{ "info": { "author": "ONNX-CoreML Team", "author_email": "onnx-coreml@apple.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 5 - Production/Stable", "Intended Audience :: Developers", "Intended Audience :: End Users/Desktop", "License :: OSI Approved :: MIT License", "Operating System :: MacOS :: MacOS X", "Programming Language :: Python", "Topic :: Scientific/Engineering", "Topic :: Software Development" ], "description": "# Convert ONNX models into Apple Core ML format.\n\n[![Build Status](https://travis-ci.org/onnx/onnx-coreml.svg?branch=master)](https://travis-ci.org/onnx/onnx-coreml)\n\nThis tool converts [ONNX](https://onnx.ai/) models to Apple Core ML format. To convert Core ML models to ONNX, use [ONNXMLTools](https://github.com/onnx/onnxmltools).\n\nThere's a comprehensive [Tutorial](https://github.com/onnx/tutorials/tree/master/examples/CoreML/ONNXLive/README.md) showing how to convert PyTorch style transfer models through ONNX to Core ML models and run them in an iOS app.\n\n## [New] Beta onnx-coreml converter with Core ML 3\n\nTo try out the new beta converter with Core ML 3 (>= iOS 13, >= macOS 15),\ninstall coremltools 3.0b6 and coremltools 1.0b3\n\n```shell\npip install coremltools==3.0b6\npip install onnx-coreml==1.0b3\n```\n\nIn beta 3, the flag `disable_coreml_rank5_mapping` (which was part of beta 2) has been removed and instead replaced by\nthe generic argument `target_ios` which can be used to target different versions of Core ML/iOS.\nThe argument `target_ios` takes a string specifying the target deployment iOS version e.g. '11.2', '12' and '13'.\nBy default, the converter uses the value of '12'.\n\nFor example:\n\n```python\nfrom onnx_coreml import convert\nml_model = convert(model='my_model.onnx', target_ios='13') # to use Core ML 3\n```\n\n## Installation\n\n### Install From PyPI\n\n```bash\npip install -U onnx-coreml\n```\n\n### Install From Source\n\nTo get the latest version of the converter, install from source by cloning the repository along with its submodules and running the install.sh script. That is,\n\n```bash\ngit clone --recursive https://github.com/onnx/onnx-coreml.git\ncd onnx-coreml\n./install.sh\n```\n\n### Install From Source (for contributors)\n\nTo get the latest version of the converter, install from source by cloning the repository along with its submodules and running the install-develop.sh script. That is,\n\n```bash\ngit clone --recursive https://github.com/onnx/onnx-coreml.git\ncd onnx-coreml\n./install-develop.sh\n```\n\n## Dependencies\n\n* click\n* numpy\n* coremltools (3.0+)\n* onnx (1.5.0+)\n\n## How to Use\n\nTo convert models use single function `convert` from onnx_coreml:\n\n```python\nfrom onnx_coreml import convert\n```\n\n```python\ndef convert(model,\n mode=None,\n image_input_names=[],\n preprocessing_args={},\n image_output_names=[],\n deprocessing_args={},\n class_labels=None,\n predicted_feature_name='classLabel',\n add_custom_layers=False,\n custom_conversion_functions={},\n target_ios='12')\n```\n\nThe function returns a Core ML model instance that can be saved to a `.mlmodel` file, e.g.:\n\n```python\nmlmodel = convert(onnx_model)\nmlmodel.save('model.mlmodel')\n```\n\nCore ML model spec can be obtained from the model instance, which can be used to update model properties such as output names, input names etc. For e.g.:\n\n```python\nimport coremltools\nfrom coremltools.models import MLModel\n\nspec = mlmodel.get_spec()\nnew_mlmodel = MLModel(spec)\ncoremltools.utils.rename_feature(spec, 'old_output_name', 'new_output_name')\ncoremltools.utils.save_spec(spec, 'model_new_output_name.mlmodel')\n```\n\nFor more details see coremltools [documentation](https://apple.github.io/coremltools/#).