{
    "info": {
        "author": "Robin Kahlow (Toraxxx)",
        "author_email": "xtremegosugaming@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha"
        ],
        "description": "gsdr\r\n====\r\n\r\nGenerative Sparse Distributed Representations, a fast generative model\r\nwritten in Python (Original C++ implementation\r\nhttps://github.com/222464/GSDR)\r\n\r\nDependencies\r\n============\r\n\r\n-  Python 3\r\n-  Python libraries\r\n\r\n   -  numpy\r\n\r\nInstallation\r\n============\r\n\r\n``pip install gsdr`` or clone and ``python setup.py install``\r\n\r\nUsage\r\n=====\r\n\r\n(More extensive examples and IPython notebooks can be found in\r\nexamples/)\r\n\r\nWith labeled data:\r\n\r\n.. code:: python\r\n\r\n    data, labels = ...\r\n\r\n    num_labels = 10\r\n\r\n    # Data: (batches, num_features)\r\n    # Labels: (batches,) (contains numbers from 0 to num_labels-1, eg. 10 for MNIST)\r\n\r\n    # Build the GSDR network (only one layer for now)\r\n    gsdr = GSDRStack()\r\n    gsdr.add(input_count=data.shape[1], hidden_count=256, sparsity=0.1, forced_latent_count=num_labels)\r\n\r\n    forced_latents = np.eye(num_labels)\r\n\r\n    # Train once for each data point\r\n    for i in range(data.shape[0]):\r\n        gsdr.train(data[i], forced_latents={0: forced_latents[labels[i]]})\r\n        \r\n    # Generate one example for each label\r\n    for i in range(num_labels):\r\n        generated = gsdr.generate(forced_latents={0: forced_latents[i]})\r\n\r\nWith unlabeled data:\r\n\r\n.. code:: python\r\n\r\n    data = ...\r\n\r\n    # Data: (batches, num_features)\r\n\r\n    # Build the GSDR network (only one layer for now)\r\n    gsdr = GSDRStack()\r\n    gsdr.add(input_count=data.shape[1], hidden_count=256, sparsity=0.1)\r\n\r\n    # Train once for each data point\r\n    for i in range(data.shape[0]):\r\n        gsdr.train(data[i])\r\n        \r\n    states = np.eye(hidden_count)\r\n\r\n    # Generate one example for each one-hot state\r\n    for i in range(hidden_count):\r\n        generated = gsdr.generate(states[i])",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "UNKNOWN",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/ToraxXx/gsdr",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "gsdr",
        "package_url": "https://pypi.org/project/gsdr/",
        "platform": "any",
        "project_url": "https://pypi.org/project/gsdr/",
        "project_urls": {
            "Download": "UNKNOWN",
            "Homepage": "https://github.com/ToraxXx/gsdr"
        },
        "release_url": "https://pypi.org/project/gsdr/0.1.1/",
        "requires_dist": null,
        "requires_python": null,
        "summary": "Generative Sparse Distributed Representations, a fast generative model",
        "version": "0.1.1"
    },
    "last_serial": 2240751,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "d04448430191a4677160b5f044447423",
                    "sha256": "c9afa114e71d2701941331f30b84d2b55d9f5d889c7d56abc52d3a8293d14341"
                },
                "downloads": -1,
                "filename": "gsdr-0.1.0.zip",
                "has_sig": false,
                "md5_digest": "d04448430191a4677160b5f044447423",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 2372,
                "upload_time": "2016-07-21T14:15:12",
                "url": "https://files.pythonhosted.org/packages/37/97/ebe96af31d28047580c8b91475c2eb7fbb84a7590c5fdab67ea53bca2d46/gsdr-0.1.0.zip"
            }
        ],
        "0.1.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "1475966985631b5a7c50b837d47c385e",
                    "sha256": "172750cc3ad23db1f40a6aa3fc121f208af5053a9649c392d380e40a1f4998df"
                },
                "downloads": -1,
                "filename": "gsdr-0.1.1.zip",
                "has_sig": false,
                "md5_digest": "1475966985631b5a7c50b837d47c385e",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 2480,
                "upload_time": "2016-07-24T12:12:07",
                "url": "https://files.pythonhosted.org/packages/3f/85/b7b0b71c19459ceb4714c70c7d90cd21a1d61abd10e815404970835feba2/gsdr-0.1.1.zip"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "1475966985631b5a7c50b837d47c385e",
                "sha256": "172750cc3ad23db1f40a6aa3fc121f208af5053a9649c392d380e40a1f4998df"
            },
            "downloads": -1,
            "filename": "gsdr-0.1.1.zip",
            "has_sig": false,
            "md5_digest": "1475966985631b5a7c50b837d47c385e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 2480,
            "upload_time": "2016-07-24T12:12:07",
            "url": "https://files.pythonhosted.org/packages/3f/85/b7b0b71c19459ceb4714c70c7d90cd21a1d61abd10e815404970835feba2/gsdr-0.1.1.zip"
        }
    ]
}