Install ONNX Runtime (ORT)

See the installation matrix for recommended instructions for desired combinations of target operating system, hardware, accelerator, and language.

Details on OS versions, compilers, language versions, dependent libraries, etc can be found under Compatibility.

Contents

• Python Installs
• C#/C/C++/WinML Installs
• Install on web and mobile
• ORT Training package
• Inference install table for all languages
• Training install table for all languages

Python Installs

Install ONNX Runtime (ORT)

pip install onnxruntime

pip install onnxruntime-gpu

Install ONNX to export the model

## ONNX is built into PyTorch
pip install torch

## tensorflow
pip install tf2onnx

## sklearn
pip install skl2onnx

C#/C/C++/WinML Installs

Install ONNX Runtime (ORT)

# CPU
dotnet add package Microsoft.ML.OnnxRuntime

# GPU
dotnet add package Microsoft.ML.OnnxRuntime.Gpu

# DirectML
dotnet add package Microsoft.ML.OnnxRuntime.DirectML

# WinML
dotnet add package Microsoft.AI.MachineLearning

Install on web and mobile

Unless stated otherwise, the installation instructions in this section refer to pre-built packages that include support for selected operators and ONNX opset versions based on the requirements of popular models. These packages may be referred to as “mobile packages”. If you use mobile packages, your model must only use the supported opsets and operators.

Another type of pre-built package has full support for all ONNX opsets and operators, at the cost of larger binary size. These packages are referred to as “full packages”.

If the pre-built mobile package supports your model/s but is too large, you can create a custom build. A custom build can include just the opsets and operators in your model/s to reduce the size.

If the pre-built mobile package does not include the opsets or operators in your model/s, you can either use the full package if available, or create a custom build.

JavaScript Installs

Install ONNX Runtime Web (browsers)

# install latest release version
npm install onnxruntime-web

# install nightly build dev version
npm install onnxruntime-web@dev

Install ONNX Runtime Node.js binding (Node.js)

# install latest release version
npm install onnxruntime-node

Install ONNX Runtime for React Native

# install latest release version
npm install onnxruntime-react-native

Install on iOS

In your CocoaPods Podfile, add the onnxruntime-c, onnxruntime-mobile-c, onnxruntime-objc, or onnxruntime-mobile-objc pod, depending on whether you want to use a full or mobile package and which API you want to use.

C/C++

  use_frameworks!

  # choose one of the two below:
  pod 'onnxruntime-c'  # full package
  #pod 'onnxruntime-mobile-c'  # mobile package

Objective-C

  use_frameworks!

  # choose one of the two below:
  pod 'onnxruntime-objc'  # full package
  #pod 'onnxruntime-mobile-objc'  # mobile package

Run pod install.

Custom build

Refer to the instructions for creating a custom iOS package.

Install on Android

Java/Kotlin

In your Android Studio Project, make the following changes to:

1. build.gradle (Project):

    repositories {
        mavenCentral()
    }
   

2. build.gradle (Module):

    dependencies {
        // choose one of the two below:
        implementation 'com.microsoft.onnxruntime:onnxruntime-android:latest.release'  // full package
        //implementation 'com.microsoft.onnxruntime:onnxruntime-mobile:latest.release'  // mobile package
    }
   

C/C++

Download the onnxruntime-android (full package) or onnxruntime-mobile (mobile package) AAR hosted at MavenCentral, change the file extension from .aar to .zip, and unzip it. Include the header files from the headers folder, and the relevant libonnxruntime.so dynamic library from the jni folder in your NDK project.

Custom build

Refer to the instructions for creating a custom Android package.

ORT Training package

pip install torch-ort
python -m torch_ort.configure

Note: This installs the default version of the torch-ort and onnxruntime-training packages that are mapped to specific versions of the CUDA libraries. Refer to the install options in ONNXRUNTIME.ai.

Add ORTModule in the train.py

   from torch_ort import ORTModule
   .
   .
   .
   model = ORTModule(model)

Note: the model where ORTModule is wrapped needs to be a derived from the torch.nn.Module class.

Inference install table for all languages

The table below lists the build variants available as officially supported packages. Others can be built from source from each release branch.

Requirements

• All builds require the English language package with en_US.UTF-8 locale. On Linux, install language-pack-en package by running locale-gen en_US.UTF-8 and update-locale LANG=en_US.UTF-8

• Windows builds require Visual C++ 2019 runtime.

• Please note additional requirements and dependencies in the table below:

Note: Dev builds created from the master branch are available for testing newer changes between official releases. Please use these at your own risk. We strongly advise against deploying these to production workloads as support is limited for dev builds.

Training install table for all languages

ONNX Runtime Training packages are available for different versions of PyTorch, CUDA and ROCm versions.

The install command is:

pip3 install torch-ort [-f location]
python 3 -m torch_ort.configure

The location needs to be specified for any specific version other than the default combination. The location for the different configurations are below: