Skip to main content

ONNX Runtime Runtime Python bindings

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 RandomForest
iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y)
clr = RandomForest()
clr.fit(X_train, y_train)

# Convert into ONNX format with onnxmltools
from onnxmltools import convert_sklearn
from onnxmltools.utils import save_model
from onnxmltools.convert.common.data_types import FloatTensorType
initial_type = [('float_input', FloatTensorType([1, 4]))]
onx = convert_sklearn(clr, initial_types=initial_type)
save_model(onx, "rf_iris.onnx")

# 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

0.1.4

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


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-0.1.4-cp37-cp37m-manylinux1_x86_64.whl (4.6 MB view hashes)

Uploaded CPython 3.7m

onnxruntime-0.1.4-cp37-cp37m-macosx_10_7_x86_64.whl (4.0 MB view hashes)

Uploaded CPython 3.7m macOS 10.7+ x86-64

onnxruntime-0.1.4-cp36-cp36m-win_amd64.whl (2.8 MB view hashes)

Uploaded CPython 3.6m Windows x86-64

onnxruntime-0.1.4-cp36-cp36m-manylinux1_x86_64.whl (4.6 MB view hashes)

Uploaded CPython 3.6m

onnxruntime-0.1.4-cp36-cp36m-macosx_10_7_x86_64.whl (4.0 MB view hashes)

Uploaded CPython 3.6m macOS 10.7+ x86-64

onnxruntime-0.1.4-cp35-cp35m-win_amd64.whl (2.8 MB view hashes)

Uploaded CPython 3.5m Windows x86-64

onnxruntime-0.1.4-cp35-cp35m-manylinux1_x86_64.whl (4.6 MB view hashes)

Uploaded CPython 3.5m

onnxruntime-0.1.4-cp35-cp35m-macosx_10_6_x86_64.whl (4.0 MB view hashes)

Uploaded CPython 3.5m macOS 10.6+ x86-64

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