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.

⚠️	NOTE: most ONNXRuntime-Extensions packages are in *active development* and most packages require building from source. The package information will be updated here if it is published.

Quickstart with the experimental Python package

on Windows

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

on Linux/macOS

the packages are not ready yet, so it could be installed from source. Please make sure the compiler toolkit like gcc(later than g++ 8.0) or clang, and the tool cmake are installed before the following command

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

Usage

1. Augment an ONNX model with a pre- and post-processing pipeline

check tutorial for a couple of examples on how to do it.

2. Using Extensions for ONNX Runtime inference

Python

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());

Use exporters to generate graphs with custom operators

The PyTorch and TensorFlow converters support custom operator generation if the operation from the original framework cannot be interpreted as a standard ONNX operators. Check the following two examples on how to do this.

Add a new custom operator to onnxruntime-extensions

You can contribute customop C++ implementations directly in this repository if they have general applicability to other users. In addition, if you want to quickly verify the ONNX model with Python, you can wrap the custom operator with PyOp.

import numpy
from onnxruntime_extensions import PyOp, onnx_op

# Implement the CustomOp by decorating a function with onnx_op
@onnx_op(op_type="Inverse", inputs=[PyOp.dt_float])
def inverse(x):
    # the user custom op implementation here:
    return numpy.linalg.inv(x)

# Run the model with this custom op
# model_func = PyOrtFunction(model_path)
# outputs = model_func(inputs)
# ...

Check development.md for build and test

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

0.10.0

Feb 6, 2024

0.9.0

Sep 20, 2023

0.8.0

May 26, 2023

This version

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-0.7.0-cp310-cp310-win_amd64.whl (1.6 MB view details)

Uploaded Mar 2, 2023 CPython 3.10 Windows x86-64

onnxruntime_extensions-0.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.2 MB view details)

Uploaded Mar 2, 2023 CPython 3.10 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.7.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl (3.8 MB view details)

Uploaded Mar 2, 2023 CPython 3.10 manylinux: glibc 2.17+ i686

onnxruntime_extensions-0.7.0-cp310-cp310-macosx_11_0_arm64.whl (3.3 MB view details)

Uploaded Mar 2, 2023 CPython 3.10 macOS 11.0+ ARM64

onnxruntime_extensions-0.7.0-cp310-cp310-macosx_10_9_x86_64.whl (3.7 MB view details)

Uploaded Mar 2, 2023 CPython 3.10 macOS 10.9+ x86-64

onnxruntime_extensions-0.7.0-cp310-cp310-macosx_10_9_universal2.whl (3.7 MB view details)

Uploaded Mar 2, 2023 CPython 3.10 macOS 10.9+ universal2 (ARM64, x86-64)

onnxruntime_extensions-0.7.0-cp39-cp39-win_amd64.whl (1.6 MB view details)

Uploaded Mar 2, 2023 CPython 3.9 Windows x86-64

onnxruntime_extensions-0.7.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.2 MB view details)

Uploaded Mar 2, 2023 CPython 3.9 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.7.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl (3.8 MB view details)

Uploaded Mar 2, 2023 CPython 3.9 manylinux: glibc 2.17+ i686

onnxruntime_extensions-0.7.0-cp39-cp39-macosx_11_0_arm64.whl (3.3 MB view details)

Uploaded Mar 2, 2023 CPython 3.9 macOS 11.0+ ARM64

onnxruntime_extensions-0.7.0-cp39-cp39-macosx_10_9_x86_64.whl (3.7 MB view details)

Uploaded Mar 2, 2023 CPython 3.9 macOS 10.9+ x86-64

onnxruntime_extensions-0.7.0-cp39-cp39-macosx_10_9_universal2.whl (3.7 MB view details)

Uploaded Mar 2, 2023 CPython 3.9 macOS 10.9+ universal2 (ARM64, x86-64)

onnxruntime_extensions-0.7.0-cp38-cp38-win_amd64.whl (1.6 MB view details)

Uploaded Mar 2, 2023 CPython 3.8 Windows x86-64

onnxruntime_extensions-0.7.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.2 MB view details)

Uploaded Mar 2, 2023 CPython 3.8 manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.7.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl (3.8 MB view details)

Uploaded Mar 2, 2023 CPython 3.8 manylinux: glibc 2.17+ i686

onnxruntime_extensions-0.7.0-cp38-cp38-macosx_11_0_arm64.whl (3.3 MB view details)

Uploaded Mar 2, 2023 CPython 3.8 macOS 11.0+ ARM64

onnxruntime_extensions-0.7.0-cp38-cp38-macosx_10_9_x86_64.whl (3.7 MB view details)

