complex-attn


Namecomplex-attn JSON
Version 0.0.3 PyPI version JSON
download
home_pagehttps://github.com/kyegomez/ct
Summaryct - Pytorch
upload_time2023-10-07 15:56:32
maintainer
docs_urlNone
authorKye Gomez
requires_python>=3.6,<4.0
licenseMIT
keywords artificial intelligence deep learning optimizers prompt engineering
VCS
bugtrack_url
requirements torch einops
Travis-CI No Travis.
coveralls test coverage No coveralls.
            [![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)

# Complex Transformer
The open source implementation of the attention and transformer from "Building Blocks for a Complex-Valued Transformer Architecture" where they propose an an attention mechanism for complex valued signals or images such as MRI and remote sensing.

They present:
- complex valued scaled dot product attention
- complex valued layer normalization
- results show improved robustness to overfitting while maintaing performance wbhen compared to real valued transformer

## Install
`pip install ct`

# License
MIT




            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/kyegomez/ct",
    "name": "complex-attn",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.6,<4.0",
    "maintainer_email": "",
    "keywords": "artificial intelligence,deep learning,optimizers,Prompt Engineering",
    "author": "Kye Gomez",
    "author_email": "kye@apac.ai",
    "download_url": "https://files.pythonhosted.org/packages/64/56/604a95193596e88713ad297f482f4ce90f8c0ea1e22af83da562d500ddcf/complex_attn-0.0.3.tar.gz",
    "platform": null,
    "description": "[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# Complex Transformer\nThe open source implementation of the attention and transformer from \"Building Blocks for a Complex-Valued Transformer Architecture\" where they propose an an attention mechanism for complex valued signals or images such as MRI and remote sensing.\n\nThey present:\n- complex valued scaled dot product attention\n- complex valued layer normalization\n- results show improved robustness to overfitting while maintaing performance wbhen compared to real valued transformer\n\n## Install\n`pip install ct`\n\n# License\nMIT\n\n\n\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "ct - Pytorch",
    "version": "0.0.3",
    "project_urls": {
        "Homepage": "https://github.com/kyegomez/ct",
        "Repository": "https://github.com/kyegomez/ct"
    },
    "split_keywords": [
        "artificial intelligence",
        "deep learning",
        "optimizers",
        "prompt engineering"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "5874a55ee4d08f251f363b9233ba94171296566c341d5e64b2f3558d367fe31d",
                "md5": "6ed9e9efea063bf5f306df04a970098f",
                "sha256": "b810d00c848ab76e61ade9b225727c3bdf833555599a4f0e5d42a9d107c61008"
            },
            "downloads": -1,
            "filename": "complex_attn-0.0.3-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "6ed9e9efea063bf5f306df04a970098f",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6,<4.0",
            "size": 4194,
            "upload_time": "2023-10-07T15:56:30",
            "upload_time_iso_8601": "2023-10-07T15:56:30.804621Z",
            "url": "https://files.pythonhosted.org/packages/58/74/a55ee4d08f251f363b9233ba94171296566c341d5e64b2f3558d367fe31d/complex_attn-0.0.3-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "6456604a95193596e88713ad297f482f4ce90f8c0ea1e22af83da562d500ddcf",
                "md5": "77dfad3c49bdc76553214df1cb588ba6",
                "sha256": "309d55fd87dfccbe6dcb25fb186fad46cc5a02f9f732da463e2434dde4e853a6"
            },
            "downloads": -1,
            "filename": "complex_attn-0.0.3.tar.gz",
            "has_sig": false,
            "md5_digest": "77dfad3c49bdc76553214df1cb588ba6",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6,<4.0",
            "size": 4219,
            "upload_time": "2023-10-07T15:56:32",
            "upload_time_iso_8601": "2023-10-07T15:56:32.696082Z",
            "url": "https://files.pythonhosted.org/packages/64/56/604a95193596e88713ad297f482f4ce90f8c0ea1e22af83da562d500ddcf/complex_attn-0.0.3.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-10-07 15:56:32",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "kyegomez",
    "github_project": "ct",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "requirements": [
        {
            "name": "torch",
            "specs": []
        },
        {
            "name": "einops",
            "specs": []
        }
    ],
    "lcname": "complex-attn"
}
        
Elapsed time: 0.13308s