{
    "info": {
        "author": "Russi Chatterjee",
        "author_email": "root@ixaxaar.in",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.3",
            "Programming Language :: Python :: 3.4",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "# subtractive LSTM (subLSTM), for Pytorch\n\n[![Build Status](https://travis-ci.org/ixaxaar/pytorch-sublstm.svg?branch=master)](https://travis-ci.org/ixaxaar/pytorch-sublstm) [![PyPI version](https://badge.fury.io/py/pytorch-sublstm.svg)](https://badge.fury.io/py/pytorch-sublstm)\n\nThis is an implementation of subLSTM described in the paper [Cortical microcircuits as gated-recurrent neural networks, Rui Ponte Costa et al.](https://arxiv.org/abs/1711.02448)\n\n## Install\n\n```bash\npip install pytorch-sublstm\n```\n\n\n## Usage\n\n**Parameters**:\n\nFollowing are the constructor parameters:\n\n| Argument | Default | Description |\n| --- | --- | --- |\n| input_size | `None` | Size of the input vectors |\n| hidden_size | `None` | Size of hidden units |\n| num_layers | `1` | Number of layers in the network |\n| bias | `True` | Bias |\n| batch_first | `False` | Whether data is fed batch first |\n| dropout | `0` | Dropout between layers in the network |\n| bidirectional | `False` | If the network is bidirectional |\n\n\n### Example usage:\n\n#### nn Interface\n```python\nimport torch\nfrom torch.autograd import Variable\nfrom subLSTM.nn import SubLSTM\n\nhidden_size = 20\ninput_size = 10\nseq_len = 5\nbatch_size = 7\nhidden = None\n\ninput = Variable(torch.randn(batch_size, seq_len, input_size))\n\nrnn = SubLSTM(input_size, hidden_size, num_layers=2, bias=True, batch_first=True)\n\n# forward pass\noutput, hidden = rnn(input, hidden)\n```\n\n#### Cell Interface\n\n```python\nimport torch\nfrom torch.autograd import Variable\nfrom subLSTM.nn import SubLSTMCell\n\nhidden_size = 20\ninput_size = 10\nseq_len = 5\nbatch_size = 7\nhidden = None\n\nhx = Variable(torch.randn(batch_size, hidden_size))\ncx = Variable(torch.randn(batch_size, hidden_size))\n\ninput = Variable(torch.randn(batch_size, input_size))\n\ncell = SubLSTMCell(input_size, hidden_size, bias=True)\n(hx, cx) = cell(input, (hx, cx))\n```\n\n### Tasks:\n\nA language modeling task is included [here](./tasks/word_language_model/).\nRefer to its [README](./tasks/word_language_model/README.md) for more info.\n\n\n### Attributions:\n\nA lot of the code is recycled from [pytorch](https://pytorch.org)\n\n\n",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/ixaxaar/pytorch-sublstm",
        "keywords": "cortical microcircuit pytorch sublstm",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "pytorch-sublstm",
        "package_url": "https://pypi.org/project/pytorch-sublstm/",
        "platform": "",
        "project_url": "https://pypi.org/project/pytorch-sublstm/",
        "project_urls": {
            "Homepage": "https://github.com/ixaxaar/pytorch-sublstm"
        },
        "release_url": "https://pypi.org/project/pytorch-sublstm/0.0.2/",
        "requires_dist": [
            "numpy",
            "torch",
            "check-manifest; extra == 'dev'",
            "coverage; extra == 'test'"
        ],
        "requires_python": ">=3",
        "summary": "Differentiable Neural Computer, for Pytorch",
        "version": "0.0.2"
    },
    "last_serial": 3339331,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "6decbdc66eccab9af109d731c8e20182",
                    "sha256": "1e4b594e15d169e66cab09346dc7c9d08e19c0faac81f83f4d80b0e69e806092"
                },
                "downloads": -1,
                "filename": "pytorch_sublstm-0.0.1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "6decbdc66eccab9af109d731c8e20182",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3",
                "size": 8539,
                "upload_time": "2017-11-16T11:46:35",
                "url": "https://files.pythonhosted.org/packages/b4/54/7f39f3f2ce49158ab456b181039d4a3b51255ac4e74bf196bbebd537eb29/pytorch_sublstm-0.0.1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "39847113c703897e90e45a3f2ac0b7dd",
                    "sha256": "8e95c95a42d9269f8a680a70832db640ce41f6920c0b644dea12b7a6e613b665"
                },
                "downloads": -1,
                "filename": "pytorch-sublstm-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "39847113c703897e90e45a3f2ac0b7dd",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3",
                "size": 6097,
                "upload_time": "2017-11-16T11:46:36",
                "url": "https://files.pythonhosted.org/packages/c3/5e/bafa3725e6e6f1aa5721e17a3834b0a6f5082871da08cc95a02bcd55760e/pytorch-sublstm-0.0.1.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4a6608ceecc7eed496be3b634d7cda30",
                    "sha256": "d4aa45da82362f7907ab78f78211eca1101f8c7d88ccce63d4f47f2922e84c66"
                },
                "downloads": -1,
                "filename": "pytorch_sublstm-0.0.2-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "4a6608ceecc7eed496be3b634d7cda30",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3",
                "size": 8235,
                "upload_time": "2017-11-16T17:28:37",
                "url": "https://files.pythonhosted.org/packages/08/a5/59a7ff047c5fdaa38f7cc3dd2769a13b1be22661ac1d1c26ff86977c5052/pytorch_sublstm-0.0.2-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "dea087cdc44fe8b720f37d9e60ab015b",
                    "sha256": "cc87001bab328d50065b005e8ed7d972da68747718d1f803413ad5e4e1b0c970"
                },
                "downloads": -1,
                "filename": "pytorch-sublstm-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "dea087cdc44fe8b720f37d9e60ab015b",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3",
                "size": 5929,
                "upload_time": "2017-11-16T17:28:38",
                "url": "https://files.pythonhosted.org/packages/98/72/3265439b8fa84f4ad96f22b7a2387113f3baced1794b41db5dab77e7b06f/pytorch-sublstm-0.0.2.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "4a6608ceecc7eed496be3b634d7cda30",
                "sha256": "d4aa45da82362f7907ab78f78211eca1101f8c7d88ccce63d4f47f2922e84c66"
            },
            "downloads": -1,
            "filename": "pytorch_sublstm-0.0.2-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "4a6608ceecc7eed496be3b634d7cda30",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3",
            "size": 8235,
            "upload_time": "2017-11-16T17:28:37",
            "url": "https://files.pythonhosted.org/packages/08/a5/59a7ff047c5fdaa38f7cc3dd2769a13b1be22661ac1d1c26ff86977c5052/pytorch_sublstm-0.0.2-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "dea087cdc44fe8b720f37d9e60ab015b",
                "sha256": "cc87001bab328d50065b005e8ed7d972da68747718d1f803413ad5e4e1b0c970"
            },
            "downloads": -1,
            "filename": "pytorch-sublstm-0.0.2.tar.gz",
            "has_sig": false,
            "md5_digest": "dea087cdc44fe8b720f37d9e60ab015b",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3",
            "size": 5929,
            "upload_time": "2017-11-16T17:28:38",
            "url": "https://files.pythonhosted.org/packages/98/72/3265439b8fa84f4ad96f22b7a2387113f3baced1794b41db5dab77e7b06f/pytorch-sublstm-0.0.2.tar.gz"
        }
    ]
}