saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-14 20:48:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update React Native documentation to reflect change to use full ORT (#13091)

Browse source 
### Description
<!-- Describe your changes. -->
Update React Native documentation to reflect change to use full ORT. Fix
broken links.


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
ORT v1.13 uses the full ORT package. Instructions for performing a
custom build did not cover this.

Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
This commit is contained in:
Scott McKay 2022-09-28 08:11:58 +10:00 committed by GitHub
parent 5c89c37f7f
commit e19163167e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 69 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

74
js/README.md
View file

@ -339,7 +339,11 @@ This project provides an ONNX Runtime React Native JavaScript library to run ONN
### Models with ORT format
By default, ONNX Runtime React Native leverages ONNX Runtime Mobile package with ORT format. Follow the [instruciton](https://onnxruntime.ai/docs/tutorials/mobile/model-conversion.html) to covert ONNX model to ORT format.
Prior to ORT v1.13, the ONNX Runtime React Native package utilized the ONNX Runtime Mobile package, which required an ONNX model to be converted to ORT format.
Follow these [instructions](https://onnxruntime.ai/docs/reference/ort-format-models.html#convert-onnx-models-to-ort-format) to convert ONNX model to ORT format.
Note that the ONNX Runtime Mobile package includes a reduced set of operators and types, so not all models are supported. See [here](https://onnxruntime.ai/docs/reference/operators/MobileOps.html) for the list of supported operators and types.
From ORT v1.13 onwards the 'full' ONNX Runtime package is used. It supports both ONNX and ORT format models, and all operators and types.
### Build
@ -349,21 +353,38 @@ By default, ONNX Runtime React Native leverages ONNX Runtime Mobile package with
- in `<ORT_ROOT>/js/common/`, run `npm ci`.
- in `<ORT_ROOT>/js/react_native/`, run `yarn`.
2. Build Android ONNX Runtime package
2. Acquire or build the Android ONNX Runtime package
1. To use a published Android ONNX Runtime Mobile package from Maven, go to step 5.
2. Set up an Android build environment referring to [instruction](https://www.onnxruntime.ai/docs/how-to/build/android-ios.html#android)
2. Set up an Android build environment using these [instructions](https://onnxruntime.ai/docs/build/android.html). Note that the dependencies are quite convoluted, so using the specified JDK and Gradle versions is important.
3. In `<ORT_ROOT>`, run this python script to build ONNX Runtime Android archive file. In windows, this requires an admin account to build. To build a model specific package with reduced size, refer to [instruction](https://www.onnxruntime.ai/docs/how-to/build/reduced.html#build-ort-with-reduced-size).
3. In `<ORT_ROOT>`, run the below python script to build the ONNX Runtime Android archive file. On a Windows machine, this requires an admin account to build.
You can build a 'full' package that supports all operators and types, or a reduced size 'mobile' package that supports a limited set of operators and types based on your model/s to miminize the binary size.
See [here](https://onnxruntime.ai/docs/build/custom.html) for information about how the reduced build works, including creating the configuration file using your model/s.
Full build:
```sh
python tools/ci_build/github/android/build_aar_package.py tools/ci_build/github/android/default_mobile_aar_build_settings.json --config MinSizeRel --android_sdk_path <ANDROID_SDK_PATH> --android_ndk_path <ANDROID_NDK_PATH> --build_dir <BUILD_DIRECTORY> --include_ops_by_config tools/ci_build/github/android/mobile_package.required_operators.config
python tools/ci_build/github/android/build_aar_package.py tools/ci_build/github/android/default_full_aar_build_settings.json --config Release --android_sdk_path <ANDROID_SDK_PATH> --android_ndk_path <ANDROID_NDK_PATH> --build_dir <BUILD_DIRECTORY>
```
4. Copy `<BUILD_DIRECTORY>/aar_out/MinSizeRel/com/microsoft/onnxruntime/onnxruntime-mobile/<version>/onnxruntime-mobile-<version>.aar` into `<ORT_ROOT>/js/react_native/android/libs` directory.
Reduced size build with configuration file generated from your model/s. Note that either Release or MinSizeRel could be used as the config, depending on your priorities:
```sh
python tools/ci_build/github/android/build_aar_package.py tools/ci_build/github/android/default_mobile_aar_build_settings.json --config MinSizeRel --android_sdk_path <ANDROID_SDK_PATH> --android_ndk_path <ANDROID_NDK_PATH> --build_dir <BUILD_DIRECTORY> --include_ops_by_config <required_ops_and_types_for_your_models.config> --enable_reduced_operator_type_support
