{
"info": {
"author": "M. Jacquemont, T. Vuillaume, L. Antiga",
"author_email": "jacquemont@lapp.in2p3.fr",
"bugtrack_url": null,
"classifiers": [
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3"
],
"description": "Indexed Convolution\n===================\n\nThe indexed operations allow the user to perform convolution and pooling on non-Euclidian grids of data given that the neighbors pixels of each pixel is known and provided.\n\nIt gives an alternative to masking or resampling the data in order to apply standard Euclidian convolution.\nThis solution has been developed in order to apply convolutional neural networks to data from physics experiments that propose specific pixels arrangements.\n\nIt is used in the `GammaLearn project `_ for the Cherenkov Telescope Array.\n\n\nHere you will find the code for the indexed operations as well as applied examples. The current implementation has been done for pytorch.\n\n`Documentation may be found online. `_\n\n.. image:: https://travis-ci.org/IndexedConv/IndexedConv.svg?branch=master\n :target: https://travis-ci.org/IndexedConv/IndexedConv\n.. image:: https://readthedocs.org/projects/indexed-convolution/badge/?version=latest\n :target: https://indexed-convolution.readthedocs.io/en/latest/?badge=latest\n :alt: Documentation Status\n.. image:: https://anaconda.org/gammalearn/indexedconv/badges/installer/conda.svg\n :target: https://anaconda.org/gammalearn/indexedconv\n\nInstall\n=======\n\nInstall from IndexedConv folder:\n\n.. code-block:: bash\n\n python setup.py install\n\nInstall with pip:\n\n.. code-block:: bash\n\n pip install indexedconv\n\nInstall with conda:\n\nfirst add conda-forge channel for tensorboardX if needed\n\n.. code-block:: bash\n\n conda config --append channels conda-forge\n\n.. code-block:: bash\n\n conda install -c gammalearn indexedconv\n\n\nRequirements\n------------\n\n.. code-block:: bash\n\n \"torch>=0.4\",\n \"torchvision\",\n \"numpy\",\n \"tensorboardx\",\n \"matplotlib\",\n \"h5py\",\n \"sphinxcontrib-katex\"\n\n\nRunning an experiment\n=====================\nFor example, to train the network with indexed convolution on the CIFAR10 dataset transformed to hexagonal:\n\n.. code-block:: bash\n\n python examples/cifar_indexed.py main_folder data_folder experiment_name --hexa --batch 125 --epochs 300 --seeds 1 2 3 4 --device cpu\n\nIn order to train on the AID dataset, it must be downloaded and can be found `here `_.\n\nAuthors\n=======\n\nThe development of the indexed convolution is born from a collaboration between physicists and computer scientists.\n\n- Luca Antiga, Orobix\n- Mikael Jacquemont, LAPP (CNRS), LISTIC (USMB)\n- Thomas Vuillaume, LAPP (CNRS)\n\nReferences\n==========\nIf you want to use IndexedConv, please cite:\n\n.. image:: https://zenodo.org/badge/150430897.svg\n :target: https://zenodo.org/badge/latestdoi/150430897\n\nContributing\n============\n\nAll contributions are welcome. \n\nStart by contacting the authors, either directly by email or by creating a GitHub issue.\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/IndexedConv/IndexedConv",
"keywords": "",
"license": "MIT",
"maintainer": "",
"maintainer_email": "",
"name": "IndexedConv",
"package_url": "https://pypi.org/project/IndexedConv/",
"platform": "",
"project_url": "https://pypi.org/project/IndexedConv/",
"project_urls": {
"Homepage": "https://github.com/IndexedConv/IndexedConv"
},
"release_url": "https://pypi.org/project/IndexedConv/1.1/",
"requires_dist": [
"torch (>=0.4)",
"torchvision",
"numpy",