Uploaded Mar 2, 2023 CPython 3.8 macOS 10.9+ x86-64

onnxruntime_extensions-0.7.0-cp38-cp38-macosx_10_9_universal2.whl (3.7 MB view details)

Uploaded Mar 2, 2023 CPython 3.8 macOS 10.9+ universal2 (ARM64, x86-64)

onnxruntime_extensions-0.7.0-cp37-cp37m-win_amd64.whl (1.6 MB view details)

Uploaded Mar 2, 2023 CPython 3.7m Windows x86-64

onnxruntime_extensions-0.7.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.2 MB view details)

Uploaded Mar 2, 2023 CPython 3.7m manylinux: glibc 2.17+ x86-64

onnxruntime_extensions-0.7.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl (3.8 MB view details)

Uploaded Mar 2, 2023 CPython 3.7m manylinux: glibc 2.17+ i686

File details

Details for the file onnxruntime_extensions-0.7.0-cp310-cp310-win_amd64.whl.

File metadata

Download URL: onnxruntime_extensions-0.7.0-cp310-cp310-win_amd64.whl
Upload date: Mar 2, 2023
Size: 1.6 MB
Tags: CPython 3.10, Windows x86-64
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.9.12

File hashes

Hashes for onnxruntime_extensions-0.7.0-cp310-cp310-win_amd64.whl
Algorithm	Hash digest
SHA256	`8c21bbd4ca967bad8f6534836dd25d1f46f1eb70ba4559e3edda7a8ef93e2339`
MD5	`67da2642c186fa32830a96b26ffb285f`
BLAKE2b-256	`1812275eaeea1f436f7ca9539c2c880866de2b4cf8222160cd9bd672fc38b135`

Algorithm	Hash digest
SHA256	`49fb6091dea9e99976442c6872cd6341ca27f527799b85b89b3cec5418deb802`
MD5	`4d6f628bc21dc89d50b222b9ff2a6bc1`
BLAKE2b-256	`36fa0d6e4593f61228bc67e839dcc29451387b6768269f1484fe46a7fbbfa9e2`

Algorithm	Hash digest
SHA256	`07b589da7a60ae3ed0163f99d775f92a296160faf54e36f2ff521229d87c36c0`
MD5	`f46e0f703181b7f5b399951a3b2761f4`
BLAKE2b-256	`b71a6570381460d97a7fab488307287477c87614aab4e30c74c31969980cce14`

Algorithm	Hash digest
SHA256	`b6801ac19ff66d97f23394cb1f40fff5ce05fbbde3a12186dbfc2f3088ca82a8`
MD5	`b632ba1b002f46bed41e00aa4ffeac4d`
BLAKE2b-256	`74c0b44a87e6aaae288eb6d1ee0b0188bbb7756f58071e81c51e10cf3f299396`

Algorithm	Hash digest
SHA256	`680fe084bc34976c4fc7669f9e0ce19273effbd2741ed0996b11a487cbd4ab4a`
MD5	`b56441caa03a9cc29a6c0199a30ea5f4`
BLAKE2b-256	`fc24c21274f4f9126afe7488ba53a7f6d8b44fe2828bf54d68fb05fe8dbdfcd0`

Algorithm	Hash digest
SHA256	`70f5a82082357521127b5b52fe3c7912558412c00061737e1b14a4b23691506c`
MD5	`d3f6d84113a04e625d05f55d8d405f13`
BLAKE2b-256	`3d7a2dc79e89eee6e103a4e395321191249b16f6ec42f16474816b722cdf7368`

Algorithm	Hash digest
SHA256	`d854c77cd2013498666b5e3810a2955a777abca487d6804ff0758be5aa08f106`
MD5	`5d9ee468408f25ba535e33c5aed69d9d`
BLAKE2b-256	`2bee66a6201d4fa4c6ce90eb7bf78b80431a1721b3d79f2b7095849831b9b306`

Algorithm	Hash digest
SHA256	`285308f39129e32810f7a38f0a06f3e54ed1d15036651fae93dceee0375de852`
MD5	`b24cf7bb833debd96bdde32a4b2e9c1f`
BLAKE2b-256	`8bc13e372cc8ea1c57c4b8bd74ed2cf8c29047eacc76deaecadb5d180f9a8259`

Algorithm	Hash digest
SHA256	`ec50d8636768b18b0daaf756046e2ad0eb9f60472263f01c1384b9a255b7b196`
MD5	`e3a175a87f34ab320061d930da7852ff`
BLAKE2b-256	`2fd71bdf6f31b748faf00d18f8a0b12b07c86f75f662c0b25b41a6761e976ffd`

