{
    "info": {
        "author": "CyberZHG",
        "author_email": "CyberZHG@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: Other/Proprietary License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 2.7",
            "Programming Language :: Python :: 3.6"
        ],
        "description": "# MXNet Octave Conv\n\n[![Travis](https://travis-ci.org/CyberZHG/mxnet-octave-conv.svg)](https://travis-ci.org/CyberZHG/mxnet-octave-conv)\n[![Coverage](https://coveralls.io/repos/github/CyberZHG/mxnet-octave-conv/badge.svg?branch=master)](https://coveralls.io/github/CyberZHG/mxnet-octave-conv)\n[![996.ICU](https://img.shields.io/badge/license-Anti%20996-blue.svg)](https://996.icu) \n\nUnofficial implementation of [Drop an Octave: Reducing Spatial Redundancy in\nConvolutional Neural Networks with Octave Convolution](https://arxiv.org/pdf/1904.05049.pdf).\n\n## Install\n\n```bash\npip install mxnet-octave-conv\n```\n\n## Usage\n\n```python\nimport mxnet as mx\nfrom mxnet_octave_conv import octave_conv, octave_dual\n\nmx.symbol.Variable(name='data')\nconv = octave_conv(x, num_filter=7, kernel=(3, 3))\npool = octave_dual(conv, lambda data: mx.symbol.Pooling(data, kernel=(2, 2), stride=(2, 2), pool_type='max'))\nconv = octave_conv(pool, num_filter=5, kernel=3, stride=1, dilate=(2, 3), name='Mid')\npool = octave_dual(conv, lambda data: mx.symbol.Pooling(data, kernel=(2, 2), stride=(2, 2), pool_type='max'))\nconv = octave_conv(pool, num_filter=3, kernel=3, stride=(1, 1), dilate=1, ratio_out=0.0)\npool = octave_dual(conv, lambda data: mx.symbol.Pooling(data, kernel=(2, 2), stride=(2, 2), pool_type='max'))\nflatten = mx.symbol.Flatten(pool)\ndense = mx.symbol.FullyConnected(flatten, num_hidden=2)\nmodel = mx.symbol.SoftmaxOutput(dense, name='softmax')\nprint(mx.visualization.print_summary(model, shape={'data': (2, 3, 32, 32)}))\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/CyberZHG/mxnet-octave-conv",
        "keywords": "",
        "license": "Anti 996",
        "maintainer": "",
        "maintainer_email": "",
        "name": "mxnet-octave-conv",
        "package_url": "https://pypi.org/project/mxnet-octave-conv/",
        "platform": "",
        "project_url": "https://pypi.org/project/mxnet-octave-conv/",
        "project_urls": {
            "Homepage": "https://github.com/CyberZHG/mxnet-octave-conv"
        },
        "release_url": "https://pypi.org/project/mxnet-octave-conv/0.1.0/",
        "requires_dist": null,
        "requires_python": "",
        "summary": "Octave convolution",
        "version": "0.1.0"
    },
    "last_serial": 5164537,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "4668570982bf5e278da85ed654f46301",
                    "sha256": "cf971c94e90669f582e37024af16347492893321ad7c2da260bd2d48fd2050b1"
                },
                "downloads": -1,
                "filename": "mxnet-octave-conv-0.1.0.tar.gz",
                "has_sig": false,
                "md5_digest": "4668570982bf5e278da85ed654f46301",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 4959,
                "upload_time": "2019-04-19T11:36:16",
                "url": "https://files.pythonhosted.org/packages/bf/b9/37cbfcc147a7f9419e2734d322dc78edc59b96036aa0abffacb39ffea4ae/mxnet-octave-conv-0.1.0.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "4668570982bf5e278da85ed654f46301",
                "sha256": "cf971c94e90669f582e37024af16347492893321ad7c2da260bd2d48fd2050b1"
            },
            "downloads": -1,
            "filename": "mxnet-octave-conv-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "4668570982bf5e278da85ed654f46301",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 4959,
            "upload_time": "2019-04-19T11:36:16",
            "url": "https://files.pythonhosted.org/packages/bf/b9/37cbfcc147a7f9419e2734d322dc78edc59b96036aa0abffacb39ffea4ae/mxnet-octave-conv-0.1.0.tar.gz"
        }
    ]
}