```
5. To verify, open Android Emulator and run this command from `<ORT_ROOT>/js/react_native/android`
4. Move the generated ONNX Runtime Android archive file to `<ORT_ROOT>/js/react_native/android/libs/`.
Full build:
Copy `<BUILD_DIRECTORY>/aar_out/Release/com/microsoft/onnxruntime/onnxruntime-android/<version>/onnxruntime-android-<version>.aar` into `<ORT_ROOT>/js/react_native/android/libs` directory.
Reduced size build:
Copy `<BUILD_DIRECTORY>/aar_out/MinSizeRel/com/microsoft/onnxruntime/onnxruntime-mobile/<version>/onnxruntime-mobile-<version>.aar` into `<ORT_ROOT>/js/react_native/android/libs` directory and update to dependencies in [js/react_native/android/build.gradle](https://github.com/microsoft/onnxruntime/blob/365a01397dbd1293e0c2773380c57fd271432b72/js/react_native/android/build.gradle#L136-L137) to use onnxruntime-mobile instead of onnxruntime-android.
5. To verify, open the Android Emulator and run this command from `<ORT_ROOT>/js/react_native/android`
```sh
./gradlew connectedDebugAndroidTest
@ -371,23 +392,40 @@ By default, ONNX Runtime React Native leverages ONNX Runtime Mobile package with
3. Build iOS ONNX Runtime package
1. To use a published c/c++ ONNX Runtime Mobile package from CocoaPods, skip all steps below.
1. To use the published C/C++ ONNX Runtime package from CocoaPods, skip all steps below.
2. Set up iOS build environment referring to [instruction](https://www.onnxruntime.ai/docs/how-to/build/android-ios.html#ios).
2. Set up iOS build environment using these [instructions](https://onnxruntime.ai/docs/build/ios.html).
3. Build a fat ONNX Runtime Mobile Framework for iOS and iOS simulator from `<ORT_ROOT>` using this command,
3. Build a fat ONNX Runtime Mobile Framework for iOS and iOS simulator from `<ORT_ROOT>` using this command:
Full build:
```sh
python tools/ci_build/github/apple/build_ios_framework.py tools/ci_build/github/apple/default_mobile_ios_framework_build_settings.json --config MinSizeRel --include_ops_by_config tools/ci_build/github/android/mobile_package.required_operators.config
python tools/ci_build/github/apple/build_ios_framework.py tools/ci_build/github/apple/default_full_ios_framework_build_settings.json --config Release
```
It creates `Headers`, `LICENSE`, and `onnxruntime.xcframework` in `build/iOS_framework/framework_out` directory. From `framework_out` directory, create an archive file named `onnxruntime-mobile-c.zip` as follows and copy to `<ORT_ROOT>/js/react_native/local_pods` directory.
Reduced size build:
```sh
python tools/ci_build/github/apple/build_ios_framework.py tools/ci_build/github/apple/default_mobile_ios_framework_build_settings.json --config MinSizeRel --include_ops_by_config <required_ops_and_types_for_your_models.config> --enable_reduced_operator_type_support
```
The build creates `Headers`, `LICENSE`, and `onnxruntime.xcframework` in `build/iOS_framework/framework_out` directory. From `framework_out` directory, create an archive file named `onnxruntime-c.zip` for a full build or `onnxruntime-mobile-c.zip` for a reduced size build and copy to `<ORT_ROOT>/js/react_native/local_pods` directory.
Full build:
```sh
zip -r onnxruntime-c.zip .
```
Reduced size build:
```sh
zip -r onnxruntime-mobile-c.zip .
```
4. To verify, open iOS Simulator and run this command from `<ORT_ROOT>/js/react_native/ios`. Change a destination to specify a running iOS Simulator.
4. To verify, open the iOS Simulator and run the below command from `<ORT_ROOT>/js/react_native/ios`. Change the destination argument as needed to specify a running iOS Simulator.
If using the reduced size build it is necessary to first update some configuration to use the mobile ORT package:
- replace `onnxruntime/onnxruntime.framework` with `onnxruntime-mobile/onnxruntime.framework` in /js/react_native/ios/OnnxruntimeModule.xcodeproj/project.pbxproj
- replace `onnxruntime-c` with `onnxruntime-mobile-c` in /js/react_native/ios/Podfile
- For reference, [this PR](https://github.com/microsoft/onnxruntime/pull/13037) shows the changes made to switch from using the 'mobile' ORT package to the 'full' package.
```sh
pod install
@ -408,7 +446,13 @@ By default, ONNX Runtime React Native leverages ONNX Runtime Mobile package with
yarn bootstrap
```
When testing with a custom built ONNX Runtime Android package, copy `<BUILD_DIRECTORY>/aar_out/MinSizeRel/com/microsoft/onnxruntime/onnxruntime-mobile/<version>/onnxruntime-mobile-<version>.aar` into `<ORT_ROOT>/js/react_native/e2e/android/app/libs` directory. Using a custom built ONNX Runtime iOS package, copy `onnxruntime-mobile-c.zip` into `<ORT_ROOT>/js/react_native/local_pods` directory if it's not already done.
