onnxruntime/docs/tutorials/mobile/initial-setup.md
Edward Chen 3c9ca35f93
[Docs] Update mobile docs for 1.9 (#9237)
* Edgchen1/objc api reference 1.9 (#1)

* Update Objective-C API reference for 1.9.

* Update spelling.

* Test link changes.

* Fix links.

* Fix links and updates in mobile-performance-tuning.md.

* Fix links in tutorials/mobile/custom-build.md.

* Fix

* Fix

* Fix links in docs/tutorials/mobile/initial-setup.md.

* Fix links.

* Update note.

* Add 1.9 op type support page.

* Add nav info to page.

* Rename files to not have spaces.
2021-10-04 15:48:53 -07:00

115 lines
3.5 KiB
Markdown

---
title: Initial setup
parent: Deploy ONNX Runtime Mobile
grand_parent: Tutorials
has_children: false
nav_order: 2
---
{::options toc_levels="2..3" /}
## Contents
{: .no_toc}
* TOC
{:toc}
## Initial setup if using a pre-built package
### Android
##### Java/Kotlin
In your Android Studio Project, make the following changes to:
1. build.gradle (Project):
```
repositories {
mavenCentral()
}
```
2. build.gradle (Module):
```
dependencies {
implementation 'com.microsoft.onnxruntime:onnxruntime-mobile:<onnxruntime mobile version>'
}
```
##### C/C++
Download the onnxruntime-mobile AAR hosted at [MavenCentral](https://mvnrepository.com/artifact/com.microsoft.onnxruntime/onnxruntime-mobile), 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.
### iOS
In your CocoaPods `Podfile`, add the `onnxruntime-mobile-c` or `onnxruntime-mobile-objc` pod depending on which API you wish to use.
##### C/C++
```
use_frameworks!
pod 'onnxruntime-mobile-c'
```
##### Objective-C
```
use_frameworks!
pod 'onnxruntime-mobile-objc'
```
Run `pod install`.
### Install ONNX Runtime python package
Install the onnxruntime python package from [https://pypi.org/project/onnxruntime/](https://pypi.org/project/onnxruntime/) in order to convert models from ONNX format to the internal ORT format.
Version v1.8 or higher is required.
- `pip install onnxruntime` will install the latest release
## Initial setup if performing a custom build
### Clone ONNX Runtime repository
Use git to clone the ONNX Runtime repository
- `git clone --recursive https://github.com/Microsoft/onnxruntime`
- this will create an 'onnxruntime' directory with the repository contents
- See the [Build for inferencing](../../build/inferencing.md) documentation for further details on supported environments. Ignore the build instructions on that page as they are for a full build and we will cover the mobile build instructions here.
Select the branch you wish to use. The latest release is recommended.
- `git checkout <branch>`
- e.g. `git checkout rel-1.8.0`
It is suggested you do not use the unreleased 'master' branch unless there is a specific new feature you require.
| Release | Date | Branch |
|---------|--------|
| 1.8 | 2021-06-02 | rel-1.8.0 |
| 1.7 | 2021-03-03 | rel-1.7.2 |
| 1.6 | 2020-12-11 | rel-1.6.0 |
| 1.5 | 2020-10-30 | rel-1.5.3 |
| Unreleased | | master |
The directory the ONNX Runtime repository was cloned into is referred to as `<ONNX Runtime repository root>` in this documentation.
### Install ONNX Runtime python package
Install the onnxruntime python package from [https://pypi.org/project/onnxruntime/](https://pypi.org/project/onnxruntime/) in order to convert models from ONNX format to the internal ORT format. Version 1.5.3 or higher is required.
- `pip install onnxruntime` will install the latest release
You must match the python package version to the branch of the ONNX Runtime repository you checked out
- e.g. if you wanted to use the 1.7 release
- `git checkout rel-1.7.2` in your local git repository
- `pip install onnxruntime==1.7.2`
If you are using the `master` branch in the git repository you should use the nightly ONNX Runtime python package
- `pip install -U -i https://test.pypi.org/simple/ ort-nightly`
-------
Next: [Converting ONNX models to ORT format](./model-conversion.md)