{
    "info": {
        "author": "",
        "author_email": "",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Education",
            "Intended Audience :: Science/Research",
            "License :: OSI Approved :: MIT License",
            "Natural Language :: English",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: 3.7",
            "Programming Language :: Python :: 3 :: Only",
            "Topic :: Documentation :: Sphinx",
            "Topic :: Scientific/Engineering :: Artificial Intelligence",
            "Topic :: Scientific/Engineering :: Mathematics",
            "Topic :: Software Development :: Libraries",
            "Topic :: Software Development :: Libraries :: Python Modules"
        ],
        "description": "# Complex-Valued Neural Networks in Keras with Tensorflow\n[![Documentation](https://readthedocs.org/projects/keras-complex/badge/?version=latest)](https://readthedocs.org/projects/keras-complex/badge/?version=latest) [![PyPI Status](https://img.shields.io/pypi/status/keras-complex.svg)](https://pypi.python.org/pypi/keras-complex) [![PyPI Versions](https://img.shields.io/pypi/pyversions/keras-complex.svg)](https://pypi.python.org/pypi/keras-complex) [![Build Status](https://travis-ci.org/JesperDramsch/keras-complex.svg?branch=master)](https://travis-ci.org/JesperDramsch/keras-complex) [![PyPI License](https://img.shields.io/pypi/l/keras-complex.svg)](LICENSCE.md)\n\n\n\n\n\n\n\n[Complex-valued convolutions](https://en.wikipedia.org/wiki/Convolution#Domain_of_definition) could provide some interesting results in signal processing-based deep learning. A simple(-ish) idea is including explicit phase information of time series in neural networks. This code enables complex-valued convolution in convolutional neural networks in [keras](https://keras.io) with the [TensorFlow](https://tensorflow.org/) backend. This makes the network modular and interoperable with standard keras layers and operations.\n\nThis code is very much in **Alpha**. Please consider helping out improving the code to advance together. This repository is based on the code which reproduces experiments presented in the paper [Deep Complex Networks](https://arxiv.org/abs/1705.09792). It is a port to Keras with Tensorflow-backend.\n\nRequirements\n------------\n\n- numpy\n- scipy\n- scikit-learn\n- keras\n- tensorflow 1.X or tensorflow-gpu 1.X\n\nInstall requirements for computer vision experiments with pip:\n```\npip install -f requirements.txt\n```\n\nFor the non-gpu version:\n```\npip install -f requirements-nogpu.txt\n```\n\nDepending on your Python installation you might want to use anaconda or other tools.\n\n\nInstallation\n------------\n\n```\npip install keras-complex\n```\nand\n```\npip install tensorflow-gpu\n```\n\nUsage\n-----\nBuild your neural networks with the help of keras. \n\n```python\nimport complexnn\n\nimport keras\nfrom keras import models\nfrom keras import layers\nfrom keras import optimizers\n\nmodel = models.Sequential()\n\nmodel.add(complexnn.conv.ComplexConv2D(32, (3, 3), activation='modrelu', padding='same', input_shape=input_shape))\nmodel.add(complexnn.bn.ComplexBatchNormalization())\nmodel.add(layers.MaxPooling2D((2, 2), padding='same'))\n\nmodel.compile(optimizer=optimizers.Adam(), loss='mse')\n\n```\n\n\nCitation\n--------\n\nPlease cite the original work as: \n\n```\n@ARTICLE {Trabelsi2017,\n    author  = \"Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk, Sandeep Subramanian, Jo\u00e3o Felipe Santos, Soroush Mehri, Negar Rostamzadeh, Yoshua Bengio, Christopher J Pal\",\n    title   = \"Deep Complex Networks\",\n    journal = \"arXiv preprint arXiv:1705.09792\",\n    year    = \"2017\"\n}\n```\n\nCite this software version as:\n```\n@misc{dramsch2019complex, \n    title     = {Complex-Valued Neural Networks in Keras with Tensorflow}, \n    url       = {https://figshare.com/articles/Complex-Valued_Neural_Networks_in_Keras_with_Tensorflow/9783773/1}, \n    DOI       = {10.6084/m9.figshare.9783773}, \n    publisher = {figshare}, \n    author    = author={Dramsch, Jesper S{\\\"o}ren and Contributors}, \n    year      = {2019}\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/JesperDramsch/keras-complex",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-complex",
        "package_url": "https://pypi.org/project/keras-complex/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-complex/",
        "project_urls": {
            "Homepage": "https://github.com/JesperDramsch/keras-complex"
        },
        "release_url": "https://pypi.org/project/keras-complex/0.1.2/",
        "requires_dist": null,
        "requires_python": ">=3.6",
        "summary": "Complex values in Keras - Deep learning for humans",
        "version": "0.1.2"
    },
    "last_serial": 5974412,
    "releases": {
        "0.1.2": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "3d20982ae1556a9f1a9ccfd52cc1f074",
                    "sha256": "a796a13aab2f1b25475a633491e9274f0f2a7745666ef1346e6060c2f9108f40"
                },
                "downloads": -1,
                "filename": "keras-complex-0.1.2.tar.gz",
                "has_sig": false,
                "md5_digest": "3d20982ae1556a9f1a9ccfd52cc1f074",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": ">=3.6",
                "size": 31475,
                "upload_time": "2019-10-15T02:15:32",
                "url": "https://files.pythonhosted.org/packages/d4/29/36ba6abad5bc722ff36a4b2dacf688e5bbf2d6f2e408a380cc113a715d54/keras-complex-0.1.2.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "3d20982ae1556a9f1a9ccfd52cc1f074",
                "sha256": "a796a13aab2f1b25475a633491e9274f0f2a7745666ef1346e6060c2f9108f40"
            },
            "downloads": -1,
            "filename": "keras-complex-0.1.2.tar.gz",
            "has_sig": false,
            "md5_digest": "3d20982ae1556a9f1a9ccfd52cc1f074",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.6",
            "size": 31475,
            "upload_time": "2019-10-15T02:15:32",
            "url": "https://files.pythonhosted.org/packages/d4/29/36ba6abad5bc722ff36a4b2dacf688e5bbf2d6f2e408a380cc113a715d54/keras-complex-0.1.2.tar.gz"
        }
    ]
}