\n\n### Parameters\n\n```\n__model__: ONNX model | str\n An ONNX model with parameters loaded in onnx package or path to file\n with models.\n\n__mode__: str ('classifier', 'regressor' or None)\n Mode of the converted coreml model:\n 'classifier', a NeuralNetworkClassifier spec will be constructed.\n 'regressor', a NeuralNetworkRegressor spec will be constructed.\n\n__image_input_names__: list of strings\n Name of the inputs to be defined as image type. Otherwise, by default all inputs are MultiArray type.\n\n__preprocessing_args__: dict\n Specify preprocessing parameters, that are be applied to all the image inputs specified through the \"image_input_names\" parameter.\n 'is_bgr', 'red_bias', 'green_bias', 'blue_bias', 'gray_bias',\n 'image_scale' keys with the same meaning as\n\nhttps://apple.github.io/coremltools/generated/coremltools.models.neural_network.html#coremltools.models.neural_network.NeuralNetworkBuilder.set_pre_processing_parameters\n\n__image_output_names__: list of strings\n Name of the outputs to be defined as image type. Otherwise, by default all outputs are MultiArray type.\n\n__deprocessing_args__: dict\n Same as 'preprocessing_args' but for the outputs.\n\n__class_labels__: A string or list of strings.\n As a string it represents the name of the file which contains\n the classification labels (one per line).\n As a list of strings it represents a list of categories that map\n the index of the output of a neural network to labels in a classifier.\n\n__predicted_feature_name__: str\n Name of the output feature for the class labels exposed in the Core ML\n model (applies to classifiers only). Defaults to 'classLabel'\n\n__add_custom_layers__: bool\n\t If True, then ['custom'](https://developer.apple.com/documentation/coreml/core_ml_api/integrating_custom_layers?language=objc) layers will be added to the model in place of unsupported onnx ops or for the ops\n\t that have unsupported attributes.\n\t Parameters for these custom layers should be filled manually by editing the mlmodel\n\t or the 'custom_conversion_functions' argument can be used to do the same during the process of conversion\n\n__custom_conversion_fuctions__: dict (str: function)\n\t Specify custom function to be used for conversion for given op.\n User can override existing conversion function and provide their own custom implementation to convert certain ops.\n Dictionary key must be string specifying ONNX Op name or Op type and value must be a function implementation available in current context.\n Example usage: {'Flatten': custom_flatten_converter, 'Exp': exp_converter}\n `custom_flatten_converter()` and `exp_converter()` will be invoked instead of internal onnx-coreml conversion implementation for these two Ops;\n Hence, User must provide implementation for functions specified in the dictionary. If user provides two separate functions for node name and node type, then custom function tied to node name will be used. As, function tied to node type is more generic than one tied to node name.\n `custom_conversion_functions` option is different than `add_custom_layers`. Both options can be used in conjuction in which case, custom function will be invoked for provided ops and custom layer will be added for ops with no respective conversion function.\n This option gives finer control to user. One use case could be to modify input attributes or certain graph properties before calling\n existing onnx-coreml conversion function. Note that, It is custom conversion function's responsibility to add respective Core ML layer into builder(coreml tools's NeuralNetworkBuilder).