ONNXRuntime Extensions

These details have not been verified by PyPI

Project links

Homepage

Development Status
- 4 - Beta
Environment
- Console
Intended Audience
- Developers
License
- OSI Approved :: MIT License
Operating System
Programming Language

Project description

ONNXRuntime-Extensions

What's ONNXRuntime-Extensions

Introduction: ONNXRuntime-Extensions is a library that extends the capability of the ONNX models and inference with ONNX Runtime, via ONNX Runtime Custom Operator ABIs. It includes a set of ONNX Runtime Custom Operator to support the common pre- and post-processing operators for vision, text, and nlp models. And it supports multiple languages and platforms, like Python on Windows/Linux/macOS, some mobile platforms like Android and iOS, and Web-Assembly etc. The basic workflow is to enhance a ONNX model firstly and then do the model inference with ONNX Runtime and ONNXRuntime-Extensions package.

Quickstart

Python installation

pip install onnxruntime-extensions

Nightly Build

on Windows

pip install --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple/ onnxruntime-extensions

Please ensure that you have met the prerequisites of onnxruntime-extensions (e.g., onnx and onnxruntime) in your Python environment.

on Linux/macOS

Please make sure the compiler toolkit like gcc(later than g++ 8.0) or clang are installed before the following command

python -m pip install git+https://github.com/microsoft/onnxruntime-extensions.git

Usage

1. Generate the pre-/post- processing ONNX model

With onnxruntime-extensions Python package, you can easily get the ONNX processing graph by converting them from Huggingface transformer data processing classes, check the following API for details.

help(onnxruntime_extensions.gen_processing_models)

NOTE: These data processing model can be merged into other model onnx.compose if needed.

2. Using Extensions for ONNX Runtime inference

Python

There are individual packages for the following languages, please install it for the build.

import onnxruntime as _ort
from onnxruntime_extensions import get_library_path as _lib_path

so = _ort.SessionOptions()
so.register_custom_ops_library(_lib_path())

# Run the ONNXRuntime Session, as ONNXRuntime docs suggested.
# sess = _ort.InferenceSession(model, so)
# sess.run (...)

C++

  // The line loads the customop library into ONNXRuntime engine to load the ONNX model with the custom op
  Ort::ThrowOnError(Ort::GetApi().RegisterCustomOpsLibrary((OrtSessionOptions*)session_options, custom_op_library_filename, &handle));

  // The regular ONNXRuntime invoking to run the model.
  Ort::Session session(env, model_uri, session_options);
  RunSession(session, inputs, outputs);

Java

var env = OrtEnvironment.getEnvironment();
var sess_opt = new OrtSession.SessionOptions();

/* Register the custom ops from onnxruntime-extensions */
sess_opt.registerCustomOpLibrary(OrtxPackage.getLibraryPath());

C#

SessionOptions options = new SessionOptions()
options.RegisterOrtExtensions()
session = new InferenceSession(model, options)

Project details

These details have not been verified by PyPI

Project links

Homepage

Development Status
- 4 - Beta
Environment
- Console
Intended Audience
- Developers
License
- OSI Approved :: MIT License
Operating System
Programming Language

Release history Release notifications | RSS feed

0.13.0

Oct 31, 2024

0.12.0

Aug 16, 2024

0.11.0

May 28, 2024

0.10.1

Feb 17, 2024

This version

0.10.0

Feb 6, 2024

0.9.0

Sep 20, 2023

0.8.0

May 26, 2023

0.7.0

Mar 2, 2023

0.4.2

Oct 7, 2021

0.4.0

Sep 28, 2021

0.3.1

Jun 4, 2021

0.3.0

Jun 2, 2021

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

onnxruntime_extensions-0.10.0-cp311-cp311-win_amd64.whl (2.1 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 Windows x86-64

onnxruntime_extensions-0.10.0-cp311-cp311-musllinux_1_1_x86_64.whl (6.7 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 musllinux: musl 1.1+ x86-64

onnxruntime_extensions-0.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.0 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.10.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (3.3 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 manylinux: glibc 2.17+ ARM64

onnxruntime_extensions-0.10.0-cp311-cp311-macosx_11_0_arm64.whl (2.5 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 macOS 11.0+ ARM64

onnxruntime_extensions-0.10.0-cp311-cp311-macosx_10_9_x86_64.whl (3.6 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 macOS 10.9+ x86-64

onnxruntime_extensions-0.10.0-cp311-cp311-macosx_10_9_universal2.whl (5.2 MB view details)

Uploaded Feb 6, 2024 CPython 3.11 macOS 10.9+ universal2 (ARM64, x86-64)

onnxruntime_extensions-0.10.0-cp310-cp310-win_amd64.whl (2.1 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 Windows x86-64

onnxruntime_extensions-0.10.0-cp310-cp310-musllinux_1_1_x86_64.whl (6.7 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 musllinux: musl 1.1+ x86-64

onnxruntime_extensions-0.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.0 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.10.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (3.3 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 manylinux: glibc 2.17+ ARM64

onnxruntime_extensions-0.10.0-cp310-cp310-macosx_11_0_arm64.whl (2.5 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 macOS 11.0+ ARM64

onnxruntime_extensions-0.10.0-cp310-cp310-macosx_10_9_x86_64.whl (3.6 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 macOS 10.9+ x86-64

onnxruntime_extensions-0.10.0-cp310-cp310-macosx_10_9_universal2.whl (5.2 MB view details)

Uploaded Feb 6, 2024 CPython 3.10 macOS 10.9+ universal2 (ARM64, x86-64)

onnxruntime_extensions-0.10.0-cp39-cp39-win_amd64.whl (2.1 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 Windows x86-64

onnxruntime_extensions-0.10.0-cp39-cp39-musllinux_1_1_x86_64.whl (6.7 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 musllinux: musl 1.1+ x86-64

onnxruntime_extensions-0.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.0 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.10.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (3.3 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 manylinux: glibc 2.17+ ARM64

onnxruntime_extensions-0.10.0-cp39-cp39-macosx_11_0_arm64.whl (2.5 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 macOS 11.0+ ARM64

onnxruntime_extensions-0.10.0-cp39-cp39-macosx_10_9_x86_64.whl (3.6 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 macOS 10.9+ x86-64

onnxruntime_extensions-0.10.0-cp39-cp39-macosx_10_9_universal2.whl (5.2 MB view details)

Uploaded Feb 6, 2024 CPython 3.9 macOS 10.9+ universal2 (ARM64, x86-64)

onnxruntime_extensions-0.10.0-cp38-cp38-win_amd64.whl (2.1 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 Windows x86-64

onnxruntime_extensions-0.10.0-cp38-cp38-musllinux_1_1_x86_64.whl (6.7 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 musllinux: musl 1.1+ x86-64

onnxruntime_extensions-0.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.0 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.10.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (3.3 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 manylinux: glibc 2.17+ ARM64

onnxruntime_extensions-0.10.0-cp38-cp38-macosx_11_0_arm64.whl (2.5 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 macOS 11.0+ ARM64

onnxruntime_extensions-0.10.0-cp38-cp38-macosx_10_9_x86_64.whl (3.6 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 macOS 10.9+ x86-64

onnxruntime_extensions-0.10.0-cp38-cp38-macosx_10_9_universal2.whl (5.2 MB view details)

Uploaded Feb 6, 2024 CPython 3.8 macOS 10.9+ universal2 (ARM64, x86-64)

File details

Details for the file onnxruntime_extensions-0.10.0-cp311-cp311-win_amd64.whl.

File metadata

Download URL: onnxruntime_extensions-0.10.0-cp311-cp311-win_amd64.whl
Upload date: Feb 6, 2024
Size: 2.1 MB
Tags: CPython 3.11, Windows x86-64
Uploaded using Trusted Publishing? No
Uploaded via: RestSharp/106.13.0.0

File hashes

Hashes for onnxruntime_extensions-0.10.0-cp311-cp311-win_amd64.whl
Algorithm	Hash digest
SHA256	`165370d7558ea720a338a88f22795c74b19da3e588a38f6a242cca7bfdad83bd`
MD5	`bcf0b6e3231c380256f77aff3fe2a694`
BLAKE2b-256	`ac4bab5c91ca841e577492e1f9a3599e42d94c66e11f59a4d546c5a472c6a8b6`

Algorithm	Hash digest
SHA256	`afb54cf0803e042a1404f39b265db19476757cf6feb7232d65b86a692641fbed`
MD5	`531af66665473de42e9a6d002979356a`
BLAKE2b-256	`8c4871b82325a783814fdfc0869295d7884964fff08f8e88bf4d9e43a61b38b0`

Algorithm	Hash digest
SHA256	`f90e83a70fe336cb316922ad867b280b2858a45840015254f7cbbc5b676109cf`
MD5	`aa07d1729d487d460828d6d4cb94f807`
BLAKE2b-256	`9b78e55279a8b74af3ba94628aa8c29e3d2706460ba7ed10141c006e92ad38b0`

