{
    "info": {
        "author": "Andrew S. Champion",
        "author_email": "andrew.champion@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 2 - Pre-Alpha",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Natural Language :: English",
            "Programming Language :: Python :: 2",
            "Programming Language :: Python :: 2.7",
            "Topic :: Scientific/Engineering :: Bio-Informatics"
        ],
        "description": "===============================\ndiluvian\n===============================\n\n\nFlood filling networks for segmenting electron microscopy of neural tissue.\n\n==============  ===============\nPyPI Release    |pypi_badge|\nDocumentation   |docs_badge|\nLicense         |license_badge|\nBuild Status    |travis_badge|\n==============  ===============\n\nDiluvian is an implementation and extension of the flood-filling network (FFN)\nalgorithm first described in [Januszewski2016]_. Flood-filling works by\nstarting at a seed location known to lie inside a region of interest, using a\nconvolutional network to predict the extent of the region within a small\nfield of view around that seed location, and queuing up new field of view\nlocations along the boundary of the current field of view that are confidently\ninside the region. This process is repeated until the region has been fully\nexplored.\n\nAs of December 2017 the original paper's authors have released `their implementation <https://github.com/google/ffn>`_.\n\n\nQuick Start\n-----------\n\nThis assumes you already have CUDA installed and have created a fresh\nvirtualenv. See `installation documentation <https://diluvian.readthedocs.io/page/installation.html>`_\nfor detailed instructions.\n\nInstall diluvian and its dependencies into your virtualenv:\n\n.. code-block:: console\n\n   pip install diluvian\n\nFor compatibility diluvian only requires TensorFlow CPU by default, but you\nwill want to use TensorFlow GPU if you have installed CUDA:\n\n.. code-block:: console\n\n   pip install 'tensorflow-gpu==1.3.0'\n\nTo test that everything works train diluvian on three volumes from the\n`CREMI challenge <https://cremi.org>`_:\n\n.. code-block:: console\n\n   diluvian train\n\nThis will automatically download the CREMI datasets to your Keras cache. Only\ntwo epochs will run with a small sample set, so the trained model is not useful\nbut will verify Tensorflow is working correctly.\n\nTo train for longer, generate a diluvian config file:\n\n.. code-block:: console\n\n   diluvian check-config > myconfig.toml\n\nNow edit settings in the ``[training]`` section of ``myconfig.toml`` to your\nliking and begin the training again:\n\n.. code-block:: console\n\n   diluvian train -c myconfig.toml\n\nFor detailed command line instructions and usage from Python, see the\n`usage documentation <https://diluvian.readthedocs.io/page/usage.html>`_.\n\n\nLimitations, Differences, and Caveats\n-------------------------------------\n\nDiluvian may differ from the original FFN algorithm or make implementation\nchoices in ways pertinent to your use:\n\n* By default diluvian uses a U-Net architecture rather than stacked convolution\n  modules with skip links. The authors of the original FFN paper also now use\n  both architectures (personal communication). To use a different architecture,\n  change the ``factory`` setting in the ``[network]`` section of your config\n  file.\n* Rather than resampling training data based on the filling fraction\n  :math:`f_a`, sample loss is (optionally) weighted based on the filling\n  fraction.\n* A FOV center's priority in the move queue is determined by the checking\n  plane mask probability of the first move to queue it, rather than the\n  highest mask probability with which it is added to the queue.\n* Currently only processing of each FOV is done on the GPU, with movement\n  being processed on the CPU and requiring copying of FOV data to host and\n  back for each move.\n\n.. [Januszewski2016]\n   Micha\u0142 Januszewski, Jeremy Maitin-Shepard, Peter Li, Jorgen Kornfeld,\n   Winfried Denk, and Viren Jain.\n   Flood-filling networks. *arXiv preprint*\n   *arXiv:1611.00421*, 2016.\n\n.. |pypi_badge|\n        image:: https://img.shields.io/pypi/v/diluvian.svg\n        :target: https://pypi.python.org/pypi/diluvian\n        :alt: PyPI Package Version\n\n.. |travis_badge|\n        image:: https://img.shields.io/travis/aschampion/diluvian.svg\n        :target: https://travis-ci.org/aschampion/diluvian\n        :alt: Continuous Integration Status\n\n.. |docs_badge|\n        image:: https://readthedocs.org/projects/diluvian/badge/?version=latest\n        :target: https://diluvian.readthedocs.io/en/latest/?badge=latest\n        :alt: Documentation Status\n\n.. |license_badge|\n        image:: https://img.shields.io/badge/License-MIT-blue.svg\n        :target: https://opensource.org/licenses/MIT\n        :alt: License: MIT\n\n\n=======\nHistory\n=======\n\n0.0.6 (2018-02-13)\n------------------\n\n* Add CREMI evaluation command.\n* Add 3D region filling animation.\n* Fix region filling animations.\n* F_0.5 validation metrics.\n* Fix pip install.\n* Many other fixes and tweaks (see git log).\n\n\n0.0.5 (2017-10-03)\n------------------\n\n* Fix bug creating U-net with far too few channels.