\n Examples: https://github.com/onnx/onnx-coreml/blob/master/tests/custom_layers_test.py#L43\n\n__onnx_coreml_input_shape_map__: dict (str: List[int])\n (Optional)\n (only used if `target_ios` version is less than '13')\n A dictionary with keys corresponding to the model input names. Values are a list of integers that specify\n how the shape of the input is mapped to Core ML. Convention used for Core ML shapes is:\n 0: Sequence, 1: Batch, 2: channel, 3: height, 4: width.\n For example, an input of rank 2 could be mapped as [3,4] (i.e. H,W) or [1,2] (i.e. B,C) etc.\n\n__target_ios__: str\n Target Deployment iOS version (default: '12')\n Supported values: '11.2', '12', '13'\n Core ML model produced by the converter will be compatible with the iOS version specified in this argument.\n e.g. if `target_ios` = '12', the converter would only utilize Core ML features released till iOS12\n (equivalently macOS 10.14, watchOS 5 etc).\n Release notes:\n * iOS 11 / Core ML 1: https://github.com/apple/coremltools/releases/tag/v0.8\n * iOS 12 / Core ML 2: https://github.com/apple/coremltools/releases/tag/v2.0\n * iOS 13 / Core ML 3: https://github.com/apple/coremltools/releases/tag/v3.0-beta\n```\n\n### Returns\n\n```\n__model__: A Core ML model.\n```\n\n### CLI\nAlso you can use command-line script for simplicity:\n```\nconvert-onnx-to-coreml [OPTIONS] ONNX_MODEL\n```\n\nThe command-line script currently doesn't support all options mentioned above. For more advanced use cases, you have to call the python function directly.\n\n## Running Unit Tests\n\nIn order to run unit tests, you need `pytest`.\n\n```shell\npip install pytest\npip install pytest-cov\n```\n\nTo run all unit tests, navigate to the `tests/` folder and run\n\n```shell\npytest\n```\n\nTo run a specific unit test, for instance the custom layer test, run\n\n```shell\npytest -s custom_layers_test.py::CustomLayerTest::test_unsupported_ops_provide_functions\n```\n\n## Currently Supported\n\n### Models\nModels from https://github.com/onnx/models that have been tested to work with this converter:\n\n- BVLC Alexnet\n- BVLC Caffenet\n- BVLC Googlenet\n- BVLC reference_rcnn_ilsvrc13\n- Densenet\n- Emotion-FERPlus\n- Inception V1\n- Inception V2\n- MNIST\n- Resnet50\n- Shufflenet\n- SqueezeNet\n- VGG\n- ZFNet\n\n\n### Operators\nList of [ONNX operators supported in Core ML 2.0 via the converter](https://github.com/onnx/onnx-coreml/blob/4d8b1cc348e2d6a983a6d38bb6921b6b77b47e76/onnx_coreml/_operators.py#L1893)\n\nList of [ONNX operators supported in Core ML 3.0 via the converter](https://github.com/onnx/onnx-coreml/blob/4d8b1cc348e2d6a983a6d38bb6921b6b77b47e76/onnx_coreml/_operators_nd.py#L1821)\n\nSome of the operators are partially compatible with Core ML, for example gemm with more than 1 non constant input is not supported in Core ML 2, or scale as an input for upsample layer is not supported in Core ML 3 etc.\nFor unsupported ops or unsupported attributes within supported ops, Core ML custom layers or custom functions can be used.\nSee the testing script `tests/custom_layers_test.py` on how to produce Core ML models with custom layers and custom functions.\n\n## License\nCopyright \u00a9 2018 by Apple Inc., Facebook Inc., and Prisma Labs Inc.\n\nUse of this source code is governed by the [MIT License](https://opensource.org/licenses/MIT) that can be found in the LICENSE.txt file.