{
    "info": {
        "author": "Jianbang Ding",
        "author_email": "jianbangding@pku.edu.cn",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: Apache Software License",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: 3.7",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "\ufeff# AdaMod\n\nAn optimizer which exerts adaptive momental upper bounds on individual learning rates to prevent them becoming undesirably lager than what the historical statistics suggest and avoid the non-convergence issue, thus to a better performance. Strong empirical results on many deep learning applications demonstrate the effectiveness of our proposed method especially on complex networks such as DenseNet and Transformer.\n\n<p align='center'><img src='img/Loss.bmp' width=\"100%\"/></p>\n\n## Installation\n\nAdaMod requires Python 3.6.0 or later.\n\n### Installing via pip\n\nThe preferred way to install AdaMod is via `pip` with a virtual environment.\nJust run \n```bash\npip install adamod\n```\nin your Python environment and you are ready to go!\n\n### Using source code\n\nAs AdaMod is a Python class with only 100+ lines, an alternative way is directly downloading\n[adamod.py](./adamod/adamod.py) and copying it to your project.\n\n## Usage\n\nYou can use AdaMod just like any other PyTorch optimizers.\n\n```python3\noptimizer = adamod.AdaMod(model.parameters(), lr=1e-3, beta3=0.999)\n```\nAs described in the paper, AdaMod can smooths out unexpected large learning rates throughout the training process. The `beta3` parameter is the smoothing coefficient for actual learning rate, which controls the average range. In common cases, a `beta3` in `{0.999,0.9999}` can achieve relatively good and stable results. See the paper for more details.\n\n## Demos\n\nFor the full list of demos, please refer to [this page](./demos).\n\n## Contributors\n\n[@luoruixuan](https://github.com/luoruixuan)\n\n\n\n\n\n\n\n\n",
        "description_content_type": "",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/karrynest/AdaMod",
        "keywords": "machine learning,deep learning",
        "license": "Apache",
        "maintainer": "",
        "maintainer_email": "",
        "name": "adamod",
        "package_url": "https://pypi.org/project/adamod/",
        "platform": "",
        "project_url": "https://pypi.org/project/adamod/",
        "project_urls": {
            "Homepage": "https://github.com/karrynest/AdaMod"
        },
        "release_url": "https://pypi.org/project/adamod/0.0.3/",
        "requires_dist": [
            "torch (>=0.4.0)"
        ],
        "requires_python": ">=3.6.0",
        "summary": "AdaMod optimization algorithm, build on PyTorch.",
        "version": "0.0.3",
        "yanked": false,
        "yanked_reason": null
    },
    "last_serial": 6036268,
    "releases": {
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "7e91c66e891d4df1aaa702085f956524",
                    "sha256": "fb77ec37f93d930e13adfa9646d4dfb63e91d8311df5b4dd826bdb677340fcc8"
                },
                "downloads": -1,
                "filename": "adamod-0.0.3-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "7e91c66e891d4df1aaa702085f956524",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.6.0",
                "size": 5694,
                "upload_time": "2019-10-27T09:10:43",
                "upload_time_iso_8601": "2019-10-27T09:10:43.173368Z",
                "url": "https://files.pythonhosted.org/packages/08/84/36499b6bd4b0bd06670210b636216780699488f6c7666f766dc6f164db7d/adamod-0.0.3-py3-none-any.whl",
                "yanked": false,
                "yanked_reason": null
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "c420903e9a8f8d89b8175b7f481b817f",
                    "sha256": "6e542b2982ad183ea7879671661d19acb581f8037adcb879464df6887d6df108"
                },
                "downloads": -1,
                "filename": "adamod-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "c420903e9a8f8d89b8175b7f481b817f",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6.0",
                "size": 3342,
                "upload_time": "2019-10-27T09:10:44",
                "upload_time_iso_8601": "2019-10-27T09:10:44.527385Z",
                "url": "https://files.pythonhosted.org/packages/23/38/42505c02b17039057ea63b5047ab8ce7348ecf840161d0c865fb40543326/adamod-0.0.3.tar.gz",
                "yanked": false,
                "yanked_reason": null
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "7e91c66e891d4df1aaa702085f956524",
                "sha256": "fb77ec37f93d930e13adfa9646d4dfb63e91d8311df5b4dd826bdb677340fcc8"
            },
            "downloads": -1,
            "filename": "adamod-0.0.3-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "7e91c66e891d4df1aaa702085f956524",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6.0",
            "size": 5694,
            "upload_time": "2019-10-27T09:10:43",
            "upload_time_iso_8601": "2019-10-27T09:10:43.173368Z",
            "url": "https://files.pythonhosted.org/packages/08/84/36499b6bd4b0bd06670210b636216780699488f6c7666f766dc6f164db7d/adamod-0.0.3-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "c420903e9a8f8d89b8175b7f481b817f",
                "sha256": "6e542b2982ad183ea7879671661d19acb581f8037adcb879464df6887d6df108"
            },
            "downloads": -1,
            "filename": "adamod-0.0.3.tar.gz",
            "has_sig": false,
            "md5_digest": "c420903e9a8f8d89b8175b7f481b817f",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6.0",
            "size": 3342,
            "upload_time": "2019-10-27T09:10:44",
            "upload_time_iso_8601": "2019-10-27T09:10:44.527385Z",
            "url": "https://files.pythonhosted.org/packages/23/38/42505c02b17039057ea63b5047ab8ce7348ecf840161d0c865fb40543326/adamod-0.0.3.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "vulnerabilities": []
}