{
    "info": {
        "author": "Samuel Barham, Nirat Saini",
        "author_email": "sbarham@terpmail.umd.edu, nirat@cs.umd.edu",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 2 - Pre-Alpha"
        ],
        "description": "# Neural DSRT: Neural dialogue systems for humans\n\n[![license](https://img.shields.io/github/license/mashape/apistatus.svg?maxAge=2592000)](https://github.com/sbarham/dsrt/blob/master/LICENSE)\n\nNewborn from the University of Maryland, Neural DSRT (pronounced *dessert*) is a high-level neural dialogue systems API, written in __Python__ and running on top of familiar deep-learning (DL) and machine-learning (ML) libraries like [Keras](https://github.com/keras-team/keras), [TensorFlow](https://github.com/tensorflow/tensorflow), and [scikit-learn](https://github.com/scikit-learn/scikit-learn). It focuses on allowing for the easy construction, training, and testing of __neural dialogue models__. \n\nIts key purpose is *to enable rapid development and experimentation* in a burgeoning field otherwise bereft of high-level libraries with busy researchers in mind.\n\n<!-- Read the documentation at [Keras.io](https://keras.io) -->\n\n\n## What is it for?\n\n__Neural DSRT__ is all about building end-to-end dialogue systems using state-of-the-art neural dialogue models. It is a new project (born at the University of Maryland in the waining days and weeks of March, 2018), and it still has a lot of growing to do.\n\nIn order to help that growth along, we adopt a few guiding principles liberally from [Keras](https://github.com/keras-team/keras):\n\n- __User-friendliness.__ Ease-of-use should be front and center, the library should expose consistent & simple APIs, and should minimize the amount of work involved in getting common use-cases up and running. The focus should be on enabling rapid, hassle-free experimentation with neural dialog models.\n\n- __Modularity.__ Dialogue experiments, and their constituent components -- dataset wrappers, data preprocessors, neural dialogue models, conversation objects -- should alike be implemented as fully-configurable modules that can be plugged together with as few restrictions as possible. Experiments, and their components, should be richly configurable -- but components should fall back on sensible defaults, so that configuration should never be necessary\n\n- __Extensibility.__ New modules should be simple to add (as new classes and functions), and existing modules and scripts should provide ample and __liberally documented__ examples.\n\n\n## How do I use it? 90 seconds to Neural DSRT\n\n*This quickstart guide has yet to be written -- but it should be coming soon.*\n<!--\n>>>>>>> cde833a8db0adfd4306cc86f265e9e3da38d39c8\nThe core data structure of Keras is a __model__, a way to organize layers. The simplest type of model is the [`Sequential`](https://keras.io/getting-started/sequential-model-guide) model, a linear stack of layers. For more complex architectures, you should use the [Keras functional API](https://keras.io/getting-started/functional-api-guide), which allows to build arbitrary graphs of layers.\n\nHere is the `Sequential` model:\n\n```python\nfrom keras.models import Sequential\n\nmodel = Sequential()\n```\n\nStacking layers is as easy as `.add()`:\n\n```python\nfrom keras.layers import Dense\n\nmodel.add(Dense(units=64, activation='relu', input_dim=100))\nmodel.add(Dense(units=10, activation='softmax'))\n```\n\nOnce your model looks good, configure its learning process with `.compile()`:\n\n```python\nmodel.compile(loss='categorical_crossentropy',\n              optimizer='sgd',\n              metrics=['accuracy'])\n```\n\nIf you need to, you can further configure your optimizer. A core principle of Keras is to make things reasonably simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code).\n```python\nmodel.compile(loss=keras.losses.categorical_crossentropy,\n              optimizer=keras.optimizers.SGD(lr=0.01, momentum=0.9, nesterov=True))\n```\n\nYou can now iterate on your training data in batches:\n\n```python\n# x_train and y_train are Numpy arrays --just like in the Scikit-Learn API.\nmodel.fit(x_train, y_train, epochs=5, batch_size=32)\n```\n\nAlternatively, you can feed batches to your model manually:\n\n```python\nmodel.train_on_batch(x_batch, y_batch)\n```\n\nEvaluate your performance in one line:\n\n```python\nloss_and_metrics = model.evaluate(x_test, y_test, batch_size=128)\n```\n\nOr generate predictions on new data:\n\n```python\nclasses = model.predict(x_test, batch_size=128)\n```\n\nBuilding a question answering system, an image classification model, a Neural Turing Machine, or any other model is just as fast. The ideas behind deep learning are simple, so why should their implementation be painful?\n\nFor a more in-depth tutorial about Keras, you can check out:\n\n- [Getting started with the Sequential model](https://keras.io/getting-started/sequential-model-guide)\n- [Getting started with the functional API](https://keras.io/getting-started/functional-api-guide)\n\nIn the [examples folder](https://github.com/keras-team/keras/tree/master/examples) of the repository, you will find more advanced models: question-answering with memory networks, text generation with stacked LSTMs, etc.