer - Physics Informed Neural Networks\n\n[](https://opensource.org/licenses/MIT)\n[](https://www.python.org/downloads/release/python-360/)\n[](https://pytorch.org/)\n\n**remin** is a Python module that provides a framework for developing Physics Informed Neural Networks (PINNs) using PyTorch. This module integrates PyTorch for model creation and training, Latin-Hypercube sampling for geometry creation, and also includes a small, user-friendly module for creating geometries.\n\n## Key Features\n\n- Implementation of Physics Informed Neural Networks (PINNs) using PyTorch.\n- Support for creating geometries using Latin-Hypercube sampling.\n- Intuitive module for defining and creating complex geometries.\n- Command-line interface (CLI) for simultaneous training of multiple models.\n\n## Installation\n\n### Prerequisites\n\nBefore using `remin`, you will need to install the following packages:\n\n* PyTorch (version 2.0.0 or later)\n* NumPy\n* pyDOE (version 0.3.8 or later)\n\nYou can install all the requirements using pip, the Python package installer. To install PyTorch, run the following command or follow the instructions on their [website](https://pytorch.org/get-started/locally/) to install with GPU support:\n```\npip install torch>=2.0.0\n```\nTo install NumPy, run the following command:\n```\npip install numpy\n```\nTo install pyDOE, run the following command:\n```\npip install pyDOE>=0.3.8\n```\nAlternatively, you can install these packages using conda or any other package manager of your choice.\n\nOnce you have installed these packages, `remin` can be installed using pip([PyPi](https://pypi.org/project/remin/)):\n```\npip install remin\n```\n---\n## Usage\n\nTo use **remin** in your Python project, import the necessary modules as follows:\n```\nimport remin.geometry as rd\nimport remin.func as rf\nimport remin.solver.residual_loss as rl\nfrom remin.solver import Solver, make_trainer\nfrom remin.residual import Residual, make_loader\n```\n*Will be extended in future.*\n\n---\n## Contributing\n\nIf you want to contribute to **remin**, feel free to submit a pull request or open an issue on [GitHub](https://github.com/SalihTasdelen/remin).\n\n## License\n\nThis project is licensed under the [MIT License](https://github.com/SalihTasdelen/remin/blob/main/LICENSE).\n\n## Contact\n\nFor any questions, suggestions, or feedback, please feel free to contact the maintainer at [salih.tasdelen@metu.edu.tr].\n\nThank you for using **remin**!\n",
"bugtrack_url": null,
"license": "",
"summary": "PINN solver implemented in Pytorch",
"version": "0.2.7",
"project_urls": {
"Bug Tracker": "https://github.com/SalihTasdelen/remin/issues",
"Homepage": "https://github.com/SalihTasdelen/remin"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ac38981f3a3946d1a33c63d80afa6abb092c7fa93af09e4c4df17eb59c923225",
"md5": "c46816adc42deb96137db6cfdd30331c",
"sha256": "9ed0bb22f3c834eea46bb83831faf0e4d76cf7ec9b2ee8973a228b10152cefbf"
},
"downloads": -1,
"filename": "remin-0.2.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c46816adc42deb96137db6cfdd30331c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 17413,
"upload_time": "2023-09-01T14:50:24",
"upload_time_iso_8601": "2023-09-01T14:50:24.406433Z",
"url": "https://files.pythonhosted.org/packages/ac/38/981f3a3946d1a33c63d80afa6abb092c7fa93af09e4c4df17eb59c923225/remin-0.2.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c88b166fa0e35dc8411d2d01bf77f45d65a7412c30cff1c820e21bb738c625cf",
"md5": "4736f5e261357c91ebb0b1662d24e554",
"sha256": "4b8dc5513ca31c094a0b48530adadf8a5f090ec4af2d0fac74ec70b9663539eb"
},
"downloads": -1,
"filename": "remin-0.2.7.tar.gz",
"has_sig": false,
"md5_digest": "4736f5e261357c91ebb0b1662d24e554",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 908928,
"upload_time": "2023-09-01T14:50:30",
"upload_time_iso_8601": "2023-09-01T14:50:30.601714Z",
"url": "https://files.pythonhosted.org/packages/c8/8b/166fa0e35dc8411d2d01bf77f45d65a7412c30cff1c820e21bb738c625cf/remin-0.2.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-01 14:50:30",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "SalihTasdelen",
"github_project": "remin",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "setuptools",
"specs": [
[
">=",
"61.0"
]
]
},
{
"name": "wheel",
"specs": []
},
{
"name": "build",
"specs": []
}
],
"lcname": "remin"
}
