Open Neural Network Exchange

Project description

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Currently we focus on the capabilities needed for inferencing (scoring).

ONNX is widely supported and can be found in many frameworks, tools, and hardware. Enabling interoperability between different frameworks and streamlining the path from research to production helps increase the speed of innovation in the AI community. We invite the community to join us and further evolve ONNX.

Use ONNX

Learn about the ONNX spec

Programming utilities for working with ONNX Graphs

Contribute

ONNX is a community project. We encourage you to join the effort and contribute feedback, ideas, and code. You can participate in the SIGs and Working Groups to shape the future of ONNX.

Check out our contribution guide to get started.

If you think some operator should be added to ONNX specification, please read this document.

Discuss

We encourage you to open Issues, or use Slack for more real-time discussion

Stay up to date with the latest ONNX news. [Facebook] [Twitter]

Installation

Official Python packages

ONNX released packages are published in PyPi.

pip install numpy protobuf==3.16.0
pip install onnx

Weekly packages are published in test pypi to enable experimentation and early testing.

Conda packages

A binary build of ONNX is available from Conda, in conda-forge:

conda install -c conda-forge numpy protobuf==3.16.0 libprotobuf=3.16.0
conda install -c conda-forge onnx

You can also use the onnx-dev docker image for a Linux-based installation without having to worry about dependency versioning.

Build ONNX from Source

Before building from source uninstall any existing versions of onnx pip uninstall onnx.
If you are building ONNX from source, it is recommended that you also build Protobuf locally as a static library. Specifically on Windows, the version distributed with conda-forge is a DLL, but ONNX expects it to be a static library. Building protobuf locally also let's you control the verison of protobuf. The tested and recommended version is 3.16.0.

Note for Windows : The instructions in this README assume you are using Visual Studio. It is recommended that you run all the commands from a shell started from "Developer Command Prompt for VS 2019" and keep the build system generator for cmake (e.g., cmake -G "Visual Studio 16 2019") consistent while building protobuf as well as ONNX.

git clone https://github.com/onnx/onnx.git
cd onnx
git submodule update --init --recursive
# prefer lite proto
set CMAKE_ARGS=-DONNX_USE_LITE_PROTO=ON
pip install -e .

Building Protobuf from source

Windows

git clone https://github.com/protocolbuffers/protobuf.git
cd protobuf
git checkout v3.16.0
cd cmake
cmake -G "Visual Studio 16 2019" -A x64 -DCMAKE_INSTALL_PREFIX=<protobug_install_dir> -Dprotobuf_MSVC_STATIC_RUNTIME=ON -Dprotobuf_BUILD_SHARED_LIBS=OFF -Dprotobuf_BUILD_TESTS=OFF -Dprotobuf_BUILD_EXAMPLES=OFF .
msbuild protobuf.sln /m /p:Configuration=Release
msbuild INSTALL.vcxproj /p:Configuration=Release

Linux

git clone https://github.com/protocolbuffers/protobuf.git
cd protobuf
git checkout v3.16.0
git submodule update --init --recursive
mkdir build_source && cd build_source
cmake ../cmake -Dprotobuf_BUILD_SHARED_LIBS=OFF -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_INSTALL_SYSCONFDIR=/etc -DCMAKE_POSITION_INDEPENDENT_CODE=ON -Dprotobuf_BUILD_TESTS=OFF -DCMAKE_BUILD_TYPE=Release
make -j$(nproc)
make install

Mac

export NUM_CORES=`sysctl -n hw.ncpu`
brew update
brew install autoconf && brew install automake
wget https://github.com/protocolbuffers/protobuf/releases/download/v3.16.0/protobuf-cpp-3.16.0.tar.gz
tar -xvf protobuf-cpp-3.16.0.tar.gz
cd protobuf-3.16.0
mkdir build_source && cd build_source
cmake ../cmake -Dprotobuf_BUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON -Dprotobuf_BUILD_TESTS=OFF -DCMAKE_BUILD_TYPE=Release
make -j${NUM_CORES}
make install

Once build is successful, update PATH to include protobuf paths. Example on Windows:
set PATH=<protobuf_install_dir>\bin;<protobuf_install_dir>\include;<protobuf_install_dir>\libs;%PATH%

Build ONNX on ARM 64

If you are building ONNX on an ARM 64 device, please make sure to install the dependencies appropriately.

pip install cython protobuf numpy
sudo apt-get install libprotobuf-dev protobuf-compiler
pip install onnx

Verify Installation

After installation, run

python -c "import onnx"

to verify it works.

