{
    "info": {
        "author": "Percy \"Thrills\" Thrillington",
        "author_email": "nicholdav@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: BSD License",
            "Programming Language :: Python",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: Implementation :: CPython"
        ],
        "description": "\n# Recurrent Models of Visual Attention\nReplication in Tensorflow of the following paper:  \nMnih, Volodymyr, Nicolas Heess, and Alex Graves.  \n\"Recurrent models of visual attention.\"  \nAdvances in neural information processing systems. 2014.  \n<https://papers.nips.cc/paper/5542-recurrent-models-of-visual-attention>\n\nBased in part on the following implementations:  \n- <https://github.com/torch/rnn/blob/master/examples/recurrent-visual-attention.lua>\n  + (license: <https://github.com/torch/rnn/blob/master/LICENSE.txt>) \n- <https://github.com/seann999/tensorflow_mnist_ram>  \n  + (MIT license: <https://github.com/seann999/tensorflow_mnist_ram/blob/master/LICENSE>)\n- <https://github.com/kevinzakka/recurrent-visual-attention>  \n\n## installation\n`$ pip install thrillington`  \n(`thrillington` because there is already a `ram` on PyPI, \nand because <https://en.wikipedia.org/wiki/Thrillington>)\n\n## usage\nThe library can be run from the command line with a config file.\n```\n$ ram train ./RAM_config-2018-10-21.ini\n\n...\n\n  0%|          | 0/10000 [00:00<?, ?it/s]\n\nconfig.train.resume is False,\nwill save new model and optimizer to checkpoint: /home/you/data/ram_output/results_20181021/checkpoints/ckpt\n\nEpoch: 1/200 - learning rate: 0.001000\n\n282.5s - hybrid loss: 1.690 - acc: 6.000: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 10000/10000 [04:42<00:00, 35.65it/s]\n  0%|          | 0/10000 [00:00<?, ?it/s]\n\nmean accuracy: 9.97\nmean losses: LossTuple(loss_reinforce=-1.1296023, loss_baseline=0.09972435, loss_action=2.3005059, loss_hybrid=1.2706277)\n\nEpoch: 2/200 - learning rate: 0.001000\n\n282.8s - hybrid loss: 1.223 - acc: 10.000: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 10000/10000 [04:42<00:00, 35.50it/s]\n  0%|          | 0/10000 [00:00<?, ?it/s]\n...\n```\n\nFor a detailed explanation of the config file format, please see [here](./doc/config.md)\n\n## CHANGELOG\nTo see past changes and work in progress, please check out the [CHANGELOG](./doc/CHANGELOG.md).\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/NickleDave/thrillington",
        "keywords": "",
        "license": "BSD",
        "maintainer": "",
        "maintainer_email": "",
        "name": "thrillington",
        "package_url": "https://pypi.org/project/thrillington/",
        "platform": "",
        "project_url": "https://pypi.org/project/thrillington/",
        "project_urls": {
            "Homepage": "https://github.com/NickleDave/thrillington"
        },
        "release_url": "https://pypi.org/project/thrillington/0.0.2a1/",
        "requires_dist": [
            "numpy",
            "tensorflow",
            "tqdm",
            "attrs"
        ],
        "requires_python": ">=3.6.0",
        "summary": "Replication of \"Recurrent models of visual attention\", Mnih et al. 2014",
        "version": "0.0.2a1"
    },
    "last_serial": 4777658,
    "releases": {
        "0.0.2a1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "34a99948292e25a7d9efc8464e7e8d87",
                    "sha256": "f9dd417d9df70a324b96e7d77b5c70248df0624496c7ea7637d4f34c65dc0fe9"
                },
                "downloads": -1,
                "filename": "thrillington-0.0.2a1-py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "34a99948292e25a7d9efc8464e7e8d87",
                "packagetype": "bdist_wheel",
                "python_version": "py3",
                "requires_python": ">=3.6.0",
                "size": 30965,
                "upload_time": "2019-02-04T13:24:18",
                "url": "https://files.pythonhosted.org/packages/d1/8f/9c5e0fab0a7ce3b869777d7dcdade4bb6280389d6339a0dfd4b8440e2a1a/thrillington-0.0.2a1-py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "3efdb3b695a36530afb3ae286d3bd277",
                    "sha256": "b97d40961ad2c03dda5176b34c5e8fb01ab5e06705e99b130c5666bdc5e15913"
                },
                "downloads": -1,
                "filename": "thrillington-0.0.2a1.tar.gz",
                "has_sig": false,
                "md5_digest": "3efdb3b695a36530afb3ae286d3bd277",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6.0",
                "size": 26859,
                "upload_time": "2019-02-04T13:24:20",
                "url": "https://files.pythonhosted.org/packages/9e/a4/b54c43e74a7ed1c0c1865bcfde360c5bb9dd9f99a81d97e76571f3a5e390/thrillington-0.0.2a1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "34a99948292e25a7d9efc8464e7e8d87",
                "sha256": "f9dd417d9df70a324b96e7d77b5c70248df0624496c7ea7637d4f34c65dc0fe9"
            },
            "downloads": -1,
            "filename": "thrillington-0.0.2a1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "34a99948292e25a7d9efc8464e7e8d87",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.6.0",
            "size": 30965,
            "upload_time": "2019-02-04T13:24:18",
            "url": "https://files.pythonhosted.org/packages/d1/8f/9c5e0fab0a7ce3b869777d7dcdade4bb6280389d6339a0dfd4b8440e2a1a/thrillington-0.0.2a1-py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "3efdb3b695a36530afb3ae286d3bd277",
                "sha256": "b97d40961ad2c03dda5176b34c5e8fb01ab5e06705e99b130c5666bdc5e15913"
            },
            "downloads": -1,
            "filename": "thrillington-0.0.2a1.tar.gz",
            "has_sig": false,
            "md5_digest": "3efdb3b695a36530afb3ae286d3bd277",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6.0",
            "size": 26859,
            "upload_time": "2019-02-04T13:24:20",
            "url": "https://files.pythonhosted.org/packages/9e/a4/b54c43e74a7ed1c0c1865bcfde360c5bb9dd9f99a81d97e76571f3a5e390/thrillington-0.0.2a1.tar.gz"
        }
    ]
}