{ "info": { "author": "pracheer", "author_email": "pracheer_gupta@hotmail.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 4 - Beta", "Intended Audience :: Developers", "License :: OSI Approved :: Apache Software License", "Operating System :: MacOS :: MacOS X", "Programming Language :: Python :: 2.7", "Topic :: Software Development :: Libraries :: Python Modules" ], "description": "MXNET -> CoreML Converter\n=========================\n\n`Apache MXNet `_ (incubating) is a deep learning framework designed for both efficiency and flexibility. It allows you to mix `symbolic and imperative programming `_ to maximize efficiency and productivity. At its core, MXNet contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations on the fly. A graph optimization layer on top of that makes symbolic execution fast and memory efficient. MXNet is portable and lightweight, scaling effectively to multiple GPUs and multiple machines.\n\n`Core ML `_ is an Apple framework which allows developers to simply and easily integrate machine learning (ML) models into apps running on Apple devices (including iOS, watchOS, macOS, and tvOS). Core ML introduces a public file format (.mlmodel) for a broad set of ML methods including deep neural networks (both convolutional and recurrent), tree ensembles with boosting, and generalized linear models. Models in this format can be directly integrated into apps through Xcode.\n\nThis tool helps convert `MXNet models `_ into `Apple CoreML `_ format which can then be run on Apple devices. You can find more information about this tool on our `github `_ page.\n\nPrerequisites\n-------------\nThis package can only be installed on MacOS X since it relies on Apple's CoreML SDK. It can be run on MacOS 10.11 or higher though for running inferences on the converted model MacOS 10.13 or higher is needed (or for phones, iOS 11 or above).\n\nInstallation\n------------\nThe method for installing this tool follows the `standard python package installation steps `_. Once you have set up a python environment, run::\n\n pip install mxnet-to-coreml\n\nThe package `documentation `_ contains more details on how to use coremltools.\n\nDependencies\n------------\nThis tool has the following dependencies:\n\n* mxnet (0.10.0+)\n* coremltools (0.5.1+)\n* pyyaml (3.12+)\n\nSample Usage\n------------\n\nIn order to convert, say a `Squeezenet model `_, with labels from `synset.txt `_, execute this ::\n\n mxnet_coreml_converter.py --model-prefix='squeezenet_v1.1' \\\n --epoch=0 --input-shape='{\"data\":\"3,227,227\"}' \\\n --mode=classifier --pre-processing-arguments='{\"image_input_names\":\"data\"}' \\\n --class-labels synset.txt --output-file=\"squeezenetv11.mlmodel\"\n\nMore Information\n----------------\n* `On Github `_\n* `MXNet framework `_\n* `Apple CoreML `_\n\n\n", "description_content_type": "", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/apache/incubator-mxnet/tree/master/tools/coreml", "keywords": "Apache MXNet Apple CoreML Converter Deep Learning", "license": "Apache 2.0", "maintainer": "", "maintainer_email": "", "name": "mxnet-to-coreml", "package_url": "https://pypi.org/project/mxnet-to-coreml/", "platform": "", "project_url": "https://pypi.org/project/mxnet-to-coreml/", "project_urls": { "Homepage": "https://github.com/apache/incubator-mxnet/tree/master/tools/coreml" }, "release_url": "https://pypi.org/project/mxnet-to-coreml/0.1.3/", "requires_dist": [ "mxnet", "coremltools", "pyyaml" ], "requires_python": "~=2.7", "summary": "Tool to convert MXNet models into Apple CoreML model format.", "version": "0.1.3" }, "last_serial": 4075137, "releases": { "0.1.0": [ { "comment_text": "", "digests": { "md5": "71f2ea93659e35a899ba527145afb780", "sha256": "6a752eaa443c82ab69ae1a17842fd5c3692f2d8ead8c4c905684e7c4d8748324" }, "downloads": -1, "filename": "mxnet_to_coreml-0.1.0-cp27-cp27m-macosx_10_12_x86_64.whl", "has_sig": false, "md5_digest": "71f2ea93659e35a899ba527145afb780", "packagetype": "bdist_wheel", "python_version": "cp27", "requires_python": "~=2.7", "size": 16114, "upload_time": "2018-07-17T19:45:06", "url": "https://files.pythonhosted.org/packages/8a/5f/f07ef447c8bdbe6438dd459b00c12cbaf797b3ad4205373a1dd7092150a0/mxnet_to_coreml-0.1.0-cp27-cp27m-macosx_10_12_x86_64.whl" }, { "comment_text": "", "digests": { "md5": "b2bdd34cef566a77f8a422cce1ae97f7", "sha256": "a87a7c2b4f296a293d3e5df69407706ae26d8830300c0c017b9f275a92120f4e" }, "downloads": -1, "filename": "mxnet_to_coreml-0.1.0-cp27-cp27m-macosx_10_7_x86_64.whl", "has_sig": false, "md5_digest": "b2bdd34cef566a77f8a422cce1ae97f7", "packagetype": "bdist_wheel", "python_version": "cp27", "requires_python": "~=2.7", "size": 18138, "upload_time": "2017-08-25T23:05:20", "url": "https://files.pythonhosted.org/packages/10/0c/722a90bba70ff6349603174f90b5340729976d0e6ba8d143987109c38a73/mxnet_to_coreml-0.1.0-cp27-cp27m-macosx_10_7_x86_64.whl" } ], "0.1.1": [ { "comment_text": "", "digests": { "md5": "ed734fbd8fe25d3dc4f13af6625d2c0e", "sha256": "df94bb6ec0aad4df7db82701b612a83d19bd9a6ea3dc7ad9ef5076ee85fe6b37" }, "downloads": -1, "filename": "mxnet_to_coreml-0.1.1-cp27-cp27m-macosx_10_7_x86_64.whl", "has_sig": false, "md5_digest": "ed734fbd8fe25d3dc4f13af6625d2c0e", "packagetype": "bdist_wheel", "python_version": "cp27", "requires_python": "~=2.7", "size": 18139, "upload_time": "2017-08-29T23:34:53", "url": "https://files.pythonhosted.org/packages/42/eb/d5b1849386265231c08453640ef63b1da14b6a81fc858f19ed37f5fbbd5e/mxnet_to_coreml-0.1.1-cp27-cp27m-macosx_10_7_x86_64.whl" } ], "0.1.2": [ { "comment_text": "", "digests": { "md5": "04a776c738b7feee11a7f23c6f82fcb5", "sha256": "dc0d6c1e7df1c7ec809020004e240c68563e3321635b25a95a7cbeabd2f89bae" }, "downloads": -1, "filename": "mxnet_to_coreml-0.1.2-cp27-cp27m-macosx_10_7_x86_64.whl", "has_sig": false, "md5_digest": "04a776c738b7feee11a7f23c6f82fcb5", "packagetype": "bdist_wheel", "python_version": "cp27", "requires_python": "~=2.7", "size": 18267, "upload_time": "2017-09-06T19:31:24", "url": "https://files.pythonhosted.org/packages/34/6f/d263d4802d0f422d849c350a47624a78ac996e7231d30eb65437fff806ab/mxnet_to_coreml-0.1.2-cp27-cp27m-macosx_10_7_x86_64.whl" } ], "0.1.3": [ { "comment_text": "", "digests": { "md5": "6e799648dd08e97716c6aebd20830909", "sha256": "ba4ff072520f3347ed9194155b305dccfd3dd6df9aa335ba9e8f84eb80344f90" }, "downloads": -1, "filename": "mxnet_to_coreml-0.1.3-cp27-cp27m-macosx_10_12_x86_64.whl", "has_sig": false, "md5_digest": "6e799648dd08e97716c6aebd20830909", "packagetype": "bdist_wheel", "python_version": "cp27", "requires_python": "~=2.7", "size": 16113, "upload_time": "2018-07-17T19:45:08", "url": "https://files.pythonhosted.org/packages/da/fe/c12fb2962e8a5673bb490adc85f87166adaf8d6a7a7c947394792124c8df/mxnet_to_coreml-0.1.3-cp27-cp27m-macosx_10_12_x86_64.whl" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "6e799648dd08e97716c6aebd20830909", "sha256": "ba4ff072520f3347ed9194155b305dccfd3dd6df9aa335ba9e8f84eb80344f90" }, "downloads": -1, "filename": "mxnet_to_coreml-0.1.3-cp27-cp27m-macosx_10_12_x86_64.whl", "has_sig": false, "md5_digest": "6e799648dd08e97716c6aebd20830909", "packagetype": "bdist_wheel", "python_version": "cp27", "requires_python": "~=2.7", "size": 16113, "upload_time": "2018-07-17T19:45:08", "url": "https://files.pythonhosted.org/packages/da/fe/c12fb2962e8a5673bb490adc85f87166adaf8d6a7a7c947394792124c8df/mxnet_to_coreml-0.1.3-cp27-cp27m-macosx_10_12_x86_64.whl" } ] }