Common Build Options

For full list refer to CMakeLists.txt
Environment variables

USE_MSVC_STATIC_RUNTIME should be 1 or 0, not ON or OFF. When set to 1 onnx links statically to runtime library.
Default: USE_MSVC_STATIC_RUNTIME=1
DEBUG should be 0 or 1. When set to 1 onnx is built in debug mode. or debug versions of the dependencies, you need to open the CMakeLists file and append a letter d at the end of the package name lines. For example, NAMES protobuf-lite would become NAMES protobuf-lited.
Default: Debug=0

CMake variables

ONNX_USE_PROTOBUF_SHARED_LIBS should be ON or OFF.
Default: ONNX_USE_PROTOBUF_SHARED_LIBS=OFF USE_MSVC_STATIC_RUNTIME=1
ONNX_USE_PROTOBUF_SHARED_LIBS determines how onnx links to protobuf libraries.
- When set to ON - onnx will dynamically link to protobuf shared libs, PROTOBUF_USE_DLLS will be defined as described here, Protobuf_USE_STATIC_LIBS will be set to OFF and USE_MSVC_STATIC_RUNTIME must be 0.
- When set to OFF - onnx will link statically to protobuf, and Protobuf_USE_STATIC_LIBS will be set to ON (to force the use of the static libraries) and USE_MSVC_STATIC_RUNTIME can be 0 or 1.
ONNX_USE_LITE_PROTO should be ON or OFF. When set to ON onnx uses lite protobuf instead of full protobuf.
Default: ONNX_USE_LITE_PROTO=OFF
ONNX_WERROR should be ON or OFF. When set to ON warnings are treated as errors.
Default: ONNX_WERROR=OFF in local builds, ON in CI and release pipelines.

Common Errors

Note: the import onnx command does not work from the source checkout directory; in this case you'll see ModuleNotFoundError: No module named 'onnx.onnx_cpp2py_export'. Change into another directory to fix this error.
Building ONNX on Ubuntu works well, but on CentOS/RHEL and other ManyLinux systems, you might need to open the CMakeLists file and replace all instances of /lib with /lib64.

Testing

ONNX uses pytest as test driver. In order to run tests, you will first need to install pytest:

pip install pytest nbval

After installing pytest, use the following command to run tests.

pytest

Development

Check out the contributor guide for instructions.

License

Apache License v2.0

Code of Conduct

ONNX Open Source Code of Conduct

Project details

Release history Release notifications | RSS feed

1.17.0

Oct 1, 2024

1.16.2

Aug 1, 2024

1.16.1

May 23, 2024

1.16.0

Mar 25, 2024

1.15.0

Oct 26, 2023

1.14.1

Aug 25, 2023

1.14.0

May 4, 2023

1.13.1

Feb 22, 2023

1.13.0

Dec 12, 2022

1.12.0

Jun 18, 2022

1.11.0

Feb 17, 2022

This version

1.10.2

Oct 26, 2021

1.10.1

Aug 2, 2021

1.10.0

Jul 31, 2021

1.9.0

Apr 19, 2021

1.8.1

Jan 29, 2021

1.8.0

Nov 6, 2020

1.7.0

May 8, 2020

1.6.0

Sep 28, 2019

1.5.0

Apr 24, 2019

1.4.1

Jan 23, 2019

1.4.0

Jan 23, 2019

1.3.0

Aug 30, 2018

1.2.3

Sep 10, 2018

1.2.2

Jun 19, 2018

1.2.1

May 25, 2018

1.1.2

Apr 27, 2018

1.1.1

Mar 22, 2018

1.1.0

Mar 21, 2018

1.0.1

Jan 26, 2018

1.0.0

Dec 4, 2017

0.2.1

Oct 25, 2017

0.2

Oct 10, 2017

0.1

Sep 7, 2017

Download files

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

Source Distribution

onnx-1.10.2.tar.gz (9.9 MB view details)

Uploaded Oct 26, 2021 Source

Built Distributions

onnx-1.10.2-cp39-cp39-win_amd64.whl (11.4 MB view details)

Uploaded Oct 26, 2021 CPython 3.9 Windows x86-64

onnx-1.10.2-cp39-cp39-win32.whl (11.3 MB view details)

