{
    "info": {
        "author": "Cesar Perez",
        "author_email": "cperez@wnohang.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 3.6",
            "Topic :: Education",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "# kim2014convolutional\n\nThis package provides a simple implementation of the models proposed in\nthe paper:\n\n> Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.\n\n## Installation\nThis package depends on the [Keras](https://keras.io/) library. This\nmeans you will need to install a backend library in order to use this\nmodule. Take a look to [Keras installation](https://keras.io/#installation)\nto get more information.\n\nAfter having installed the backend of yout choice, you just need to\ninstall this package using [pip](https://pypi.org/):\n\n    pip install kim2014convolutional\n\n## Usage\nThis package only provides a single model. To get detailed information\non the parameters the model accepts, take a look to the documentation\nincluded with the module class.\n\nHere is a complete example of instantiation of the `CNN-multichannel`\nmodel proposed in the original paper using two channel of randomly\ninitialized word embeddings:\n\n```python\nimport numpy as np\nimport numpy.random as rng\n\nvocabulary_size = 10000\nembedding_size = 300\n\nvalue = np.sqrt(6/embedding_size)\n\nweights_shape = (vocabulary_size+1, embedding_size)\nweights = rng.uniform(low=-value, high=value, size=weights_shape)\n\nchannels = [\n    {\n      'weights': [weights],\n      'trainable': False,\n      'input_dim': vocabulary_size + 1,\n      'output_dim': embedding_size,\n      'name': 'random-embedding-1'\n    },\n    {\n      'weights': [weights],\n      'trainable': True,\n      'input_dim': vocabulary_size + 1,\n      'output_dim': embedding_size,\n      'name': 'random-embedding-2'\n    }\n]\n\nwindows = [\n    {\n        'filters': 100,\n        'kernel_size': 3,\n        'activation': 'relu',\n        'name': '3-grams'\n    },\n    {\n        'filters': 100,\n        'kernel_size': 4,\n        'activation': 'relu',\n        'name': '4-grams'\n    },\n    {\n        'filters': 100,\n        'kernel_size': 5,\n        'activation': 'relu',\n        'name': '5-grams'\n    }\n]\n\nfrom kim2014convolutional import Model\n\nmodel = Model(channels=channels,\n              windows=windows,\n              sentence_length=37,\n              num_classes=6,\n              dropout_rate=0.5,\n              maxnorm_value=3,\n              classifier_activation='softmax',\n              include_top=True,\n              name='CNN-multichannel')\n\nmodel.summary()\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/wnohang/kim2014convolutional",
        "keywords": "research model",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "kim2014convolutional",
        "package_url": "https://pypi.org/project/kim2014convolutional/",
        "platform": "",
        "project_url": "https://pypi.org/project/kim2014convolutional/",
        "project_urls": {
            "Homepage": "https://github.com/wnohang/kim2014convolutional"
        },
        "release_url": "https://pypi.org/project/kim2014convolutional/0.2.0/",
        "requires_dist": [
            "keras"
        ],
        "requires_python": "",
        "summary": "Implementation of kim2014convolutional",
        "version": "0.2.0"
    },
    "last_serial": 4468863,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "9d104b8286d93cecaa2148e29b527bf6",
                    "sha256": "107a52f24c50f9e2f31b9b2065ac93e8d956971f96869e6371ae33afb51b138f"
                },
                "downloads": -1,
                "filename": "kim2014convolutional-0.1.0-py3-none-any.whl",
                "has_sig": true,
                "md5_digest": "9d104b8286d93cecaa2148e29b527bf6",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 5227,
                "upload_time": "2018-10-14T22:54:24",
                "url": "https://files.pythonhosted.org/packages/52/19/7e4787f48905f06128b95ac1e92a0e4712c6b3b6cfd105642bdded3c4f52/kim2014convolutional-0.1.0-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "fd6fadf740b0f43861c47c77b79f1a57",
                    "sha256": "34a56f9f6c36b36553b240eab44dec907a6ea8e7aed6c02c7266c077e37f86e1"
                },
                "downloads": -1,
                "filename": "kim2014convolutional-0.1.0.tar.gz",
                "has_sig": true,
                "md5_digest": "fd6fadf740b0f43861c47c77b79f1a57",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4517,
                "upload_time": "2018-10-14T22:54:26",
                "url": "https://files.pythonhosted.org/packages/7f/d2/4dd8325c6cdd193e012af99dc9377aaaeaca593bc16bda272c48df0995a6/kim2014convolutional-0.1.0.tar.gz"
            }
        ],
        "0.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "ace825b7aafc3cc0da7d7c6664ceb00d",
                    "sha256": "0fa8c0e986c29226ab8d079623515b47a366da0f059b8eb3082e4e0fc17f88dc"
                },
                "downloads": -1,
                "filename": "kim2014convolutional-0.2.0-py2-none-any.whl",
                "has_sig": false,
                "md5_digest": "ace825b7aafc3cc0da7d7c6664ceb00d",
                "packagetype": "bdist_wheel",
                "python_version": "py2",
                "requires_python": null,
                "size": 6917,
                "upload_time": "2018-11-09T10:16:34",
                "url": "https://files.pythonhosted.org/packages/f9/19/f92bea9615674e651ee6f3a932d0c9136273a9a033a080838c90ce738ba3/kim2014convolutional-0.2.0-py2-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "b6468ddfd3f5f4db30a161ba97f27001",
                    "sha256": "e4cccd512a0206ca086d0e020d13a4b08b24850e6dc143bf22529e04d8d0120a"
                },
                "downloads": -1,
                "filename": "kim2014convolutional-0.2.0.tar.gz",
                "has_sig": false,
                "md5_digest": "b6468ddfd3f5f4db30a161ba97f27001",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 5327,
                "upload_time": "2018-11-09T10:16:35",
                "url": "https://files.pythonhosted.org/packages/e9/9d/127502c308ae7c72c1f4f735f91a2b447ecbf2f86f7e447b7dc421410477/kim2014convolutional-0.2.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "ace825b7aafc3cc0da7d7c6664ceb00d",
                "sha256": "0fa8c0e986c29226ab8d079623515b47a366da0f059b8eb3082e4e0fc17f88dc"
            },
            "downloads": -1,
            "filename": "kim2014convolutional-0.2.0-py2-none-any.whl",
            "has_sig": false,
            "md5_digest": "ace825b7aafc3cc0da7d7c6664ceb00d",
            "packagetype": "bdist_wheel",
            "python_version": "py2",
            "requires_python": null,
            "size": 6917,
            "upload_time": "2018-11-09T10:16:34",
            "url": "https://files.pythonhosted.org/packages/f9/19/f92bea9615674e651ee6f3a932d0c9136273a9a033a080838c90ce738ba3/kim2014convolutional-0.2.0-py2-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "b6468ddfd3f5f4db30a161ba97f27001",
                "sha256": "e4cccd512a0206ca086d0e020d13a4b08b24850e6dc143bf22529e04d8d0120a"
            },
            "downloads": -1,
            "filename": "kim2014convolutional-0.2.0.tar.gz",
            "has_sig": false,
            "md5_digest": "b6468ddfd3f5f4db30a161ba97f27001",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 5327,
            "upload_time": "2018-11-09T10:16:35",
            "url": "https://files.pythonhosted.org/packages/e9/9d/127502c308ae7c72c1f4f735f91a2b447ecbf2f86f7e447b7dc421410477/kim2014convolutional-0.2.0.tar.gz"
        }
    ]
}