{
    "info": {
        "author": "CyberZHG",
        "author_email": "CyberZHG@users.noreply.github.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 Transfer Masking\n\n[![Travis](https://travis-ci.org/CyberZHG/keras-trans-mask.svg)](https://travis-ci.org/CyberZHG/keras-trans-mask)\n[![Coverage](https://coveralls.io/repos/github/CyberZHG/keras-trans-mask/badge.svg?branch=master)](https://coveralls.io/github/CyberZHG/keras-trans-mask)\n\nRemove and restore masks for layers that do not support masking. Note that the result may be incorrect in most cases.\n\n## Install\n\n```bash\npip install keras-trans-mask\n```\n\n## Usage\n\n`Conv1D` does not support masking. By removing the mask you'll get a \"nearly correct\" output:\n\n```python\nimport keras\nfrom keras_trans_mask import RemoveMask, RestoreMask\n\ninput_layer = keras.layers.Input(shape=(None,))\nembed_layer = keras.layers.Embedding(\n    input_dim=10,\n    output_dim=15,\n    mask_zero=True,\n)(input_layer)\nremoved_layer = RemoveMask()(embed_layer)  # Remove mask from embeddings\nconv_layer = keras.layers.Conv1D(\n    filters=32,\n    kernel_size=3,\n    padding='same',\n)(removed_layer)\nrestored_layer = RestoreMask()([conv_layer, embed_layer])  # Restore mask from embeddings\nlstm_layer = keras.layers.LSTM(units=5)(restored_layer)\ndense_layer = keras.layers.Dense(units=2, activation='softmax')(lstm_layer)\nmodel = keras.models.Model(inputs=input_layer, outputs=dense_layer)\nmodel.compile(optimizer='adam', loss='sparse_categorical_crossentropy')\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-trans-mask",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-trans-mask",
        "package_url": "https://pypi.org/project/keras-trans-mask/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-trans-mask/",
        "project_urls": {
            "Homepage": "https://github.com/CyberZHG/keras-trans-mask"
        },
        "release_url": "https://pypi.org/project/keras-trans-mask/0.3.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Transfer masking in Keras",
        "version": "0.3.0"
    },
    "last_serial": 5603988,
    "releases": {
        "0.2.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b4ecba0851069430ee766492969668b0",
                    "sha256": "3a57d662b9a841acdfb8ce9ca88dfecb88696e097b17436897b43787f2f57691"
                },
                "downloads": -1,
                "filename": "keras-trans-mask-0.2.0.tar.gz",
                "has_sig": false,
                "md5_digest": "b4ecba0851069430ee766492969668b0",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 2954,
                "upload_time": "2019-07-30T04:13:52",
                "url": "https://files.pythonhosted.org/packages/30/0f/3ef6b484773952aba2f2ff782e07e8de2db14146fe28987279f91dfc1e96/keras-trans-mask-0.2.0.tar.gz"
            }
        ],
        "0.3.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "11b394cbc70a342ae3958d262279779c",
                    "sha256": "07a8b240bb83497d86b4b5ee16e318acde3344a680b8cc93bb382d5233d44b32"
                },
                "downloads": -1,
                "filename": "keras-trans-mask-0.3.0.tar.gz",
                "has_sig": false,
                "md5_digest": "11b394cbc70a342ae3958d262279779c",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 3139,
                "upload_time": "2019-07-30T04:55:44",
                "url": "https://files.pythonhosted.org/packages/69/7e/ab721f17aeb089144c52d26355ff5d27f63611c54bd3e3065829488e8d08/keras-trans-mask-0.3.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "11b394cbc70a342ae3958d262279779c",
                "sha256": "07a8b240bb83497d86b4b5ee16e318acde3344a680b8cc93bb382d5233d44b32"
            },
            "downloads": -1,
            "filename": "keras-trans-mask-0.3.0.tar.gz",
            "has_sig": false,
            "md5_digest": "11b394cbc70a342ae3958d262279779c",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 3139,
            "upload_time": "2019-07-30T04:55:44",
            "url": "https://files.pythonhosted.org/packages/69/7e/ab721f17aeb089144c52d26355ff5d27f63611c54bd3e3065829488e8d08/keras-trans-mask-0.3.0.tar.gz"
        }
    ]
}