\n* Fix bug causing revisit of seed position.\n* Fix bug breaking sparse fill.\n\n\n0.0.4 (2017-10-02)\n------------------\n\n* Much faster, more reliable training and validation.\n* U-net supports valid padding mode and other features from original\n  specification.\n* Add artifact augmentation.\n* More efficient subvolume sampling.\n* Many other changes.\n\n\n0.0.3 (2017-06-04)\n------------------\n\n* Training now works in Python 3.\n* Multi-GPU filling: filling will now use the same number of processes and\n  GPUs specified by ``training.num_gpus``.\n\n\n0.0.2 (2017-05-22)\n------------------\n\n* Attempt to fix PyPI configuration file packaging.\n\n\n0.0.1 (2017-05-22)\n------------------\n\n* First release on PyPI.\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/aschampion/diluvian",
        "keywords": "diluvian",
        "license": "MIT license",
        "maintainer": "",
        "maintainer_email": "",
        "name": "diluvian",
        "package_url": "https://pypi.org/project/diluvian/",
        "platform": "",
        "project_url": "https://pypi.org/project/diluvian/",
        "project_urls": {
            "Homepage": "https://github.com/aschampion/diluvian"
        },
        "release_url": "https://pypi.org/project/diluvian/0.0.6/",
        "requires_dist": [
            "h5py (>=2.6.0)",
            "Keras (==2.0.8)",
            "keras-contrib",
            "matplotlib (==2.0.0)",
            "networkx (==1.11)",
            "neuroglancer (==0.0.8)",
            "numpy (==1.13.1)",
            "Pillow (==4.0.0)",
            "pytoml (==0.1.11)",
            "requests (==2.13.0)",
            "scikit-image (==0.13.0)",
            "scipy (==0.19.1)",
            "six (==1.10.0)",
            "tensorflow (==1.3.0)",
            "tqdm (==4.19.1)"
        ],
        "requires_python": "",
        "summary": "Flood filling networks for segmenting electron microscopy of neural tissue.",
        "version": "0.0.6"
    },
    "last_serial": 3579563,
    "releases": {
        "0.0.1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4973f6787e1ad00e333937ebeb93b086",
                    "sha256": "f68644f8b84111e16134caf7ea0b671b0158843ce32a9ce50a33524aab5c1908"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.1.tar.gz",
                "has_sig": false,
                "md5_digest": "4973f6787e1ad00e333937ebeb93b086",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 58127,
                "upload_time": "2017-05-22T18:33:48",
                "url": "https://files.pythonhosted.org/packages/23/a7/3b5e6b2fa4a28f7f3a5a143aa52ef4241c40d1e1d36d1b989db376934c2c/diluvian-0.0.1.tar.gz"
            }
        ],
        "0.0.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "97bd0d497710947e65f1be8cd431c3ff",
                    "sha256": "31e45f535d482f0d9daf4914509d278997855054b19687c691cc83ab2545c5fa"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.2-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "97bd0d497710947e65f1be8cd431c3ff",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 53105,
                "upload_time": "2017-05-22T19:23:12",
                "url": "https://files.pythonhosted.org/packages/3b/07/133a2109d8b21a26afc11bf56a22d6eee5b6e2a86e36b4550864a0e84da6/diluvian-0.0.2-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "f0359e64b92d53195d99004fe99ab7d6",
                    "sha256": "bf0dc33cda7d3919b543e10b7ada1794e55d457d3de154cb51a4f1333c20fa52"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.2.tar.gz",
                "has_sig": false,
                "md5_digest": "f0359e64b92d53195d99004fe99ab7d6",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 57822,
                "upload_time": "2017-05-22T19:23:14",
                "url": "https://files.pythonhosted.org/packages/c1/6e/394c1610fbaf13c150ac0b6a6be66f81b33917f1192e1763f76ebe9f2acf/diluvian-0.0.2.tar.gz"
            }
        ],
        "0.0.3": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "02e37576cafa84e3cc5b965415331379",
                    "sha256": "3949814b40eaec79602c223709c4f82eb6a995b470909acd41126cbdfae54ae1"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.3-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "02e37576cafa84e3cc5b965415331379",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 56656,
                "upload_time": "2017-06-04T18:23:18",
                "url": "https://files.pythonhosted.org/packages/ef/4d/b840ad7dc3978bcdce314004472656c4b388ce3d026c99fc5e7049d0e3e2/diluvian-0.0.3-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "e6a767e818b741bd959b8ad4e3ab2889",
                    "sha256": "ed75ee92d576ff20cbba797a8d5d4b7462ac080b7bd5d239b7e62994c52a163a"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.3.tar.gz",
                "has_sig": false,
                "md5_digest": "e6a767e818b741bd959b8ad4e3ab2889",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 60737,
                "upload_time": "2017-06-04T18:23:20",
                "url": "https://files.pythonhosted.org/packages/bc/5e/1d25dd8377c042b198ec72939f12bf9d591173f39d496d1a0a1dd848a12e/diluvian-0.0.3.tar.gz"
            }
        ],