Uploaded Oct 26, 2021 CPython 3.9 Windows x86

onnx-1.10.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.9 manylinux: glibc 2.17+ ARM64

onnx-1.10.2-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.9 manylinux: glibc 2.12+ x86-64

onnx-1.10.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl (12.8 MB view details)

Uploaded Oct 26, 2021 CPython 3.9 manylinux: glibc 2.12+ i686

onnx-1.10.2-cp39-cp39-macosx_10_12_x86_64.whl (12.1 MB view details)

Uploaded Oct 26, 2021 CPython 3.9 macOS 10.12+ x86-64

onnx-1.10.2-cp38-cp38-win_amd64.whl (11.4 MB view details)

Uploaded Oct 26, 2021 CPython 3.8 Windows x86-64

onnx-1.10.2-cp38-cp38-win32.whl (11.3 MB view details)

Uploaded Oct 26, 2021 CPython 3.8 Windows x86

onnx-1.10.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.8 manylinux: glibc 2.17+ ARM64

onnx-1.10.2-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.8 manylinux: glibc 2.12+ x86-64

onnx-1.10.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl (12.8 MB view details)

Uploaded Oct 26, 2021 CPython 3.8 manylinux: glibc 2.12+ i686

onnx-1.10.2-cp38-cp38-macosx_10_12_x86_64.whl (12.1 MB view details)

Uploaded Oct 26, 2021 CPython 3.8 macOS 10.12+ x86-64

onnx-1.10.2-cp37-cp37m-win_amd64.whl (11.4 MB view details)

Uploaded Oct 26, 2021 CPython 3.7m Windows x86-64

onnx-1.10.2-cp37-cp37m-win32.whl (11.3 MB view details)

Uploaded Oct 26, 2021 CPython 3.7m Windows x86

onnx-1.10.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.7m manylinux: glibc 2.17+ ARM64

onnx-1.10.2-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.7m manylinux: glibc 2.12+ x86-64

onnx-1.10.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl (12.8 MB view details)

Uploaded Oct 26, 2021 CPython 3.7m manylinux: glibc 2.12+ i686

onnx-1.10.2-cp37-cp37m-macosx_10_12_x86_64.whl (12.1 MB view details)

Uploaded Oct 26, 2021 CPython 3.7m macOS 10.12+ x86-64

onnx-1.10.2-cp36-cp36m-win_amd64.whl (11.4 MB view details)

Uploaded Oct 26, 2021 CPython 3.6m Windows x86-64

onnx-1.10.2-cp36-cp36m-win32.whl (11.3 MB view details)

Uploaded Oct 26, 2021 CPython 3.6m Windows x86

onnx-1.10.2-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.6m manylinux: glibc 2.17+ ARM64

onnx-1.10.2-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (12.7 MB view details)

Uploaded Oct 26, 2021 CPython 3.6m manylinux: glibc 2.12+ x86-64

onnx-1.10.2-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.whl (12.8 MB view details)

Uploaded Oct 26, 2021 CPython 3.6m manylinux: glibc 2.12+ i686

onnx-1.10.2-cp36-cp36m-macosx_10_12_x86_64.whl (12.1 MB view details)

Uploaded Oct 26, 2021 CPython 3.6m macOS 10.12+ x86-64

File details

Details for the file onnx-1.10.2.tar.gz.

File metadata

Download URL: onnx-1.10.2.tar.gz
Upload date: Oct 26, 2021
Size: 9.9 MB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.0 CPython/3.8.6

File hashes

Hashes for onnx-1.10.2.tar.gz
Algorithm	Hash digest
SHA256	`24d73ca7dfd7e6c7339944f89554b4010719899337924fca1447d8f1b5db50d6`
MD5	`beb027e7efd88ce5f03ff31564dc915c`
BLAKE2b-256	`166abdae938babb4bc23de7b599439f3d1f1179748385e4ced099f3b4cb646bd`

Algorithm	Hash digest
SHA256	`0c176ef6e0c3b6bdfb69a43a66dcb8e6ba687437e302c79b4efb75027e1007dc`
MD5	`838030ee1d6acbcc4e51e7d8d6151930`
BLAKE2b-256	`328bf6ba84a47fcdc58645822c68bf3d31e7589a4bd4445961e6a043fe41810a`