Algorithm	Hash digest
SHA256	`7a0ec0f82da07efd4d24ffc40d880b3c2b80789fa7891d1024ababc48fde2d8e`
MD5	`b51df295f50c6df2f34fc5f39ce3ba40`
BLAKE2b-256	`75ac2f1a6a05dcac1deb3ceeb79dcaf7b6fbc6b59e6529ef0b6d0881e9739cd5`

Algorithm	Hash digest
SHA256	`4a2bd9bd1fe37eada739aa2b72688aa4e6aeaff17097853aec18a19fcf2693d9`
MD5	`93004c66774d4c0bdc17d0c30ff084a2`
BLAKE2b-256	`efe501a85523d5a12a26481e3c058edcc9fa6f8717d8ea05b07de01cd6b31594`

Algorithm	Hash digest
SHA256	`f5ccb25763f99d159b3b6c6141f2a83bed92b3bc41a7cfc04dffd5592ffd7580`
MD5	`9c0f14a27eb1d3fe67eb649597706a0a`
BLAKE2b-256	`e7a3dc36c905d6beaa618280efc6729cc2dbb7dc5034f0dfe4b3b5410557994c`

Algorithm	Hash digest
SHA256	`5bb31d65da491913f32450b72bd65cd49187304d4052c6eb0c1b2d3897bbb816`
MD5	`1dabb75abb082f68a3a7d33ff4f94c18`
BLAKE2b-256	`48c8d9a984675213039ecca636697b31d8deba6c4b8bfd64e70156be0bf35741`

Algorithm	Hash digest
SHA256	`f496970f51e23f825a0c0b45d232826956369f36c52abe47067637031caa2d60`
MD5	`3445beae4ba22d26507cd2a75f01c42c`
BLAKE2b-256	`5249b20cdc68ed84da6ff8facfad0db8cf029f9754648ea43907a131fd1fc07a`

Algorithm	Hash digest
SHA256	`7992191cb79a6eaa007e049cec56384f120909f86a0938886f55b5280e529c1c`
MD5	`39dc2a74d096840c1e28689c7157725e`
BLAKE2b-256	`74ea7b3737d795dc54d5247f4d1b436d686faffab448739833a66d33becc5c19`

Algorithm	Hash digest
SHA256	`0517ac11343d276ec8b2aae745405ef24aec9299cc35cd518ab919178380943b`
MD5	`9ce4dc7fe42d4454005d2de10d963562`
BLAKE2b-256	`ca81053e0287686b13dfabc888a2087ce8ab59f26d587e3c0040d0329716c7e1`

Algorithm	Hash digest
SHA256	`5eaf790fe986b98884a30d5ba9424f1142f7812a35d15d8a1b5f992f319f6a87`
MD5	`c171442753fdc2359998535017b1718c`
BLAKE2b-256	`10b94edfd85649fb2de52baa25f02cfad13b4173746ab97b67bb3e5caf2612b7`

Algorithm	Hash digest
SHA256	`77e045dd9e30671a84443f734e97800b2531a270b6ac8c1ca38aa326fda19c24`
MD5	`53b8ea324b000b9e69926f160fc0f333`
BLAKE2b-256	`d204ecb7813912d45a3d8dd7c546327c4c5d987ae49df4afdcbc7cc0df26da2c`

Algorithm	Hash digest
SHA256	`1e328f76642f28781e9812e652150f56a63e31a264fd3ae43aa5e41eec8285d8`
MD5	`81537ffc17d8be021128d1aa4f09ffdd`
BLAKE2b-256	`17a715a9ae479312cf3b868d9e3135ea69ab88efd7c6d09287499a816d343bff`

Algorithm	Hash digest
SHA256	`93597a41bf95f44beb03c5075594f04f8a750df992f5a6b3f93db4a71ca7cead`
MD5	`2798f7baa63e249b0d0afe73fb6f6404`
BLAKE2b-256	`e65bd5dee54ed29a547953bc2c09e17fdf2a982aae2e6587cb15438074c1de1d`

Algorithm	Hash digest
SHA256	`df5333b5ce399977531412031bbd2bf4aa934f2f54394f60e1e91fbf72019fb7`
MD5	`da4251e06f20c609ba55a83d5967be9a`
BLAKE2b-256	`30f27f1220be1aa820b6a444fc1c2ab9bd4cf0e8caf299890e288a9b4d52b71b`

Algorithm	Hash digest
SHA256	`f664d1979c9bb37722cba4a8064725341a60aef5ae4c341bcfb19f4957e74a66`
MD5	`8966791e1db28b28e2f7d7a38d01d15b`
BLAKE2b-256	`6811abab8be13ca1bb062340b91cec986abb28b986cc7c438d7d5565a14d0614`