"tensorboardx",
"matplotlib",
"h5py",
"sphinxcontrib-katex"
],
"requires_python": "",
"summary": "An implementation of indexed convolution and pooling",
"version": "1.1"
},
"last_serial": 4707937,
"releases": {
"0.1.0a0": [
{
"comment_text": "",
"digests": {
"md5": "b38005b13cd6189346713897b5800ea1",
"sha256": "83167b886e4b94cd97a176805a2dfb1c177bba3602b6f6cb28621f9155701a0b"
},
"downloads": -1,
"filename": "IndexedConv-0.1.0a0-py3.6.egg",
"has_sig": false,
"md5_digest": "b38005b13cd6189346713897b5800ea1",
"packagetype": "bdist_egg",
"python_version": "3.6",
"requires_python": null,
"size": 34224,
"upload_time": "2018-11-21T13:24:03",
"url": "https://files.pythonhosted.org/packages/de/ed/d5f9ab9f4331ca949b4e765a515fdd52c1a65ab9edb622f993352d16d462/IndexedConv-0.1.0a0-py3.6.egg"
},
{
"comment_text": "",
"digests": {
"md5": "0c17891d01d4c80ae85ddc0ac4e6d913",
"sha256": "21add9b4acc9acfffe77eff76edaa39dd0dcc862528311707910ef2763f7f198"
},
"downloads": -1,
"filename": "IndexedConv-0.1.0a0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0c17891d01d4c80ae85ddc0ac4e6d913",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 15633,
"upload_time": "2018-11-21T13:24:00",
"url": "https://files.pythonhosted.org/packages/20/d0/706ff072da2d22754cfb762b81a309568567574c83dc7cc99f30b1b1e653/IndexedConv-0.1.0a0-py3-none-any.whl"
},
{
"comment_text": "",
"digests": {
"md5": "553dcb4f3ce1c2087f95e6447c516e66",
"sha256": "b05f0f26c11b22d7aa4ffe4fb309439a618acfb88b8730a9be70ca4f925c7958"
},
"downloads": -1,
"filename": "IndexedConv-0.1.0a0.tar.gz",
"has_sig": false,
"md5_digest": "553dcb4f3ce1c2087f95e6447c516e66",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 10984,
"upload_time": "2018-11-21T13:24:04",
"url": "https://files.pythonhosted.org/packages/cf/32/669ebd16b30405110fe8d0f5118491c70c36ea7b6269a93e3c866dd66e97/IndexedConv-0.1.0a0.tar.gz"
}
],
"1.0": [
{
"comment_text": "",
"digests": {
"md5": "1ab75e6ddbecf3acbb32fe2c56ea24bd",
"sha256": "79263f6632ffb4cf66a2c97e12bc3e44bc7a5bd8a50b8885e1780f30783ef45f"
},
"downloads": -1,
"filename": "IndexedConv-1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1ab75e6ddbecf3acbb32fe2c56ea24bd",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 16524,
"upload_time": "2019-01-08T14:19:24",
"url": "https://files.pythonhosted.org/packages/85/db/a74362c2340d26ac1274509abf4632822b35507fd30fd581b0ddcdc40ed2/IndexedConv-1.0-py3-none-any.whl"
}
],
"1.1": [
{
"comment_text": "",
"digests": {
"md5": "7ef632869e164b4ec03d664484563b56",
"sha256": "270944c3ddbbcdac6872d9b4acfce7cea138074847b52b5233b5f4e498dd977c"
},
"downloads": -1,
"filename": "IndexedConv-1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7ef632869e164b4ec03d664484563b56",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 16662,
"upload_time": "2019-01-17T13:09:49",
"url": "https://files.pythonhosted.org/packages/b4/f8/8a3c3585b3f773aca3d3dd238b0ac02e4222e3983997f54f795691c0e7ff/IndexedConv-1.1-py3-none-any.whl"
}
]
},
"urls": [
{
"comment_text": "",
"digests": {
"md5": "7ef632869e164b4ec03d664484563b56",
"sha256": "270944c3ddbbcdac6872d9b4acfce7cea138074847b52b5233b5f4e498dd977c"
},
"downloads": -1,
"filename": "IndexedConv-1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7ef632869e164b4ec03d664484563b56",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 16662,
"upload_time": "2019-01-17T13:09:49",
"url": "https://files.pythonhosted.org/packages/b4/f8/8a3c3585b3f773aca3d3dd238b0ac02e4222e3983997f54f795691c0e7ff/IndexedConv-1.1-py3-none-any.whl"
}
]
}