{
    "info": {
        "author": "niley1nov",
        "author_email": "nilaysharma1nov@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 3.7"
        ],
        "description": "# Keras RNAdam\n\nuse of nesterov accelerated geadient instead of momentum in rectified-adam\n\n## Install\n\n```bash\npip install keras_rnadam\n```\n\n## Usage\n\n```python\nimport keras\nimport numpy as np\nfrom keras_rnadam import RNAdam\n\n# Build toy model with RNAdam optimizer\nmodel = keras.models.Sequential()\nmodel.add(keras.layers.Dense(input_shape=(17,), units=3))\nmodel.compile(RNAdam(), loss='mse')\n\n# Generate toy data\nx = np.random.standard_normal((4096 * 30, 17))\nw = np.random.standard_normal((17, 3))\ny = np.dot(x, w)\n\n# Fit\nmodel.fit(x, y, epochs=5)\n```\n\n### Use Warmup\n\n```python\nfrom keras_nradam import RNAdam\nRNAdam(total_step=10000, warmup_proportion=0.1, min_lr=1e-5)\n```",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/niley1nov/keras_rnadam/archive/0.2.0.tar.gz",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-rnadam",
        "package_url": "https://pypi.org/project/keras-rnadam/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-rnadam/",
        "project_urls": {
            "Homepage": "https://github.com/niley1nov/keras_rnadam/archive/0.2.0.tar.gz"
        },
        "release_url": "https://pypi.org/project/keras-rnadam/0.2.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Rectified Nadam implemented in Keras",
        "version": "0.2.0"
    },
    "last_serial": 5690951,
    "releases": {
        "0.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b509fb34eafefbe57cce3c40a2c0137a",
                    "sha256": "7436f9d1a7b9bc36251993f53f04db91f7bc1b6576bfa7cddd0dc2f05c433cd3"
                },
                "downloads": -1,
                "filename": "keras_rnadam-0.2.0.tar.gz",
                "has_sig": false,
                "md5_digest": "b509fb34eafefbe57cce3c40a2c0137a",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 3500,
                "upload_time": "2019-08-17T08:15:56",
                "url": "https://files.pythonhosted.org/packages/0a/d9/1f0fccf4fd7252a5cdf913f02273c4cbebe8b61f4251d438e7040011b8fd/keras_rnadam-0.2.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "b509fb34eafefbe57cce3c40a2c0137a",
                "sha256": "7436f9d1a7b9bc36251993f53f04db91f7bc1b6576bfa7cddd0dc2f05c433cd3"
            },
            "downloads": -1,
            "filename": "keras_rnadam-0.2.0.tar.gz",
            "has_sig": false,
            "md5_digest": "b509fb34eafefbe57cce3c40a2c0137a",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 3500,
            "upload_time": "2019-08-17T08:15:56",
            "url": "https://files.pythonhosted.org/packages/0a/d9/1f0fccf4fd7252a5cdf913f02273c4cbebe8b61f4251d438e7040011b8fd/keras_rnadam-0.2.0.tar.gz"
        }
    ]
}