\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://github.com/onnx/onnx-coreml/", "keywords": "onnx coreml machinelearning ml coremltools converter neural", "license": "MIT", "maintainer": "", "maintainer_email": "", "name": "onnx-coreml", "package_url": "https://pypi.org/project/onnx-coreml/", "platform": "", "project_url": "https://pypi.org/project/onnx-coreml/", "project_urls": { "Homepage": "https://github.com/onnx/onnx-coreml/" }, "release_url": "https://pypi.org/project/onnx-coreml/1.0/", "requires_dist": [ "click", "numpy", "onnx (==1.5.0)", "typing (>=3.6.4)", "typing-extensions (>=3.6.2.1)", "coremltools (==3.0)" ], "requires_python": "", "summary": "Convert ONNX (Open Neural Network Exchange)models into Apple CoreML format.", "version": "1.0" }, "last_serial": 5946980, "releases": { "0.0.2": [ { "comment_text": "", "digests": { "md5": "37eeab457a06b133a38504f4d3041b70", "sha256": "33473ac96169dfa66af15542b851697589899c173b6e9e8741fc47734e9eca62" }, "downloads": -1, "filename": "onnx_coreml-0.0.2-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "37eeab457a06b133a38504f4d3041b70", "packagetype": "bdist_wheel", "python_version": "py2.py3", "requires_python": null, "size": 14333, "upload_time": "2017-10-30T09:53:01", "url": "https://files.pythonhosted.org/packages/2a/93/c50f07182b0c967a63cf83f75e835ac61e9314db15b73685accb3a210dd4/onnx_coreml-0.0.2-py2.py3-none-any.whl" } ], "0.0.3": [ { "comment_text": "", "digests": { "md5": "4fd5ca103e59ac3260f878b5f2954b03", "sha256": "665e9401422aa1c5fd038c4066c5b5567e01a9282d5dd8f663b30387fc62c7d8" }, "downloads": -1, "filename": "onnx-coreml-0.0.3.tar.gz", "has_sig": false, "md5_digest": "4fd5ca103e59ac3260f878b5f2954b03", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 37877, "upload_time": "2018-05-01T00:35:00", "url": "https://files.pythonhosted.org/packages/9d/7e/d64a2f8087888fe4ea8d1cab5e6918e800ceeed4eb2f9f5a02e3497dedfd/onnx-coreml-0.0.3.tar.gz" } ], "0.0.4": [ { "comment_text": "", "digests": { "md5": "c8fad9082e1716146a29940c5f771398", "sha256": "587599c64dd8cb017871a347646cbfd67bf59070292b081e35ad97c68a310af4" }, "downloads": -1, "filename": "onnx-coreml-0.0.4.tar.gz", "has_sig": false, "md5_digest": "c8fad9082e1716146a29940c5f771398", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 37877, "upload_time": "2018-05-01T00:39:12", "url": "https://files.pythonhosted.org/packages/7f/aa/e2d329141de7ecfcf5912a65499357e3af35349155fda170f8d34b5c6608/onnx-coreml-0.0.4.tar.gz" } ], "0.1.0": [ { "comment_text": "", "digests": { "md5": "75eaf531708c74526a821f8a62bb2444", "sha256": "2473457f1e63b5296a459e02a97e1632808413a61dbe1e59e12b3f69bb3636b0" }, "downloads": -1, "filename": "onnx_coreml-0.1.0-py2.py3-none-any.whl", "has_sig": false, "md5_digest": "75eaf531708c74526a821f8a62bb2444", "packagetype": "bdist_wheel", "python_version": "py2.py3", "requires_python": null, "size": 39610, "upload_time": "2018-05-01T00:59:51", "url": "https://files.pythonhosted.org/packages/8c/14/f0ddbc945999d41b06197def428f5d4f42c8d8a0eac094dbb3a9ca1cf249/onnx_coreml-0.1.0-py2.py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "353de50cd47498dd64959d1045772773", "sha256": "b895f33d9e1de5cb5aef1e3ce115f23dcf1cb44e78fee23b9e55a8e4347fb7a9" }, "downloads": -1, "filename": "onnx-coreml-0.1.0.tar.gz", "has_sig": false, "md5_digest": "353de50cd47498dd64959d1045772773", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 37898, "upload_time": "2018-05-01T00:47:15", "url": "https://files.pythonhosted.org/packages/00/3f/d02de385fe1caaa37dce067e407e1180ca87799fd94c19f0a111ee026aab/onnx-coreml-0.1.0.tar.gz" } ], "0.1.1": [ { "comment_text": "", "digests": { "md5": "555be2ad649a9e93abb08ebe8cbfcb24", "sha256": "956029c44607f8bc298b023044ed93579f7d27b48c18fc0c2e504ad83e726889" }, "downloads": -1, "filename": "onnx_coreml-0.1.1-py3-none-any.whl", "has_sig": false, "md5_digest": "555be2ad649a9e93abb08ebe8cbfcb24", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 39618, "upload_time": "2018-05-01T21:55:26", "url": "https://files.pythonhosted.org/packages/de/0e/94b00e68c4d125fc53404926817a0376843619d18ac94ce34b29d9d3e693/onnx_coreml-0.1.