mingru-keras

Name	mingru-keras JSON
Version	0.1.0 JSON
	download
home_page	None
Summary	This package contains a Keras 3 implementation of the MinGRU layer, a minimal and parallelizable version of the gated recurrent unit (GRU).
upload_time	2024-10-25 09:26:08
maintainer	None
docs_url	None
author	None
requires_python	>=3.10
license	None
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # MinGRU Implementation in Keras

This repository contains a Keras implementation of the MinGRU model, a minimal
and parallelizable version of the traditional Gated Recurrent Unit (GRU)
architecture. The MinGRU model is based on the research paper ["Were RNNs All We
Needed?"](https://arxiv.org/abs/2410.01201) that revisits traditional recurrent
neural networks and modifies them to be efficiently trained in parallel.

## Features

* Minimal GRU architecture with significantly fewer parameters than traditional GRUs
* Fully parallelizable during training, achieving faster training times
* Compatible with Keras 3

## Dependencies

This project uses uv to manage dependencies. To install the required dependencies, run:

```bash
uv install
```

## Usage

To use the MinGRU model in your own project, simply import the `MinGRU` class
and use it as you would any other Keras layer.

## Example

```python
import keras

from mingru_keras import MinGRU

layer = MinGRU(units=64)

b, t, d = 32, 1000, 8
X = keras.random.normal((b, t, d))
Y = layer(X)
```

## Contributing

Contributions are welcome! If you'd like to report a bug or suggest a feature, please open an issue or submit a pull request.
            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "mingru-keras",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.10",
    "maintainer_email": null,
    "keywords": null,
    "author": null,
    "author_email": "Boris Reuderink <boris@cortext.nl>",
    "download_url": "https://files.pythonhosted.org/packages/78/d9/22fa68867abd525d90fd6f297d0728d11596327bd1be2c76d12ca14ee882/mingru_keras-0.1.0.tar.gz",
    "platform": null,
    "description": "# MinGRU Implementation in Keras\n\nThis repository contains a Keras implementation of the MinGRU model, a minimal\nand parallelizable version of the traditional Gated Recurrent Unit (GRU)\narchitecture. The MinGRU model is based on the research paper [\"Were RNNs All We\nNeeded?\"](https://arxiv.org/abs/2410.01201) that revisits traditional recurrent\nneural networks and modifies them to be efficiently trained in parallel.\n\n## Features\n\n* Minimal GRU architecture with significantly fewer parameters than traditional GRUs\n* Fully parallelizable during training, achieving faster training times\n* Compatible with Keras 3\n\n## Dependencies\n\nThis project uses uv to manage dependencies. To install the required dependencies, run:\n\n```bash\nuv install\n```\n\n## Usage\n\nTo use the MinGRU model in your own project, simply import the `MinGRU` class\nand use it as you would any other Keras layer.\n\n## Example\n\n```python\nimport keras\n\nfrom mingru_keras import MinGRU\n\nlayer = MinGRU(units=64)\n\nb, t, d = 32, 1000, 8\nX = keras.random.normal((b, t, d))\nY = layer(X)\n```\n\n## Contributing\n\nContributions are welcome! If you'd like to report a bug or suggest a feature, please open an issue or submit a pull request.",
    "bugtrack_url": null,
    "license": null,
    "summary": "This package contains a Keras 3 implementation of the MinGRU layer, a minimal and parallelizable version of the gated recurrent unit (GRU).",
    "version": "0.1.0",
    "project_urls": null,
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "7c03b087e66d6064ef75ef4c49f24dadb71badc6d969be502c1a7657368d46cd",
                "md5": "20855dba44cc72c16bc6e625d9afb5ec",
                "sha256": "7a9ab300b1f77d3a7fc79c6161df896b695c8a71b333e6f864dad9e9fd492ec5"
            },
            "downloads": -1,
            "filename": "mingru_keras-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "20855dba44cc72c16bc6e625d9afb5ec",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.10",
            "size": 3762,
            "upload_time": "2024-10-25T09:26:07",
            "upload_time_iso_8601": "2024-10-25T09:26:07.160528Z",
            "url": "https://files.pythonhosted.org/packages/7c/03/b087e66d6064ef75ef4c49f24dadb71badc6d969be502c1a7657368d46cd/mingru_keras-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "78d922fa68867abd525d90fd6f297d0728d11596327bd1be2c76d12ca14ee882",
                "md5": "2579f90663f368187eff1b15acffd4d7",
                "sha256": "6982e9b7ed52308dd0b95909b2c05044a6459d6150f8d74b5525b658b3f62eaf"
            },
            "downloads": -1,
            "filename": "mingru_keras-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "2579f90663f368187eff1b15acffd4d7",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.10",
            "size": 3795,
            "upload_time": "2024-10-25T09:26:08",
            "upload_time_iso_8601": "2024-10-25T09:26:08.364335Z",
            "url": "https://files.pythonhosted.org/packages/78/d9/22fa68867abd525d90fd6f297d0728d11596327bd1be2c76d12ca14ee882/mingru_keras-0.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-10-25 09:26:08",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "mingru-keras"
}