\n-->\n\n\n## How can I install it?\n\nBefore attempting to install Neural DSRT, you'll need to install Keras (which it's built on):\n\n- [Keras installation instructions](https://keras.io/#installation)\n\nIn installing Keras, you'll of course need to install a neural-network backend. We recommend TensorFlow:\n\n- [TensorFlow installation instructions](https://www.tensorflow.org/install/).\n\nOnce you've done this, you're ready to install DSRT. Currently, the only way to do this is from the GitHub source. Thankfully, this is pretty easy, so long as you have `pip` installed on your machine (did we mention you'll need Python? you'll need Python -- we recommend the latest version of Python 3). \n\nJust in case, instructions for installing `pip` may be found here:\n\n- [pip installation instructions](https://pip.pypa.io/en/stable/installing/)\n\nAssuming you've followed up until this point, proceed to __clone DSRT__ using `git`:\n\n```sh\ngit clone https://github.com/sbarham/dsrt.git\n```\n\n Now, `cd` to the Neural DSRT folder and install using `pip`:\n```sh\ncd dsrt\nsudo pip install .\n```\n\nIt's as easy as that. Now you're ready to use Neural DSRT!\n\n\n# How can I help?\n\nAs we mentioned above, DSRT is very young -- in fact, it's only a few weeks old at the moment. If you're a developer (and especially if you're confident with deep learning, machine learning, or neural dialogue systems) and you'd like to help, please contact the original authors directly at `sbarham@cs.umd.edu`. We'd love to collaborate with you.\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/sbarham/dsrt",
        "keywords": "AI artificial intelligence neural dialogue systems chat chatbot chatterbot nlp nautral language generation human computer interaction conversation",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "dsrt",
        "package_url": "https://pypi.org/project/dsrt/",
        "platform": "",
        "project_url": "https://pypi.org/project/dsrt/",
        "project_urls": {
            "Homepage": "https://github.com/sbarham/dsrt"
        },
        "release_url": "https://pypi.org/project/dsrt/0.0.1/",
        "requires_dist": [
            "dsrt",
            "h5py"
        ],
        "requires_python": ">=3",
        "summary": "High-level library for building and testing neural dialogue systems",
        "version": "0.0.1"
    },
    "last_serial": 3730534,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "a3d3b78eec50e7de3ef3fddc7bc15ea9",
                    "sha256": "90633a19370ea1c38eb72092aa4dc8e466860fb3597b04f8c6f4ccc1c2ba0455"
                },
                "downloads": -1,
                "filename": "dsrt-0.0.1-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "a3d3b78eec50e7de3ef3fddc7bc15ea9",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": ">=3",
                "size": 36423,
                "upload_time": "2018-04-03T17:26:37",
                "url": "https://files.pythonhosted.org/packages/33/32/a7108df30345c6d61e96ca2dc6fb68f8a7d77fdbe691e800d8d910f13966/dsrt-0.0.1-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "06089adb219b1547e137a3925f110f71",
                    "sha256": "5f892daceaea993296e7905bab579d88992c6ba755a49d6e0791204db2bdc145"
                },
                "downloads": -1,
                "filename": "dsrt-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "06089adb219b1547e137a3925f110f71",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3",
                "size": 25098501,
                "upload_time": "2018-04-03T17:26:40",
                "url": "https://files.pythonhosted.org/packages/be/79/14c10d4658ab8049e30510c0d26a8ed2168b7f10ff3565f64ffbbabeff05/dsrt-0.0.1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "a3d3b78eec50e7de3ef3fddc7bc15ea9",
                "sha256": "90633a19370ea1c38eb72092aa4dc8e466860fb3597b04f8c6f4ccc1c2ba0455"
            },
            "downloads": -1,
            "filename": "dsrt-0.0.1-py2.py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "a3d3b78eec50e7de3ef3fddc7bc15ea9",
            "packagetype": "bdist_wheel",
            "python_version": "py2.py3",
            "requires_python": ">=3",
            "size": 36423,
            "upload_time": "2018-04-03T17:26:37",
            "url": "https://files.pythonhosted.org/packages/33/32/a7108df30345c6d61e96ca2dc6fb68f8a7d77fdbe691e800d8d910f13966/dsrt-0.0.1-py2.py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "06089adb219b1547e137a3925f110f71",
                "sha256": "5f892daceaea993296e7905bab579d88992c6ba755a49d6e0791204db2bdc145"
            },
            "downloads": -1,
            "filename": "dsrt-0.0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "06089adb219b1547e137a3925f110f71",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3",
            "size": 25098501,
            "upload_time": "2018-04-03T17:26:40",
            "url": "https://files.pythonhosted.org/packages/be/79/14c10d4658ab8049e30510c0d26a8ed2168b7f10ff3565f64ffbbabeff05/dsrt-0.0.1.tar.gz"
        }
    ]
}