{
    "info": {
        "author": "Somshubra Majumdar",
        "author_email": "titu1994@gmail.com",
        "bugtrack_url": null,
        "classifiers": [
            "License :: OSI Approved :: MIT License",
            "Operating System :: OS Independent",
            "Programming Language :: Python :: 3",
            "Programming Language :: Python :: 3.5",
            "Programming Language :: Python :: 3.6",
            "Programming Language :: Python :: 3.7",
            "Topic :: Software Development :: Libraries",
            "Topic :: Software Development :: Libraries :: Python Modules"
        ],
        "description": "\n# Keras MixNets: Mixed Depthwise Convolutional Kernels\nKeras Implementation of MixNets from the paper [MixNets: : Mixed Depthwise Convolution Kernels](https://arxiv.org/abs/1907.09595).\n\nCode ported from the official codebase [https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mixnet](https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mixnet)\n\n# Mixed Depthwise Convolutional Kernel\n\n<img src=\"https://github.com/titu1994/keras_mixnets/blob/master/images/MixedConv.png\" height=100% width=100%>\n\nFrom the above paper, a Mixed Convolution is a group of convolutions with varying filter sizes. The paper suggests that [3x3, 5x5, 7x7] can be used safely without any loss in performance (and possible increase in performance), while a 9x9 or 11x11 may degrade performance if used without proper architecture search.\n\n# Usage\n\nDue to the use of Model Subclassing, the keras model built **cannot* be deserialized using `load_model`. You must build the model each time. tf.keras supports writing Layers which have additional Layers within them, but as Keras itself does not support it yet, these models cannot be deserialized using `load_model`.\n\n```python\n\nfrom keras_mixnets import MixNetSmall  # Medium and Large can also be used\n\nmodel = MixNetSmall((224, 224, 3), include_top=True)\n```\n\n# Weights\n\nWeights for these models have not been ported yet from Tensorflow.\n\n# Requirements\n\n - Tensorflow 1.14+ (Not 2.x)\n - Keras 2.2.4+\n\n\n",
        "description_content_type": "text/markdown",
        "docs_url": null,
        "download_url": "https://github.com/titu1994/keras_mixnets",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/titu1994/keras_mixnets",
        "keywords": "",
        "license": "MIT",
        "maintainer": "",
        "maintainer_email": "",
        "name": "keras-mixnets",
        "package_url": "https://pypi.org/project/keras-mixnets/",
        "platform": "",
        "project_url": "https://pypi.org/project/keras-mixnets/",
        "project_urls": {
            "Download": "https://github.com/titu1994/keras_mixnets",
            "Homepage": "https://github.com/titu1994/keras_mixnets"
        },
        "release_url": "https://pypi.org/project/keras-mixnets/0.1.0/",
        "requires_dist": [
            "keras (>=2.2.4)",
            "scipy (>=1.1.0)",
            "scikit-learn (>=0.21.2)",
            "pytest; extra == 'test'",
            "pillow; extra == 'test'"
        ],
        "requires_python": ">=3.0.0",
        "summary": "Keras implementation of MixNets of any configuration.",
        "version": "0.1.0"
    },
    "last_serial": 5589508,
    "releases": {
        "0.1.0": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "f2f0cf4bc1422e851f5ce3af1f06a847",
                    "sha256": "9b67bd31a56a4a8b95da151f1e2791dc07ebc801231eb63fe3f4c6b95e8d3518"
                },
                "downloads": -1,
                "filename": "keras_mixnets-0.1.0-py2.py3-none-any.whl",
                "has_sig": false,
                "md5_digest": "f2f0cf4bc1422e851f5ce3af1f06a847",
                "packagetype": "bdist_wheel",
                "python_version": "py2.py3",
                "requires_python": ">=3.0.0",
                "size": 14115,
                "upload_time": "2019-07-26T15:18:44",
                "url": "https://files.pythonhosted.org/packages/51/e4/d653aad41c7b10cdeb0dd762d584cc8b5cdacbe71f4796e060661eac6518/keras_mixnets-0.1.0-py2.py3-none-any.whl"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "f2f0cf4bc1422e851f5ce3af1f06a847",
                "sha256": "9b67bd31a56a4a8b95da151f1e2791dc07ebc801231eb63fe3f4c6b95e8d3518"
            },
            "downloads": -1,
            "filename": "keras_mixnets-0.1.0-py2.py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "f2f0cf4bc1422e851f5ce3af1f06a847",
            "packagetype": "bdist_wheel",
            "python_version": "py2.py3",
            "requires_python": ">=3.0.0",
            "size": 14115,
            "upload_time": "2019-07-26T15:18:44",
            "url": "https://files.pythonhosted.org/packages/51/e4/d653aad41c7b10cdeb0dd762d584cc8b5cdacbe71f4796e060661eac6518/keras_mixnets-0.1.0-py2.py3-none-any.whl"
        }
    ]
}