When testing with a custom built ONNX Runtime Android package, copy `<BUILD_DIRECTORY>/aar_out/MinSizeRel/com/microsoft/onnxruntime/onnxruntime-{android|mobile}/<version>/onnxruntime-{android|mobile}-<version>.aar` into the `<ORT_ROOT>/js/react_native/e2e/android/app/libs` directory.
When testing with a custom built ONNX Runtime iOS package, copy `onnxruntime-[mobile-]c.zip` into the `<ORT_ROOT>/js/react_native/local_pods` directory.
If using the reduced size build it is necessary to update some configuration to use the mobile ORT package:
- replace `com.microsoft.onnxruntime:onnxruntime-android` with `com.microsoft.onnxruntime:onnxruntime-mobile` in /js/react_native/e2e/android/app/build.gradle
- replace `onnxruntime-c` with `onnxruntime-mobile-c` in /js/react_native/e2e/ios/Podfile
From `<ORT_ROOT>/js/react_native/e2e/android`, run e2e Android tests as follows,
@ -433,7 +477,7 @@ By default, ONNX Runtime React Native leverages ONNX Runtime Mobile package with
### NPM Packaging
1. Update a version using `npm verison <version>` from `<ORT_ROOT>/js/react_native` folder. If it's for a dev, use `npm version <version>-dev.<subversion>`
1. Update a version using `npm version <version>` from `<ORT_ROOT>/js/react_native` folder. If it's for a dev, use `npm version <version>-dev.<subversion>`
2. Run `npm pack` and verify NPM package contents

14
js/react_native/README.md
View file

@ -1,6 +1,6 @@
# onnxruntime-react-native
ONNX Runtime React Native provides a JavaScript library for running ONNX models on React Native app.
ONNX Runtime React Native provides a JavaScript library for running ONNX models in a React Native app.
### Why ONNX models
@ -8,7 +8,7 @@ The [Open Neural Network Exchange](http://onnx.ai/) (ONNX) is an open standard f
### Why ONNX Runtime React Native
With ONNX Runtime React Native, React Native developers can score pre-trained ONNX models directy on React Native apps by leveraging [ONNX Runtime Mobile](https://www.onnxruntime.ai/docs/reference/mobile/prebuilt-package/), so it provides a light-weight inference solution for Android and iOS.
With ONNX Runtime React Native, React Native developers can score pre-trained ONNX models directly in React Native apps by leveraging [ONNX Runtime](https://onnxruntime.ai/docs/), so it provides a light-weight inference solution for Android and iOS.
### Installation
@ -27,14 +27,16 @@ const session: InferenceSession = await InferenceSession.create(modelPath);
const result = session.run(input, ['num_detection:0', 'detection_classes:0'])
```
Refer to [ONNX Runtime JavaScript examples](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/js) for samples and tutorials. Different from other JavaScript frameworks like node.js and web, React Native library doesn't support these features.
- Unsigned data type at Tensor
Refer to [ONNX Runtime JavaScript examples](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/js) for samples and tutorials. The ONNX Runtime React Native library does not currently support the following features:
- Tensors with unsigned data types, with the exception of uint8 on Android devices
- Model loading using ArrayBuffer
### Operator and type support
ONNX Runtime React Native currently supports most operators used by popular models. Refer to [ONNX Runtime Mobile Pacakge Operator and Type](https://www.onnxruntime.ai/docs/reference/mobile/prebuilt-package/1.8%20ORTMobilePackageOperatorTypeSupport).
ONNX Runtime React Native version 1.13 supports both ONNX and ORT format models, and includes all operators and types.
Previous ONNX Runtime React Native packages use the ONNX Runtime Mobile package, and support operators and types used in popular mobile models.
See [here](https://onnxruntime.ai/docs/reference/operators/MobileOps.html) for the list of supported operators and types.
### License

4
js/react_native/package.json
View file

@ -40,7 +40,7 @@
"source": "lib/index",
"version": "1.13.0",
"main": "dist/commonjs/index",
"homepage": "https://github.com/Microsoft/onnxruntime/js/react_native#readme",
"homepage": "https://github.com/microsoft/onnxruntime/blob/main/js/react_native/README.md",
"files": [
"lib",
"dist",
@ -60,7 +60,7 @@
"!android/gradle/wrapper/*.jar",
"!android/libs"
],
"description": "Onnxruntime bridge for react native",
"description": "ONNX Runtime bridge for react native",
"repository": "https://github.com/Microsoft/onnxruntime.git",
"react-native-builder-bob": {
"source": "lib",