Algorithm	Hash digest
SHA256	`253fd36cbcfcbbbe00e55dde7a09995b22fc2cc825f6de28e5ef9c47f581f264`
MD5	`88e074a96938fd921b2bf35d37ac0279`
BLAKE2b-256	`141f9179cbb3452260ebf6206cdef186c2982ef7f7ab8a6e3be1724b5a2c3bb5`

Algorithm	Hash digest
SHA256	`ce14dbe32a250b7691751e809c232b9a206da138ac055e24b9e60a1500b4d5b8`
MD5	`486e60b3bdd464d32104bf650c489167`
BLAKE2b-256	`de689d5e58df85275f86e8805d6d243d0cc417e8e8612ea85fcfdcf154cd2299`

Algorithm	Hash digest
SHA256	`526de93b57dd65b136bec85d5b4c6fa4455d6d817bb319b54797d29111b9c407`
MD5	`ab071db19888eb83131b20f076cdf8c1`
BLAKE2b-256	`2e12c4b674795f0874190c43a0e32aa307e5deb0f441b8c9b442811cf673acd8`

Algorithm	Hash digest
SHA256	`38e7d106fa98921faf909c2908bfd022eb2c594ecfbd275b60f80e0161cb8476`
MD5	`190960ba6b1e1224e65acafb142c9be3`
BLAKE2b-256	`d534ae4110fcdbaccd8532be1e8dbd66292f55b131d039da5c04432bae18a69c`

Algorithm	Hash digest
SHA256	`4138093cbf11e4300b7a7679aedfe1972f81abeb284a731e90dffdf3ef6c5ca3`
MD5	`e412a25b24937cbf4edb7c4c22e044f7`
BLAKE2b-256	`adcafa01efd6657ac10645202afcf2a2b01e96ab3d5f9b845fb1b14fdd03bd7e`

Algorithm	Hash digest
SHA256	`d0a3951276ac83fde93632303ad0b3b69e10894b69b7fe5eab0361e4f4212627`
MD5	`cbce125a4a229f0108b2405dd79d097c`
BLAKE2b-256	`7eb4a71d0a1a1bc584eb7969a3e22aff9536defae16937f6d1dd256337f2a487`

Algorithm	Hash digest
SHA256	`57f93db536766b1dcfeee583c02bd86c9f1c9a652253bd4f9bf189a39446de1c`
MD5	`3a66ab7f230acfcebd952254d9d46afe`
BLAKE2b-256	`76f0405820a950aa7e3d3515671649738f811b2f5b617cda37c3d87f13fb9030`

Algorithm	Hash digest
SHA256	`bd31e61ba95c62548543d8de2007fcb18fd2f017a9a36f712bbc08ddad1f25f4`
MD5	`bed98a93dc84dc2044770fbb2fd88a9b`
BLAKE2b-256	`cdffa6dd7a3da6df92e7613c16f9b49405e9cc1fdb2a2d772af3204f729e5da2`

Algorithm	Hash digest
SHA256	`a86e3f956e2a1d39772ae36d28c5b7f20fb6a883ae35971ada261b25548a8b32`
MD5	`ec75cd90004e8bc0187f05232243389e`
BLAKE2b-256	`fa4fff18d9c32b1b1b3a3b93b9984e36efca847aeb133922e73fd309a6238960`

Algorithm	Hash digest
SHA256	`4a53055b8f13747b607dbf835914c2bd60fa7214ee719893b003ceb5fc903220`
MD5	`222c61cb09da4c2ab782a42b20b03a03`
BLAKE2b-256	`2a13f88364d896207b54451106d19ff997eeafefea43678529e8248e13178a4b`

Algorithm	Hash digest
SHA256	`3b73128c269ef84694099dad2b06568f2672ce95761a51e0225401695dc2c136`
MD5	`1381a7ff0ef4d7b80a20968973234559`
BLAKE2b-256	`e81e7f8029e3fa97bc2c6550fe8c702c8f2c0ecfcf0b704150cf1b2f4fd6c14a`

Algorithm	Hash digest
SHA256	`24e654cca4c7285ea339fae15998dd33a5b9e57831d8ecb0bdb1f439c61c5736`
MD5	`794d2679f5639d0532f2f1bab0ce2072`
BLAKE2b-256	`5f4790ad6657d02221941efef6a8d031d50c93c0111c2242a8ae44e86ebf81ab`

