{
    "info": {
        "author": "CyberZHG",
        "author_email": "CyberZHG@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3.6"
        ],
        "description": "# Keras Successive Regularization Wrapper\n\n[![Travis](https://travis-ci.org/CyberZHG/keras-succ-reg-wrapper.svg)](https://travis-ci.org/CyberZHG/keras-succ-reg-wrapper)\n[![Coverage](https://coveralls.io/repos/github/CyberZHG/keras-succ-reg-wrapper/badge.svg?branch=master)](https://coveralls.io/github/CyberZHG/keras-succ-reg-wrapper)\n\nA wrapper that slows down the updates of trainable weights.\n\n![](https://user-images.githubusercontent.com/853842/50722430-dce6c580-1109-11e9-834d-7dc92b9221db.png)\n\n## Install\n\n```bash\npip install keras-succ-reg-wrapper\n```\n\n## Usage\n\n```python\nimport keras\nfrom keras_succ_reg_wrapper import SuccReg\n\ninput_layer = keras.layers.Input(shape=(1,), name='Input')\ndense_layer = SuccReg(\n    layer=keras.layers.Dense(units=1, name='Dense'),\n    regularizer=keras.regularizers.L1L2(l2=1e-3),  # Any regularizer\n    name='Output',\n)(input_layer)\nmodel = keras.models.Model(inputs=input_layer, outputs=dense_layer)\nmodel.compile(optimizer='adam', loss='mse')\nmodel.summary()\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/CyberZHG/keras-succ-reg-wrapper",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-succ-reg-wrapper",
        "package_url": "https://pypi.org/project/keras-succ-reg-wrapper/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-succ-reg-wrapper/",
        "project_urls": {
            "Homepage": "https://github.com/CyberZHG/keras-succ-reg-wrapper"
        },
        "release_url": "https://pypi.org/project/keras-succ-reg-wrapper/0.4.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "A wrapper that slows down the updates of trainable weights",
        "version": "0.4.0"
    },
    "last_serial": 4766719,
    "releases": {
        "0.3.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "89b79fb80183827572bab0f974ecfdd6",
                    "sha256": "78c7f480001411ea908a0fdcf5a51e86403d02d27a14faf9db5e09d9f9ca596b"
                },
                "downloads": -1,
                "filename": "keras-succ-reg-wrapper-0.3.0.tar.gz",
                "has_sig": false,
                "md5_digest": "89b79fb80183827572bab0f974ecfdd6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 2801,
                "upload_time": "2019-01-05T10:05:07",
                "url": "https://files.pythonhosted.org/packages/c8/39/f6e33ab3e5f4782d96b6bd997f466b89e3fe2524c97ba8f355921db220df/keras-succ-reg-wrapper-0.3.0.tar.gz"
            }
        ],
        "0.4.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "c7978ce087645c9d45e05ecac6be691a",
                    "sha256": "f95e5da1fd1b1f59a8e800dbec4db7582d99abcdcfbde613d4454ec50a844ce9"
                },
                "downloads": -1,
                "filename": "keras-succ-reg-wrapper-0.4.0.tar.gz",
                "has_sig": false,
                "md5_digest": "c7978ce087645c9d45e05ecac6be691a",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 2863,
                "upload_time": "2019-02-01T03:32:56",
                "url": "https://files.pythonhosted.org/packages/78/31/7a2847ddf48af8c3aff91b926c2b22c9fb2cb3db12afb92994eeae0195fd/keras-succ-reg-wrapper-0.4.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "c7978ce087645c9d45e05ecac6be691a",
                "sha256": "f95e5da1fd1b1f59a8e800dbec4db7582d99abcdcfbde613d4454ec50a844ce9"
            },
            "downloads": -1,
            "filename": "keras-succ-reg-wrapper-0.4.0.tar.gz",
            "has_sig": false,
            "md5_digest": "c7978ce087645c9d45e05ecac6be691a",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 2863,
            "upload_time": "2019-02-01T03:32:56",
            "url": "https://files.pythonhosted.org/packages/78/31/7a2847ddf48af8c3aff91b926c2b22c9fb2cb3db12afb92994eeae0195fd/keras-succ-reg-wrapper-0.4.0.tar.gz"
        }
    ]
}