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "b17dbad593a3ad8d915e9cb11bd49ef8", "sha256": "0a30ac9707f29255be4040142e2a9b9f1fcf5839d74c9ee22f9251f0c1667e64" }, "downloads": -1, "filename": "onnx-coreml-0.1.1.tar.gz", "has_sig": false, "md5_digest": "b17dbad593a3ad8d915e9cb11bd49ef8", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 37931, "upload_time": "2018-05-01T21:55:28", "url": "https://files.pythonhosted.org/packages/fb/78/4c105d475c3fa6b97791252951f7dca60a007df2c79467f93de40513f749/onnx-coreml-0.1.1.tar.gz" } ], "0.2.0": [ { "comment_text": "", "digests": { "md5": "9c3b2b4497871fcc3261113c8d092e78", "sha256": "ea349054da43afdd3ea1aeab014f42852740c4a4a9475a5d443d9e44620aa97b" }, "downloads": -1, "filename": "onnx_coreml-0.2.0-py2-none-any.whl", "has_sig": false, "md5_digest": "9c3b2b4497871fcc3261113c8d092e78", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 44752, "upload_time": "2018-09-24T00:26:39", "url": "https://files.pythonhosted.org/packages/6c/e0/f73fd4bd8bd93583339a1a902889fd25acc340b94a4337ea1a419e8515a8/onnx_coreml-0.2.0-py2-none-any.whl" }, { "comment_text": "", "digests": { "md5": "56cdd57218de4e9f4ada87150c53112c", "sha256": "c6051ac085f7475c382ae31a3ce6b5b3d94df497fb600079e461c86f8f69f79a" }, "downloads": -1, "filename": "onnx_coreml-0.2.0-py3-none-any.whl", "has_sig": false, "md5_digest": "56cdd57218de4e9f4ada87150c53112c", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 44775, "upload_time": "2018-09-24T00:26:41", "url": "https://files.pythonhosted.org/packages/7d/f8/6032947614b7c85684c8e8dcd4d3946f20bcd29d016d54f1be71a94fa09d/onnx_coreml-0.2.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "bbe8dbf272f883393907a30cd603b6fd", "sha256": "24d968777c56132a6d7ee150090f3d28e2824ee937950f577b63124c96466ac7" }, "downloads": -1, "filename": "onnx-coreml-0.2.0.tar.gz", "has_sig": false, "md5_digest": "bbe8dbf272f883393907a30cd603b6fd", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 42041, "upload_time": "2018-09-24T00:26:42", "url": "https://files.pythonhosted.org/packages/ea/9e/a5f84533ece788df79cb672fbcb50b8b140ed802cb5c62a92d74da2c046a/onnx-coreml-0.2.0.tar.gz" } ], "0.3.0": [ { "comment_text": "", "digests": { "md5": "63183702ebddc1b5bbb65ae64af12be9", "sha256": "fe8e2fce6c9e73ea5586d2a8c261e899bf6e82491d5751e5edcb24835b129716" }, "downloads": -1, "filename": "onnx_coreml-0.3.0-py2-none-any.whl", "has_sig": false, "md5_digest": "63183702ebddc1b5bbb65ae64af12be9", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 51020, "upload_time": "2018-09-30T04:01:36", "url": "https://files.pythonhosted.org/packages/59/16/dcf5a5da1511a307143479a5f569fc32bbe8cd19e066445246b2121d4e79/onnx_coreml-0.3.0-py2-none-any.whl" }, { "comment_text": "", "digests": { "md5": "66e245727fda7817237d76afbf6e3b1d", "sha256": "ee38d82279a2fae5e0b222e70d67c2df7fce33d5ffd8bc9b04f83ff0a4d09ba3" }, "downloads": -1, "filename": "onnx_coreml-0.3.0-py3-none-any.whl", "has_sig": false, "md5_digest": "66e245727fda7817237d76afbf6e3b1d", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 51043, "upload_time": "2018-09-30T04:01:37", "url": "https://files.pythonhosted.org/packages/9f/69/373d383c797bec4b591a3f5e350d533068c74fd799391be02c04088731bb/onnx_coreml-0.3.