Algorithm	Hash digest
SHA256	`796fa0b80f108f2824cccf5c7298895a925aaea7831330a0bd720ceffc7be3c6`
MD5	`3baf02f3c551e6374d4ef316633d6af4`
BLAKE2b-256	`98982c3c432042eeaf80deff7fbfe98b8d513e47520bea6b194053bf3a3170a9`

Algorithm	Hash digest
SHA256	`cc830b15fe11846911fdf068460fd5f20b0f711c8b4c575c68478a6bf2884304`
MD5	`fc9927810ef985c26c5d33e970e884ab`
BLAKE2b-256	`319055cbc652ca35eb78a8caa6bf8ec6b73b4fccb22fcaccc81a01aaf0ee386a`

Algorithm	Hash digest
SHA256	`6205849c935837a934a9ec1fd994f1e858ad7d253e02d0bacbe4add211e4255d`
MD5	`1f23747f537b3221a98952acae8aa321`
BLAKE2b-256	`bf45485394be214020c1dd137d3f5b82b5135d18f2bd6e2a802257b3bafea00f`

Algorithm	Hash digest
SHA256	`1e2f92a77d84ae84d25ac84ec84a77b53e427cc7b2eb72ed7d56f2204f885715`
MD5	`a3db93047e178716d3a42db4e94f50f8`
BLAKE2b-256	`abaa4d4498c2303185cb149bf0ed80f4b9f400d93a123ca3d9bcf6dbbb07b2c6`

Algorithm	Hash digest
SHA256	`358fc6f71841e30ca793a0c1bcd3d0b9c62e436e215773e77a301acb6106cbda`
MD5	`a87c4f3817c3cb7510a652298ee23313`
BLAKE2b-256	`0549efde13eb3eed970ee00048807af4a13e06cf064e129b582e03fa4b166b56`

Algorithm	Hash digest
SHA256	`7e59a6da6e437488059080babc9d96cde7c929cc758ffe4b0171aceaea559ada`
MD5	`5914bd5d8354c3142fe6276406cc652a`
BLAKE2b-256	`13631569d92d756b3d140262a4c0af78d081f42c24ad2eec4454de89b9480f58`

Algorithm	Hash digest
SHA256	`63aee84aed68c8e14583af48c79d99405844034043dee1efbd1937a78dfa7f6b`
MD5	`0fe458a53d28099878ba8ad0fcf604ec`
BLAKE2b-256	`4244daf23013f718c4e7d5fce7ba9dcf0ffd6bd52c33abba8c1afff5f61a684a`

onnx 1.10.2

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Project description

Use ONNX

Learn about the ONNX spec

Programming utilities for working with ONNX Graphs

Contribute

Discuss

Follow Us

Installation

Official Python packages

Conda packages

Build ONNX from Source

Building Protobuf from source

Build ONNX on ARM 64

Verify Installation

Common Build Options

Common Errors

Testing

Development

License

Code of Conduct

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Release history Release notifications | RSS feed

Download files

Source Distribution

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

Algorithm	Hash digest
SHA256	`48a747b247bc626e049341b8e8c4aeac20aa2306d6b8dff9c9e53a6b14931f1e`
MD5	`55ca737004951c3db89b4bd45723fb16`
BLAKE2b-256	`e27ee00c2471f35ca39df404ff4ab878aacd1dc855beed95657a4d87a9280996`

Algorithm	Hash digest
SHA256	`186abf5e9189b4b011da290c6d83d5499adefac8f6a07f5d596a192b4c911098`
MD5	`1f01fa89f4dcbcc6a28f91b312a0aaba`
BLAKE2b-256	`a5888fda38a7ae5f73c8f996b994377596205db8dc22a099da523383da9f8f36`

Algorithm	Hash digest
SHA256	`86baab35fc1a317369f2a0cd3816c0eeb9036c29f9a27ed5e8f6935e67cbf0a8`
MD5	`136660f9cadaf0aadf4247f37ec42162`
BLAKE2b-256	`ad442e58a98f2092b8da9b2b6b47c598fb54bdb65737dc8845b3f7d02b1dcffd`

Algorithm	Hash digest
SHA256	`898915bcba9c1d54abef00f4ea7d60e59fdb2d21d49e7493acac40c121eca4df`
MD5	`96988f1822dc7d6d81d11f0c31592b0a`
BLAKE2b-256	`dfb1079de495b50d0d8ebfe3c1b804b40eaca0452c8eb69f6845cac63e572787`