Skip to main content

Convert scikit-learn models to ONNX

Project description

Introduction

sklearn-onnx converts scikit-learn models to ONNX. Once in the ONNX format, you can use tools like ONNX Runtime for high performance scoring. All converters are tested with onnxruntime.

Documentation

Full documentation including tutorials is available at https://onnx.ai/sklearn-onnx/. Supported scikit-learn Models Last supported opset is 15.

You may also find answers in existing issues or submit a new one.

Installation

You can install from PyPi:

pip install skl2onnx

Or you can install from the source with the latest changes.

pip install git+https://github.com/onnx/sklearn-onnx.git

Contribute

We welcome contributions in the form of feedback, ideas, or code.

License

Apache License v2.0

Project details


Download files

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

Source Distribution

skl2onnx-1.10.3.tar.gz (858.2 kB view details)

Uploaded Source

Built Distribution

skl2onnx-1.10.3-py2.py3-none-any.whl (272.0 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file skl2onnx-1.10.3.tar.gz.

File metadata

  • Download URL: skl2onnx-1.10.3.tar.gz
  • Upload date:
  • Size: 858.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.6.0 importlib_metadata/4.6.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.9.5

File hashes

Hashes for skl2onnx-1.10.3.tar.gz
Algorithm Hash digest
SHA256 798933378145412b9876ab3ff2c1dd5f241a7296406d786262000afa8d329628
MD5 a7f6a7c3002a6d4b3c41abc343ede06b
BLAKE2b-256 db4a16571c58825a69b9a99f8462e0dcee76ba78de337add7ff134e2c2f63d8b

See more details on using hashes here.

File details

Details for the file skl2onnx-1.10.3-py2.py3-none-any.whl.

File metadata

  • Download URL: skl2onnx-1.10.3-py2.py3-none-any.whl
  • Upload date:
  • Size: 272.0 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.6.0 importlib_metadata/4.6.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.9.5

File hashes

Hashes for skl2onnx-1.10.3-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 908bccb2974b6ef852878b28a2a5e65cfe59c7572ea285aee46c64a4b6d2728a
MD5 b8963c2e00bc7ebee3db4dcf7d86f109
BLAKE2b-256 862d055c27bdbcfe8fca11ba901e9161349f608c70173632f8241914d56ed20f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page