ONNX Runtime Python bindings

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for microsoft from gravatar.com microsoft

Unverified details

These details have not been verified by PyPI
Meta
Classifiers

Project description

ONNX Runtime enables high-performance evaluation of trained machine learning (ML) models while keeping resource usage low. Building on Microsoft’s dedication to the Open Neural Network Exchange (ONNX) community, it supports traditional ML models as well as Deep Learning algorithms in the ONNX-ML format. Documentation is available at Python Bindings for ONNX Runtime.

Example

The following example demonstrates an end-to-end example in a very common scenario. A model is trained with scikit-learn but it has to run very fast in a optimized environment. The model is then converted into ONNX format and ONNX Runtime replaces scikit-learn to compute the predictions.

# Train a model.
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y)
clr = RandomForestClassifier()
clr.fit(X_train, y_train)

# Convert into ONNX format with onnxmltools
from skl2onnx import convert_sklearn
from skl2onnx.common.data_types import FloatTensorType
initial_type = [('float_input', FloatTensorType([1, 4]))]
onx = convert_sklearn(clr, initial_types=initial_type)
with open("rf_iris.onnx", "wb") as f:
    f.write(onx.SerializeToString())

# Compute the prediction with ONNX Runtime
import onnxruntime as rt
import numpy
sess = rt.InferenceSession("rf_iris.onnx")
input_name = sess.get_inputs()[0].name
label_name = sess.get_outputs()[0].name
pred_onx = sess.run([label_name], {input_name: X_test.astype(numpy.float32)})[0]

Changes

0.4.0

Release Notes : https://github.com/Microsoft/onnxruntime/releases/tag/v0.4.0

0.3.1

Protobuf-lite, NuGet file fixes (patch to 0.3.0).

0.3.0

C-API, Linux support for Dotnet Nuget package, Cuda 9.1 support.

0.2.1

C-API, Linux support for Dotnet Nuget package, Cuda 10.0 support (patch to 0.2.0).

0.2.0

C-API, Linux support for Dotnet Nuget package, Cuda 10.0 support

0.1.5

GA release as part of open sourcing onnxruntime (patch to 0.1.4).

0.1.4

GA release as part of open sourcing onnxruntime.

0.1.3

Fixes a crash on machines which do not support AVX instructions.

0.1.2

First release on Ubuntu 16.04 for CPU and GPU with Cuda 9.1 and Cudnn 7.0, supports runtime for deep learning models architecture such as AlexNet, ResNet, XCeption, VGG, Inception, DenseNet, standard linear learner, standard ensemble learners, and transform scaler, imputer.

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for microsoft from gravatar.com microsoft

Unverified details

These details have not been verified by PyPI
Meta
Classifiers

Release history Release notifications | RSS feed

1.20.1

1.20.0

1.19.2

1.19.0

1.18.1

1.18.0

1.17.3

1.17.1

1.17.0

1.16.3

1.16.2

1.16.1

1.16.0

1.15.1

1.15.0

1.14.1

1.14.0

1.13.1

1.12.1

1.12.0

1.11.1

1.11.0

1.10.0

1.9.0

1.8.1

1.8.0

1.7.0

1.6.0

1.5.2

1.5.1

1.4.0

1.3.0

1.2.0

1.1.2

1.1.1

1.1.0

1.0.0

0.5.0

This version

0.4.0

0.3.0

0.2.1

0.1.4

0.1.3

0.1.2

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-0.4.0-cp37-cp37m-win_amd64.whl (1.9 MB view details)

Uploaded CPython 3.7m Windows x86-64

onnxruntime-0.4.0-cp37-cp37m-manylinux1_x86_64.whl (3.1 MB view details)

Uploaded CPython 3.7m

onnxruntime-0.4.0-cp37-cp37m-macosx_10_7_x86_64.whl (2.5 MB view details)

Uploaded CPython 3.7m macOS 10.7+ x86-64

onnxruntime-0.4.0-cp36-cp36m-win_amd64.whl (1.9 MB view details)

Uploaded CPython 3.6m Windows x86-64

onnxruntime-0.4.0-cp36-cp36m-manylinux1_x86_64.whl (3.1 MB view details)

Uploaded CPython 3.6m

onnxruntime-0.4.0-cp36-cp36m-macosx_10_7_x86_64.whl (2.5 MB view details)

Uploaded CPython 3.6m macOS 10.7+ x86-64

onnxruntime-0.4.0-cp35-cp35m-win_amd64.whl (1.9 MB view details)

Uploaded CPython 3.5m Windows x86-64

onnxruntime-0.4.0-cp35-cp35m-manylinux1_x86_64.whl (3.1 MB view details)

Uploaded CPython 3.5m

onnxruntime-0.4.0-cp35-cp35m-macosx_10_6_x86_64.whl (2.5 MB view details)

