{
    "info": {
        "author": "Kristian Klemon",
        "author_email": "kristian.klemon@gmail.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "Keras \u2764\ufe0f torchtext\n=================\n\n> Keras is love  \nKeras is life  \nKeras loves torchtext\n\n[torchtext](https://github.com/pytorch/text) is a great library, putting a layer of abstraction over the usually very heavy data component in NLP projects, making the work with complex datasets a pace.\nSadly, as torchtext is based and built on PyTorch, using it with Keras is not directly possible.\n\n_Keras \u2764\ufe0f torchtext_ is to the rescue by providing lightweight wrappers for some Torchtext classes, making them easily work with Keras.\n\nInstallation\n------------\n```bash\npip install keras-loves-torchtext\n```\n\nExamples\n--------\nWrap a `torchtext.data.Iterator` with `WrapIterator` and use it to train a Keras model:\n```python\nfrom torchtext.data import Dataset, Field, Iterator\nfrom kltt import WrapIterator\n\n...\n\nfields  = [('text', Field()),\n           ('label', Field(sequential=False))]\ndataset = Dataset(examples, fields)\niterator = Iterator(dataset, batch_size=32)\n\n# Keras \u2764\ufe0f torchtext comes to play\ndata_gen = WrapIterator(iterator, x_fields=['text'], y_fields=['label'])\n\nmodel.fit_generator(iter(data_gen), steps_per_epoch=len(data_gen))\n```\n\n\nEasily wrap multiple iterators at once:\n```python\nfrom torchtext.data import Dataset, Field, Iterator\nfrom kltt import WrapIterator\n\n...\n\nfields  = [('text', Field()),\n           ('label', Field(sequential=False))]\ndataset = Dataset(examples, fields)\nsplits = dataset.split()\n\niterators = Iterator.splits(splits, batch_size=32)\ntrain, valid, test = WrapIterator.wraps(iterators, x_fields=['text'], y_fields=['label'])\nmodel.fit_generator(iter(train), steps_per_epoch=len(train),\n                    validation_data=iter(valid), validation_steps=len(valid))\nloss, acc = model.evaluate_generator(iter(test), steps=len(test))\n```\n\nFurther and full working examples can be found in the `examples` folder. \n\nDocumentation\n-------------\nTodo\n\nSee `examples` and inline documentation for now.\n\n\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/kklemon/keras-loves-torchtext",
        "keywords": "",
        "license": "BSD",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-loves-torchtext",
        "package_url": "https://pypi.org/project/keras-loves-torchtext/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-loves-torchtext/",
        "project_urls": {
            "Homepage": "https://github.com/kklemon/keras-loves-torchtext"
        },
        "release_url": "https://pypi.org/project/keras-loves-torchtext/0.0.1.1/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Make torchtext work with Keras",
        "version": "0.0.1.1"
    },
    "last_serial": 4323429,
    "releases": {
        "0.0.1": [],
        "0.0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "bb7ae80953e946e7917f3bf5e4fe4a25",
                    "sha256": "d34d9308e7dac577330daf8add3e590e86f8267e81bc6e7989f0ba3393541d2e"
                },
                "downloads": -1,
                "filename": "keras_loves_torchtext-0.0.1.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "bb7ae80953e946e7917f3bf5e4fe4a25",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": null,
                "size": 3474,
                "upload_time": "2018-09-29T19:51:54",
                "url": "https://files.pythonhosted.org/packages/2b/53/3869583538fa61e1a559a627c0ee5c2ba41c1a88e3b7d076dfc73f48957d/keras_loves_torchtext-0.0.1.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "53012fce88ae08d1bdb4666e89b14934",
                    "sha256": "4ae04689f30ea2b3ae5250fac604ab143f19f513ffaa4683dc30009ace68063d"
                },
                "downloads": -1,
                "filename": "keras-loves-torchtext-0.0.1.1.tar.gz",
                "has_sig": false,
                "md5_digest": "53012fce88ae08d1bdb4666e89b14934",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 3643,
                "upload_time": "2018-09-29T19:51:56",
                "url": "https://files.pythonhosted.org/packages/40/6c/2c95a107df8e3afd0a247212a838fdfbaf780d387ebdcb4d19b600a70faf/keras-loves-torchtext-0.0.1.1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "bb7ae80953e946e7917f3bf5e4fe4a25",
                "sha256": "d34d9308e7dac577330daf8add3e590e86f8267e81bc6e7989f0ba3393541d2e"
            },
            "downloads": -1,
            "filename": "keras_loves_torchtext-0.0.1.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "bb7ae80953e946e7917f3bf5e4fe4a25",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 3474,
            "upload_time": "2018-09-29T19:51:54",
            "url": "https://files.pythonhosted.org/packages/2b/53/3869583538fa61e1a559a627c0ee5c2ba41c1a88e3b7d076dfc73f48957d/keras_loves_torchtext-0.0.1.1-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "53012fce88ae08d1bdb4666e89b14934",
                "sha256": "4ae04689f30ea2b3ae5250fac604ab143f19f513ffaa4683dc30009ace68063d"
            },
            "downloads": -1,
            "filename": "keras-loves-torchtext-0.0.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "53012fce88ae08d1bdb4666e89b14934",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 3643,
            "upload_time": "2018-09-29T19:51:56",
            "url": "https://files.pythonhosted.org/packages/40/6c/2c95a107df8e3afd0a247212a838fdfbaf780d387ebdcb4d19b600a70faf/keras-loves-torchtext-0.0.1.1.tar.gz"
        }
    ]
}