{
    "info": {
        "author": "Hannes Bretschneider",
        "author_email": "hannes@psi.utoronto.ca",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: GNU General Public License v2 (GPLv2)",
            "Programming Language :: C",
            "Programming Language :: Python :: 2.7",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Scientific/Engineering :: Image Recognition"
        ],
        "description": "Hebel\n=====\n\nGPU-Accelerated Deep Learning Library in Python\n\nHebel is a library for deep learning with neural networks in Python\nusing GPU acceleration with CUDA through PyCUDA. It implements the most\nimportant types of neural network models and offers a variety of\ndifferent activation functions and training methods such as momentum,\nNesterov momentum, dropout, and early stopping.\n\nModels\n------\n\nRight now, Hebel implements feed-forward neural networks for\nclassification and regression on one or multiple tasks. Other models\nsuch as Autoencoder, Convolutional neural nets, and Restricted Boltzman\nmachines are planned for the future.\n\nHebel implements dropout as well as L1 and L2 weight decay for\nregularization.\n\nOptimization\n------------\n\nHebel implements stochastic gradient descent (SGD) with regular and\nNesterov momentum.\n\nCompatibility\n-------------\n\nCurrently, Hebel will run on Linux and Windows, and probably Mac OS X\n(not tested).\n\nDependencies\n------------\n\n-  PyCUDA\n-  numpy\n-  PyYAML\n-  skdata (only for MNIST example)\n\nInstallation\n------------\n\nHebel is on PyPi, so you can install it with\n\n::\n\n    pip install hebel\n\nGetting started\n---------------\n\nStudy the yaml configuration files in ``examples/`` and run\n\n::\n\n    python train_model.py examples/mnist_neural_net_shallow.yml\n\nThe script will create a directory in ``examples/mnist`` where the\nmodels and logs are saved.\n\nRead the Getting started guide at\n`hebel.readthedocs.org/en/latest/getting\\_started.html <http://hebel.readthedocs.org/en/latest/getting_started.html>`__\nfor more information.\n\nDocumentation\n-------------\n\n`hebel.readthedocs.org <http://hebel.readthedocs.org>`__ (coming slowly)\n\nContact\n-------\n\nMaintained by `Hannes Bretschneider <http://github.com/hannes-brt>`__\n(hannes@psi.utoronto.ca). If your are using Hebel, please let me know\nwhether you find it useful and file a Github issue if you find any bugs\nor have feature requests.\n\nWhat's with the name?\n---------------------\n\n*Hebel* is the German word for *lever*, one of the oldest tools that\nhumans use. As Archimedes said it: *\"Give me a lever long enough and a\nfulcrum on which to place it, and I shall move the world.\"*",
        "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/hannes-brt/hebel",
        "keywords": "cuda gpu machine-learning deep-learning neural-networks",
        "license": "GPLv2",
        "maintainer": null,
        "maintainer_email": null,
        "name": "Hebel",
        "package_url": "https://pypi.org/project/Hebel/",
        "platform": "UNKNOWN",
        "project_url": "https://pypi.org/project/Hebel/",
        "project_urls": {
            "Download": "UNKNOWN",
            "Homepage": "https://github.com/hannes-brt/hebel"
        },
        "release_url": "https://pypi.org/project/Hebel/0.02.1/",
        "requires_dist": null,
        "requires_python": null,
        "summary": "GPU-Accelerated Deep Learning Library in Python",
        "version": "0.02.1"
    },
    "last_serial": 1101164,
    "releases": {
        "0.02.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "75ae526b858adfa9d5ad78a4ed0aeb21",
                    "sha256": "9aa2af25152628e1f845978fc4a96e46e3f78ed0e123ebd69e014da301bb3158"
                },
                "downloads": -1,
                "filename": "Hebel-0.02.1.tar.gz",
                "has_sig": false,
                "md5_digest": "75ae526b858adfa9d5ad78a4ed0aeb21",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 70688,
                "upload_time": "2014-05-22T15:49:50",
                "url": "https://files.pythonhosted.org/packages/c9/3c/7e494d8cf5169b77ab74361650255b827b55e5670684d86a48435de300ec/Hebel-0.02.1.tar.gz"
            }
        ],
        "0.03-dev": []
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "75ae526b858adfa9d5ad78a4ed0aeb21",
                "sha256": "9aa2af25152628e1f845978fc4a96e46e3f78ed0e123ebd69e014da301bb3158"
            },
            "downloads": -1,
            "filename": "Hebel-0.02.1.tar.gz",
            "has_sig": false,
            "md5_digest": "75ae526b858adfa9d5ad78a4ed0aeb21",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 70688,
            "upload_time": "2014-05-22T15:49:50",
            "url": "https://files.pythonhosted.org/packages/c9/3c/7e494d8cf5169b77ab74361650255b827b55e5670684d86a48435de300ec/Hebel-0.02.1.tar.gz"
        }
    ]
}