Algorithm	Hash digest
SHA256	`c9e353cbd52c88204348b798c9f9212a044e5547ee35abaf3e8859d63dda90f9`
MD5	`a9ba25aa90fadf52faf85c90a01314bb`
BLAKE2b-256	`519ffea56d2b8772aff8d60d9a260c148314f55698b7bde0f6020216b66c9c3b`

Algorithm	Hash digest
SHA256	`44633ea724dec111928115b68fac04c39fe38b24ee6257a2382bb55fdd84cda8`
MD5	`1f6e2f7af77d4dfd8248489e15a49891`
BLAKE2b-256	`a8b1fc73f82abd47218ed631aad646e6c533a0654cc23532657e892a78284edf`

Algorithm	Hash digest
SHA256	`2bd79ead766b0a117d0b55f5c85e6c9cb168ab3d5dc20286d8854ae940f6a4e4`
MD5	`2a2a74af225842f1842e42f6caad5989`
BLAKE2b-256	`82bea8db41550827d066a795884cd03c90c2b8361b6f48d71d570809529eb670`

Algorithm	Hash digest
SHA256	`ed3bc9d3bca45a07eb49caccfb473c25b95657c3492ebcb60984a9376cee4002`
MD5	`dbb87665ccc7f69b59a3caa53d99bede`
BLAKE2b-256	`3130e39cb341174068225911ec28da86e154a0c3c2f6d152963b00bb86c7c6f3`

Algorithm	Hash digest
SHA256	`0c1325aef14e78a6848775c41c5eb2c018cfa3279f0655ae86796bbc9da44ebf`
MD5	`6c396bac7912574da8dc9e8d5af57cd2`
BLAKE2b-256	`a79a621fe9344db563edad47f39804d8d94b4ffed383bef48c86ec8e74db4c17`

onnxruntime_extensions 0.10.0

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

ONNXRuntime-Extensions

What's ONNXRuntime-Extensions

Quickstart

Python installation

Nightly Build

on Windows

on Linux/macOS

Usage

1. Generate the pre-/post- processing ONNX model

NOTE: These data processing model can be merged into other model onnx.compose if needed.

2. Using Extensions for ONNX Runtime inference

Python

C++

Java

C#

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

Algorithm	Hash digest
SHA256	`fcc0cac09adbafa7fe39ffd12b6f8431e05a583597c11739bf1be1d656a414ab`
MD5	`6a1e355a4e09b64532c43f7a87e18d15`
BLAKE2b-256	`0e5878d064abda67ad0853e93850771597a792f771ee2ab208dd8f3b6867c32e`

Algorithm	Hash digest
SHA256	`4ae087cc53743a060c28e75f56b5af037173eee9cd5b4888d0225f0ebfa35b2a`
MD5	`8b4bdfabc5cc7547f61d740f53271bd8`
BLAKE2b-256	`d8e4c8cc8baf1f421c4c880ff8f30749822d86386468675935ae5107350e794f`

Algorithm	Hash digest
SHA256	`13f6e797cc034a715955885352607753675a16d67147d14a2cb5f879612d935e`
MD5	`09c05387bf97ed0e8f07d827f95600d1`
BLAKE2b-256	`a629619655de17c7c19391a8e16e7baab3437ab17bc975cba3c91ec45014d9f3`

Algorithm	Hash digest
SHA256	`197cae092ff71322f0c231a5afb6cee161bca8189ff1a3dc2c7f8633e1b1133c`
MD5	`fb480143a888862332f6bad35d438236`
BLAKE2b-256	`ea1b3a5007ed9cc5aecd7392775e875dae606ecf52fab7742a254869b57017cb`

Algorithm	Hash digest
SHA256	`4a2fd94766bec8021337f25316c4a1ad54f508b2019b24cc54a32a18c1ca5be3`
MD5	`dee3fffe302cdbdf4f77f125f41be6e2`
BLAKE2b-256	`89e6634cc6657e1db75106e9c9f7f00a6b9e242fb18c3583d644b46e60382587`

Algorithm	Hash digest
SHA256	`44e557a25747d0c8d095bbe46110d9092f20cd928c8f9d68a9365c4443740311`
MD5	`6d374290d12257e9c2054d160115a945`
BLAKE2b-256	`77d5168358b199d5555749477d17557a8558ca43ab28b9679bc7b6641284a24b`

Algorithm	Hash digest
SHA256	`c5850b7cd1bddfbb6fffb150c25c96a89faf0951717df6e263d50e984ca664a9`
MD5	`14dcb7940fd91bdb140d20cac9a2add2`
BLAKE2b-256	`65715dde99562f37bbc3f7514e4e27698900fc2851620221fecf33d6c1420439`