phiflow

Name	phiflow JSON
Version	2.5.3 JSON
	download
home_page	https://github.com/tum-pbs/PhiFlow
Summary	Differentiable PDE solving framework for machine learning
upload_time	2023-11-26 12:24:42
maintainer
docs_url	None
author	Philipp Holl
requires_python
license	MIT
keywords	differentiable simulation fluid machine learning deep learning
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage

            # PhiFlow

[**Homepage**](https://github.com/tum-pbs/PhiFlow)
    [**Documentation**](https://tum-pbs.github.io/PhiFlow/)
    [**API**](https://tum-pbs.github.io/PhiFlow/phi)
    [**Demos**](https://github.com/tum-pbs/PhiFlow/tree/master/demos)
&nbsp;&nbsp;&nbsp; [<img src="https://www.tensorflow.org/images/colab_logo_32px.png" height=16> **Fluids Tutorial**](https://colab.research.google.com/github/tum-pbs/PhiFlow/blob/develop/docs/Fluids_Tutorial.ipynb#offline=true&sandboxMode=true)
&nbsp;&nbsp;&nbsp; [<img src="https://www.tensorflow.org/images/colab_logo_32px.png" height=16> **Playground**](https://colab.research.google.com/drive/1zBlQbmNguRt-Vt332YvdTqlV4DBcus2S#offline=true&sandboxMode=true)

PhiFlow is an open-source simulation toolkit built for optimization and machine learning applications.
It is written mostly in Python and can be used with NumPy, TensorFlow, Jax or PyTorch.
The close integration with machine learning frameworks allows it to leverage their automatic differentiation functionality,
making it easy to build end-to-end differentiable functions involving both learning models and physics simulations.

See the [installation Instructions](https://tum-pbs.github.io/PhiFlow/Installation_Instructions.html) on how to compile the optional custom CUDA operations.
            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/tum-pbs/PhiFlow",
    "name": "phiflow",
    "maintainer": "",
    "docs_url": null,
    "requires_python": "",
    "maintainer_email": "",
    "keywords": "Differentiable,Simulation,Fluid,Machine Learning,Deep Learning",
    "author": "Philipp Holl",
    "author_email": "philipp.holl@tum.de",
    "download_url": "https://files.pythonhosted.org/packages/af/30/79c9e4e2c128b73f31262b8458b7755c277b99ffab1bd8bd59a5217443ef/phiflow-2.5.3.tar.gz",
    "platform": null,
    "description": "# PhiFlow\n\n[**Homepage**](https://github.com/tum-pbs/PhiFlow)\n&nbsp;&nbsp;&nbsp; [**Documentation**](https://tum-pbs.github.io/PhiFlow/)\n&nbsp;&nbsp;&nbsp; [**API**](https://tum-pbs.github.io/PhiFlow/phi)\n&nbsp;&nbsp;&nbsp; [**Demos**](https://github.com/tum-pbs/PhiFlow/tree/master/demos)\n&nbsp;&nbsp;&nbsp; [<img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" height=16> **Fluids Tutorial**](https://colab.research.google.com/github/tum-pbs/PhiFlow/blob/develop/docs/Fluids_Tutorial.ipynb#offline=true&sandboxMode=true)\n&nbsp;&nbsp;&nbsp; [<img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" height=16> **Playground**](https://colab.research.google.com/drive/1zBlQbmNguRt-Vt332YvdTqlV4DBcus2S#offline=true&sandboxMode=true)\n\nPhiFlow is an open-source simulation toolkit built for optimization and machine learning applications.\nIt is written mostly in Python and can be used with NumPy, TensorFlow, Jax or PyTorch.\nThe close integration with machine learning frameworks allows it to leverage their automatic differentiation functionality,\nmaking it easy to build end-to-end differentiable functions involving both learning models and physics simulations.\n\nSee the [installation Instructions](https://tum-pbs.github.io/PhiFlow/Installation_Instructions.html) on how to compile the optional custom CUDA operations.",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "Differentiable PDE solving framework for machine learning",
    "version": "2.5.3",
    "project_urls": {
        "Download": "https://github.com/tum-pbs/PhiFlow/archive/2.5.3.tar.gz",
        "Homepage": "https://github.com/tum-pbs/PhiFlow"
    },
    "split_keywords": [
        "differentiable",
        "simulation",
        "fluid",
        "machine learning",
        "deep learning"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "af3079c9e4e2c128b73f31262b8458b7755c277b99ffab1bd8bd59a5217443ef",
                "md5": "2a03755ba6c30230989ba0b208a6b234",
                "sha256": "7e3b7a159b8c71adf50e5b54a97d403e00b45da6d72c7e1a8dc08c9f7211a724"
            },
            "downloads": -1,
            "filename": "phiflow-2.5.3.tar.gz",
            "has_sig": false,
            "md5_digest": "2a03755ba6c30230989ba0b208a6b234",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 123916,
            "upload_time": "2023-11-26T12:24:42",
            "upload_time_iso_8601": "2023-11-26T12:24:42.126908Z",
            "url": "https://files.pythonhosted.org/packages/af/30/79c9e4e2c128b73f31262b8458b7755c277b99ffab1bd8bd59a5217443ef/phiflow-2.5.3.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-11-26 12:24:42",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "tum-pbs",
    "github_project": "PhiFlow",
    "travis_ci": false,
    "coveralls": true,
    "github_actions": true,
    "lcname": "phiflow"
}