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "248736ac1d923e9c58d217fde61a6ffd", "sha256": "581f0e1d05180a1323b00d1f16ed8daa319695482061c15688aae9783c6b1f2d" }, "downloads": -1, "filename": "onnx-coreml-0.3.0.tar.gz", "has_sig": false, "md5_digest": "248736ac1d923e9c58d217fde61a6ffd", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 48248, "upload_time": "2018-09-30T04:01:39", "url": "https://files.pythonhosted.org/packages/58/81/d1799a6336fe41ca2d63b9e026a6efb5bdfce5d4b7fe9c246d536282f442/onnx-coreml-0.3.0.tar.gz" } ], "0.4.0": [ { "comment_text": "", "digests": { "md5": "34a4e9fd7eabd796f1af0b23e36d74c5", "sha256": "692804f715ab1dd30178732812d713ada4984599e9158c937fef142d0a4c84f0" }, "downloads": -1, "filename": "onnx_coreml-0.4.0-py2-none-any.whl", "has_sig": false, "md5_digest": "34a4e9fd7eabd796f1af0b23e36d74c5", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 53344, "upload_time": "2019-02-22T05:54:36", "url": "https://files.pythonhosted.org/packages/eb/ab/93bdfff7590dbdfd93cbc8e673ed1efe1e01fa029d9c9ab3845048701698/onnx_coreml-0.4.0-py2-none-any.whl" }, { "comment_text": "", "digests": { "md5": "940d3eaea799de7b7dea21eee96ed172", "sha256": "448d5c3a0012e6ed4ae95d0cde11b1e506cb8a19d3c306c2b041767c7fdbf49e" }, "downloads": -1, "filename": "onnx_coreml-0.4.0-py3-none-any.whl", "has_sig": false, "md5_digest": "940d3eaea799de7b7dea21eee96ed172", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 53367, "upload_time": "2019-02-22T05:54:37", "url": "https://files.pythonhosted.org/packages/cc/a4/c4a464524423ff86e24771c0e4e7e635d72d2775f0cc797161486e61f931/onnx_coreml-0.4.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "6c6f9ab6815cfda6a4ba56af85cefd81", "sha256": "ce36b5aafc73eef3ab98c9d35dced4922b4a792ec9f5398bf35f275eb56c02ab" }, "downloads": -1, "filename": "onnx-coreml-0.4.0.tar.gz", "has_sig": false, "md5_digest": "6c6f9ab6815cfda6a4ba56af85cefd81", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 50703, "upload_time": "2019-02-22T05:54:39", "url": "https://files.pythonhosted.org/packages/d2/60/4133c8aa86ecff54f41b658449427780267d01b7b34c7cd48bd531da8227/onnx-coreml-0.4.0.tar.gz" } ], "1.0": [ { "comment_text": "", "digests": { "md5": "3b7c705fe2a8a2f7a369b27f7a8d0468", "sha256": "d4d1f71243f95c4d12cafdbef900790bf2c1a30a463075b069dfa1b885bcf415" }, "downloads": -1, "filename": "onnx_coreml-1.0-py2-none-any.whl", "has_sig": false, "md5_digest": "3b7c705fe2a8a2f7a369b27f7a8d0468", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 78871, "upload_time": "2019-10-08T22:39:14", "url": "https://files.pythonhosted.org/packages/cd/7f/e066974d6f45e0b129972c2fc6fd145c35daf564dfc1070f3cd7f8014ee2/onnx_coreml-1.0-py2-none-any.whl" }, { "comment_text": "", "digests": { "md5": "a5e8456f67e9dba06dee4f313e92d684", "sha256": "632ba14485e204ecab7a8513ba55cae73a06fdc20a093366c60a994df56b4b62" }, "downloads": -1, "filename": "onnx_coreml-1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "a5e8456f67e9dba06dee4f313e92d684", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 78895, "upload_time": "2019-10-08T22:39:16", "url": "https://files.pythonhosted.org/packages/c6/07/6a32d936762ec37eb893aeb00d8b36209f3b3559765f9a5980053a438dce/onnx_coreml-1.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "ce5e15a7de87301c225ef0deaf0e90db", "sha256": "569988d52bc67250882006a5fa4c095a0fdf21064cd3df279559b9470f94c7fb" }, "downloads": -1, "filename": "onnx-coreml-1.0.tar.gz", "has_sig": false, "md5_digest": "ce5e15a7de87301c225ef0deaf0e90db", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 75991, "upload_time": "2019-10-08T22:39:17", "url": "https://files.pythonhosted.org/packages/43/e1/d50c8cee29a8b7b65151e6407a48537f865cf6a87ce59bf7a6cc0af0758e/onnx-coreml-1.0.tar.gz" } ], "1.0b2": [ { "comment_text": "", "digests": { "md5": "b5ec95dc0f0ee29a0fcc81471c5680e3", "sha256": "174a9eb7cb2cc0f839ca01050cb19693a0629934c9bf492d26634ff1f5a45ecc" }, "downloads": -1, "filename": "onnx_coreml-1.0b2-py3-none-any.whl", "has_sig": false, "md5_digest": "b5ec95dc0f0ee29a0fcc81471c5680e3", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 73926, "upload_time": "2019-08-23T22:34:00", "url": "https://files.pythonhosted.org/packages/8d/38/484682aa87ad271774e0c4110d06cea739e12f19a45d335b20885d10a2cc/onnx_coreml-1.0b2-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "ae84bb8554c8ab8df8d6c5f9746bd3f3", "sha256": "60d6858a4c89ca69d44ae0c120f08fb548e70b290dd480abb7c521ed6e843b72" }, "downloads": -1, "filename": "onnx-coreml-1.0b2.tar.gz", "has_sig": false, "md5_digest": "ae84bb8554c8ab8df8d6c5f9746bd3f3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 67797, "upload_time": "2019-08-23T22:34:02", "url": "https://files.pythonhosted.org/packages/1d/0c/d0244b01967e7af036f15298f73080b685aee62f296fec7001bdf33e0f8f/onnx-coreml-1.0b2.tar.gz" } ], "1.0b3": [ { "comment_text": "", "digests": { "md5": "9a22ec036074db92a95c49cace7b701f", "sha256": "3303173b3212b81b40825dab73216ea601eb3fc1c0cbab4791797295f8f02f7a" }, "downloads": -1, "filename": "onnx_coreml-1.0b3-py3-none-any.whl", "has_sig": false, "md5_digest": "9a22ec036074db92a95c49cace7b701f", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 77804, "upload_time": "2019-09-17T19:01:01", "url": "https://files.pythonhosted.org/packages/a9/b1/cf0434573080c1053e76e8dcb10c6d0ff5c8632c5ec0607637ed806a57ab/onnx_coreml-1.0b3-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "0b6eacd13a246380ace989588c99777b", "sha256": "de8ceb7897f3f1a7ef09d37089f8d533b5da0f5bff9dc2618b2c1bc7571879de" }, "downloads": -1, "filename": "onnx-coreml-1.0b3.tar.gz", "has_sig": false, "md5_digest": "0b6eacd13a246380ace989588c99777b", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 75158, "upload_time": "2019-09-17T19:01:03", "url": "https://files.pythonhosted.org/packages/5d/7a/b92ad597cb826d60ef202952980dbb5ab10930d29c1983f428137082a7b9/onnx-coreml-1.0b3.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "3b7c705fe2a8a2f7a369b27f7a8d0468", "sha256": "d4d1f71243f95c4d12cafdbef900790bf2c1a30a463075b069dfa1b885bcf415" }, "downloads": -1, "filename": "onnx_coreml-1.0-py2-none-any.whl", "has_sig": false, "md5_digest": "3b7c705fe2a8a2f7a369b27f7a8d0468", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 78871, "upload_time": "2019-10-08T22:39:14", "url": "https://files.pythonhosted.org/packages/cd/7f/e066974d6f45e0b129972c2fc6fd145c35daf564dfc1070f3cd7f8014ee2/onnx_coreml-1.0-py2-none-any.whl" }, { "comment_text": "", "digests": { "md5": "a5e8456f67e9dba06dee4f313e92d684", "sha256": "632ba14485e204ecab7a8513ba55cae73a06fdc20a093366c60a994df56b4b62" }, "downloads": -1, "filename": "onnx_coreml-1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "a5e8456f67e9dba06dee4f313e92d684", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 78895, "upload_time": "2019-10-08T22:39:16", "url": "https://files.pythonhosted.org/packages/c6/07/6a32d936762ec37eb893aeb00d8b36209f3b3559765f9a5980053a438dce/onnx_coreml-1.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "ce5e15a7de87301c225ef0deaf0e90db", "sha256": "569988d52bc67250882006a5fa4c095a0fdf21064cd3df279559b9470f94c7fb" }, "downloads": -1, "filename": "onnx-coreml-1.0.tar.gz", "has_sig": false, "md5_digest": "ce5e15a7de87301c225ef0deaf0e90db", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 75991, "upload_time": "2019-10-08T22:39:17", "url": "https://files.pythonhosted.org/packages/43/e1/d50c8cee29a8b7b65151e6407a48537f865cf6a87ce59bf7a6cc0af0758e/onnx-coreml-1.0.tar.gz" } ] }