{
    "info": {
        "author": "OCI ML Team",
        "author_email": "vish.ishaya@oracle.com",
        "bugtrack_url": null,
        "classifiers": [],
        "description": "# GraphPipe helpers for TensorFlow\n\nThis package contains helpers and examples for using GraphPipe with tensorflow.\nIt contains a new plug-in operation for tensorflow that makes a call to a\nGraphPipe remote model from within a local tensorflow graph.  The new operation\nis called remote_op and communicates with the remote model using libcurl and\nthe GraphPipe protocol.\n\nAdditionaly, a new keras layer is included based on the remote operation.  This\nallows you to include a layer in a keras model that makes a remote call.\n\nFinally, various examples are included of serving tensorflow models in python.\nFor production, a more performant server like\n[`graphpipe-tf`](https://github.com/oracle/graphpipe-go/cmd/graphpipe-tf) is\nrecommended, but the python server is useful for experimentation.\n\n## List Of Examples\n\n * [Jupyter Notebook: serving and querying VGG with\n   GraphPipe](examples/RemoteModelWithGraphPipe.ipynb)\n * [Complete client/server example](examples/simple_request.py)\n * [Simple tensorflow model server](examples/model_server.py)\n * [Keras to GraphDef](examples/convert.py)\n * [Using a remote operation](examples/call_remote_op.py)\n * [Tensorflow graph to GraphDef](examples/tf_graph.py)\n\n## Build\n\nBuilding manually requires a few libraries to be installed, but the Makefile\nwill happily run a build for you in a docker container.\n```\n  make build\n```\n\nSee `build_linux.sh` for the additional headers besides libcurl that you will\nneed to build the C library. (From tensorflow and flatbuffers)\n\nIf you've successfully built the C library, to build installation packages:\n\n    python setup.py bdist_wheel\n\nNote that these are not manylinux wheels and depend on libcurl being installed\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://oracle.github.io/graphpipe",
        "keywords": "",
        "license": "",
        "maintainer": "",
        "maintainer_email": "",
        "name": "graphpipe-tf",
        "package_url": "https://pypi.org/project/graphpipe-tf/",
        "platform": "",
        "project_url": "https://pypi.org/project/graphpipe-tf/",
        "project_urls": {
            "Homepage": "https://oracle.github.io/graphpipe"
        },
        "release_url": "https://pypi.org/project/graphpipe-tf/1.0.4/",
        "requires_dist": [
            "numpy (>=1.13.3)",
            "requests (==2.18.4)",
            "tensorflow (>=1.4.0)",
            "graphpipe (>=1.0.1)",
            "flatbuffers (==1.9.0)"
        ],
        "requires_python": "",
        "summary": "Graphpipe helpers for TensorFlow remote ops",
        "version": "1.0.4"
    },
    "last_serial": 4174551,
    "releases": {
        "1.0.4": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "5c35a2ff7c914a5d2718c07152cd4dc8",
                    "sha256": "4443ab6f0ccab810301ea9715bc8d6b3fcfcceec24c87138edb78217c1ac5367"
                },
                "downloads": -1,
                "filename": "graphpipe_tf-1.0.4-cp36-cp36m-macosx_10_11_x86_64.whl",
                "has_sig": false,
                "md5_digest": "5c35a2ff7c914a5d2718c07152cd4dc8",
                "packagetype": "bdist_wheel",
                "python_version": "cp36",
                "requires_python": null,
                "size": 24232,
                "upload_time": "2018-08-15T21:33:01",
                "url": "https://files.pythonhosted.org/packages/d3/b1/c1a7a218ffd7dedb2cb049019452cc8316962928170bbcb7cdfb15aa443c/graphpipe_tf-1.0.4-cp36-cp36m-macosx_10_11_x86_64.whl"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "5c35a2ff7c914a5d2718c07152cd4dc8",
                "sha256": "4443ab6f0ccab810301ea9715bc8d6b3fcfcceec24c87138edb78217c1ac5367"
            },
            "downloads": -1,
            "filename": "graphpipe_tf-1.0.4-cp36-cp36m-macosx_10_11_x86_64.whl",
            "has_sig": false,
            "md5_digest": "5c35a2ff7c914a5d2718c07152cd4dc8",
            "packagetype": "bdist_wheel",
            "python_version": "cp36",
            "requires_python": null,
            "size": 24232,
            "upload_time": "2018-08-15T21:33:01",
            "url": "https://files.pythonhosted.org/packages/d3/b1/c1a7a218ffd7dedb2cb049019452cc8316962928170bbcb7cdfb15aa443c/graphpipe_tf-1.0.4-cp36-cp36m-macosx_10_11_x86_64.whl"
        }
    ]
}