Uploaded CPython 3.5m macOS 10.6+ x86-64

File details

Details for the file onnxruntime-0.4.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 1.9 MB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 ddcbde5acf3e4720cf9a870c3fec897ce06bacf805bc9406b96cf3d9bebfeb56
MD5 8a194d735d002cc7b2c899f55d30d2a7
BLAKE2b-256 a12b222209ff75a70e56114b927b1e970a8de77d36d932f2eb453ae55d7db173

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp37-cp37m-manylinux1_x86_64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp37-cp37m-manylinux1_x86_64.whl
  • Upload date:
  • Size: 3.1 MB
  • Tags: CPython 3.7m
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp37-cp37m-manylinux1_x86_64.whl
Algorithm Hash digest
SHA256 9f94d2754814d436fd948d3b1771d27e75bc8e0b29398df51e588c0a53accd59
MD5 6e911cb42e598bfe555c78de9620477a
BLAKE2b-256 5f6912e7048508193cb9cebca27202c247cc847e75ab7894a21513debdb2d935

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp37-cp37m-macosx_10_7_x86_64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp37-cp37m-macosx_10_7_x86_64.whl
  • Upload date:
  • Size: 2.5 MB
  • Tags: CPython 3.7m, macOS 10.7+ x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp37-cp37m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 af38d0c4557eb9e7fef2d239238c16f02533721820744450150198fd6e06bb7d
MD5 9d40932ae9b6e2b41c20068394ba0365
BLAKE2b-256 a55f103ce0a167892c3924842079b05acc63a6697b4823e261ad6ebf759448e5

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 1.9 MB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 7927adf4f3e0299a059037d907afbdba7da579e595901b478364b697adec07a5
MD5 ce0c6429cca254c7f68c4c8a668392e4
BLAKE2b-256 af2b003820bfc750b8e11bff1d6842a0d4303d24f31b544304e2874a55742cd8

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp36-cp36m-manylinux1_x86_64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp36-cp36m-manylinux1_x86_64.whl
  • Upload date:
  • Size: 3.1 MB
  • Tags: CPython 3.6m
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp36-cp36m-manylinux1_x86_64.whl
Algorithm Hash digest
SHA256 8cc015c27731f61257661a8f9eff83ed63e7df8e20df9d3abb5126140396f8bc
MD5 4302cb133c1a0228af3a580e8b22e36d
BLAKE2b-256 fae11548ef61a5c3b583c7ce777c9f38e30b7fdeda309ddcc886b5883cba5771

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp36-cp36m-macosx_10_7_x86_64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp36-cp36m-macosx_10_7_x86_64.whl
  • Upload date:
  • Size: 2.5 MB
  • Tags: CPython 3.6m, macOS 10.7+ x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp36-cp36m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 01e961e558aa9fc678cd2f2046a901f9a8ce392d7f9286d0adb68c1e43cf284b
MD5 d1151491c2393af19dd188ffb4aa5c5d
BLAKE2b-256 0188d0b731180d958e7505d146fad23927df5c87997017ea3fb0def4f62ee187

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp35-cp35m-win_amd64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp35-cp35m-win_amd64.whl
  • Upload date:
  • Size: 1.9 MB
  • Tags: CPython 3.5m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp35-cp35m-win_amd64.whl
Algorithm Hash digest
SHA256 6344d54d66badb9d9c7dc767b416faf2e32ab12e0779a68ced08e24ef726be3c
MD5 6cd15d29884a07cc38ec7247df29b925
BLAKE2b-256 4363dbba09de81d1756b116b220f4183309c67234a32b7ff28d46936681d90e9

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp35-cp35m-manylinux1_x86_64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp35-cp35m-manylinux1_x86_64.whl
  • Upload date:
  • Size: 3.1 MB
  • Tags: CPython 3.5m
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp35-cp35m-manylinux1_x86_64.whl
Algorithm Hash digest
SHA256 afb57e7e43c5466208e8eb656d740eef85a98ccbba22831582a365a87336f25c
MD5 51810a1ecab95d2a5b3c44d49fc7d135
BLAKE2b-256 2418576d62d4c87b7d4f74872b4e48261017e0477211e7647080c31a9f8cd8cd

See more details on using hashes here.

File details

Details for the file onnxruntime-0.4.0-cp35-cp35m-macosx_10_6_x86_64.whl.

File metadata

  • Download URL: onnxruntime-0.4.0-cp35-cp35m-macosx_10_6_x86_64.whl
  • Upload date:
  • Size: 2.5 MB
  • Tags: CPython 3.5m, macOS 10.6+ x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.5

File hashes

Hashes for onnxruntime-0.4.0-cp35-cp35m-macosx_10_6_x86_64.whl
Algorithm Hash digest
SHA256 ddd311747060217e3d8b4a3c590fd1a25452d66e2e9f3894f3510ac26872ca6a
MD5 ee4146642792cfda3beb2f4fd0c5fe9b
BLAKE2b-256 2039af77ab5328b68977804d68ffd390e032835daf2a1051b4cc749b5a32d485

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