Algorithm	Hash digest
SHA256	`efead65e2ec903749f10ae65aedb2e77c0b6e58f810e9f1007b4197e02479b0b`
MD5	`5df35aadb6521f94a73d365599190a94`
BLAKE2b-256	`094cb2cce3f0fa524f8065edffbfcd7051c2a3c5f9fb8dae7614284acf950540`

Algorithm	Hash digest
SHA256	`fce78766b46e0573e6ff2a70a54e3da00cd20c4a59e5a4a3638be87822fccdc8`
MD5	`3541ac4da93e02bc491a0fdbcd31e20f`
BLAKE2b-256	`a51bdd426b39f7d82eb75714a6d33bb583d33beb8b466cd334a42b447354bc17`

Algorithm	Hash digest
SHA256	`3bd7d175952b77834becde5c5ec97895311930a757fa16cb5ac7c1442e888b4b`
MD5	`79ea4dad2e2e729590caadc29c4720d3`
BLAKE2b-256	`e2456604600394192d65d20402d839a59da3f3c44fa017ba332581ef37d00c43`

Algorithm	Hash digest
SHA256	`96db8d365b5805e007b57939105903cbd3dfa9b919908feda5d3e962cd496213`
MD5	`326c8b8636c546892760685918d8bbe0`
BLAKE2b-256	`48537f50f602de4466236215cc3fcf0171f39b27b19892da39d6ee850494dc34`

Algorithm	Hash digest
SHA256	`f789d6d5923ef10e96737e8bcd27d226f1eff7076b470261fe597d3fd3a1b637`
MD5	`f4385d567a751257ded87d0feb365cee`
BLAKE2b-256	`fa04885455047e26dae4f2ecbed0a4de229c0244977d37b3555f24e97a32f9de`

Algorithm	Hash digest
SHA256	`0666a35b6ef622d44abac9a3cb139e33b1e09c937b0b21edb4313cc3f787d4d0`
MD5	`ce8667c3b148c837b8181f32d4b967e7`
BLAKE2b-256	`0aeee4931280909d7712c14e387b6566928fd2895044e48415e20d6b80286da1`

Algorithm	Hash digest
SHA256	`d4a91717ef577b3b775c847a44e90a5eabede8e4b4c0bc167e839e81cfca4cf9`
MD5	`4391524fd743d718dd485fe79447c58a`
BLAKE2b-256	`914eee29fca06ad403d72fb02f11adc3c2af1cbc61277595999d2fd98f1f961c`

Algorithm	Hash digest
SHA256	`2f63a2387e4c2a60a94618729f3e7ed01eef816d9711744cd6cdc740cdc947ed`
MD5	`1fc330a0a9ac517a5de8c2cc6e85ff1c`
BLAKE2b-256	`428fe46746283c6b3e69a7f185be07c0942851b4942ffbe794834fbd7a750752`

Algorithm	Hash digest
SHA256	`a58eaabe5716519481af2a166f4f7f4a6418a040f2909d6eaf4cb8cae02825d1`
MD5	`89527b143bdd78ce791135ea44a0bcbc`
BLAKE2b-256	`894122d55240eb0b537789ae2822a60557316eebcf123c9f67b537dd1390e256`

Algorithm	Hash digest
SHA256	`c6f92183b482f3df2ee5bce2be98a923e19eeebfa25e95fa5ea5c45fe75847da`
MD5	`72f666b73ef0e0af270e9bf8eb367fef`
BLAKE2b-256	`8f01312c9c73293c0bb84567892058738318f9767afda1fd7a525fa7b181654b`

Algorithm	Hash digest
SHA256	`d4cc979b6f5586d9bcfde2687bfcfcbf7fa1afc95477a203b522162521aa3e7c`
MD5	`a00ea5df7e15f33620cb3a4a0949e344`
BLAKE2b-256	`41aa7c4024a59ec1f509cc29e57ab26959141556502433ff2e82bf438853a6e7`

Algorithm	Hash digest
SHA256	`1a5a29d454f90a07018b79f18ee6c1b7eb48d3e567efe3428aa74fb74de684d1`
MD5	`ceeaf8df5a30d19a2c8af60ca2af80e9`
BLAKE2b-256	`173a041f4e7550301b56f4ba2d0a87b7db04dc6fc551faa16c6e39011ad6ae1d`

onnxruntime_extensions 0.7.0

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

ONNXRuntime-Extensions

What's ONNXRuntime-Extensions

Quickstart with the experimental Python package

on Windows

on Linux/macOS

Usage

1. Augment an ONNX model with a pre- and post-processing pipeline

2. Using Extensions for ONNX Runtime inference

Python

C++

Java

Use exporters to generate graphs with custom operators

Add a new custom operator to onnxruntime-extensions

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

File details

File metadata