        "0.0.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "eca1d6040ef91b500fa61c1b3f0902b7",
                    "sha256": "5cd2bf9617ec5fefd869276fc9d9217f8986e705a247eb3d1e6e2438d63695b0"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.4-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "eca1d6040ef91b500fa61c1b3f0902b7",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 64044,
                "upload_time": "2017-10-02T15:39:25",
                "url": "https://files.pythonhosted.org/packages/49/c7/f966c0a5c22eee3828859c117c804af99409ee2045245b70fb449ea2806f/diluvian-0.0.4-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "bb5c01b31a4f49d13a4e038b5c4bdcfb",
                    "sha256": "e37fe861e79b003303bb91d6417b56dfd6876f28110f2e62fd026db8e47e2dc0"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.4.tar.gz",
                "has_sig": false,
                "md5_digest": "bb5c01b31a4f49d13a4e038b5c4bdcfb",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 67911,
                "upload_time": "2017-10-02T15:39:29",
                "url": "https://files.pythonhosted.org/packages/de/a3/c6fb503771ad1c67bb85dcdd60001d0b98c754abeef92445a8b2b3e5bfcf/diluvian-0.0.4.tar.gz"
            }
        ],
        "0.0.5": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "b3fab8f8c16f7083c11319a5829618e4",
                    "sha256": "4de9fd8d063f5f6598ccf4bdc51be9b84b7ed0efdf2ef65836bd4ee44bdc9dc3"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.5-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "b3fab8f8c16f7083c11319a5829618e4",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 64221,
                "upload_time": "2017-10-03T20:34:49",
                "url": "https://files.pythonhosted.org/packages/a0/e1/a46fde63b346bdfab9e443e27f5d38e0bcd067bd4627ff921c777bee35fb/diluvian-0.0.5-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "ff5c79799424910164e5c4a2d482de31",
                    "sha256": "0157447abd6862c94c1e28e16ef981901188a870ac79c0b4d6b5f5c338af8015"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.5.tar.gz",
                "has_sig": false,
                "md5_digest": "ff5c79799424910164e5c4a2d482de31",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 68087,
                "upload_time": "2017-10-03T20:35:33",
                "url": "https://files.pythonhosted.org/packages/28/be/843b74f968104f70973719b99f796cd536b394f8d242cff031c579d267da/diluvian-0.0.5.tar.gz"
            }
        ],
        "0.0.6": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "d61e239fb995d84ae643fdfe85d11505",
                    "sha256": "9fc5441523d0ae4a4bfc81428e923af08cba9f22f7f609fbda8e7eacb80bcd0e"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.6-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "d61e239fb995d84ae643fdfe85d11505",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": null,
                "size": 70597,
                "upload_time": "2018-02-13T20:43:21",
                "url": "https://files.pythonhosted.org/packages/9c/fa/39e1bb0d7875b691d6031f5c89a11d5b3af75fa682859d9b52ec99106399/diluvian-0.0.6-py2.py3-none-any.whl"
            },
            {
                "comment_text": "",
                "digests": {
                    "md5": "37206e8ac0c4fb325a2239a06993d1d7",
                    "sha256": "79e71fab0ef44532c87a087e8604064f083737f304daef61afcc1165f68e4327"
                },
                "downloads": -1,
                "filename": "diluvian-0.0.6.tar.gz",
                "has_sig": false,
                "md5_digest": "37206e8ac0c4fb325a2239a06993d1d7",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 72941,
                "upload_time": "2018-02-13T20:43:23",
                "url": "https://files.pythonhosted.org/packages/67/2d/1653a7a2871be4a9c326386ee1592314b07911baccdc43ca5c2fd5a7b660/diluvian-0.0.6.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "d61e239fb995d84ae643fdfe85d11505",
                "sha256": "9fc5441523d0ae4a4bfc81428e923af08cba9f22f7f609fbda8e7eacb80bcd0e"
            },
            "downloads": -1,
            "filename": "diluvian-0.0.6-py2.py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "d61e239fb995d84ae643fdfe85d11505",
            "packagetype": "bdist_wheel",
            "python_version": "py2.py3",
            "requires_python": null,
            "size": 70597,
            "upload_time": "2018-02-13T20:43:21",
            "url": "https://files.pythonhosted.org/packages/9c/fa/39e1bb0d7875b691d6031f5c89a11d5b3af75fa682859d9b52ec99106399/diluvian-0.0.6-py2.py3-none-any.whl"
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "37206e8ac0c4fb325a2239a06993d1d7",
                "sha256": "79e71fab0ef44532c87a087e8604064f083737f304daef61afcc1165f68e4327"
            },
            "downloads": -1,
            "filename": "diluvian-0.0.6.tar.gz",
            "has_sig": false,
            "md5_digest": "37206e8ac0c4fb325a2239a06993d1d7",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 72941,
            "upload_time": "2018-02-13T20:43:23",
            "url": "https://files.pythonhosted.org/packages/67/2d/1653a7a2871be4a9c326386ee1592314b07911baccdc43ca5c2fd5a7b660/diluvian-0.0.6.tar.gz"
        }
    ]
}