c3db1d3628
A couple of places in onnxruntime used `float_t` data type alias as an
alternative to `float`. However, this is not entirely correct, since
`float_t` is an implementation-defined type alias, which may be `float`,
`double`, `long double` or some other implementation-defined data type,
depending on the state of the internal `FLT_EVAL_METHOD` macro:
https://en.cppreference.com/w/c/numeric/math/float_t
On most major platforms and compilers (clang, GCC, MSVC) this is only a
cosmetic change and will not lead to any changes. However, icpx compiler
(and legacy icc) tends to substitute `float_t` with `long double`,
resulting in a linker error (unresolved reference) to the base onnx
library, that only contains the `ParseData` function for `float` and
`double` as in
[here](
|
||
|---|---|---|
| .. | ||
| android | ||
| e2e | ||
| ios | ||
| lib | ||
| scripts | ||
| .gitignore | ||
| app.plugin.js | ||
| babel.config.js | ||
| onnxruntime-react-native.podspec | ||
| package.json | ||
| README.md | ||
| test_types_models.readme.md | ||
| tsconfig.build.json | ||
| tsconfig.json | ||
| tsconfig.scripts.json | ||
| unimodule.json | ||
| yarn.lock | ||
onnxruntime-react-native
ONNX Runtime React Native provides a JavaScript library for running ONNX models in a React Native app.
Why ONNX models
The Open Neural Network Exchange (ONNX) is an open standard for representing machine learning models. The biggest advantage of ONNX is that it allows interoperability across different open source AI frameworks, which itself offers more flexibility for AI frameworks adoption.
Why ONNX Runtime React Native
With ONNX Runtime React Native, React Native developers can score pre-trained ONNX models directly in React Native apps by leveraging ONNX Runtime, so it provides a light-weight inference solution for Android and iOS.
Installation
yarn add onnxruntime-react-native
Usage
import { InferenceSession } from "onnxruntime-react-native";
// load a model
const session: InferenceSession = await InferenceSession.create(modelPath);
// input as InferenceSession.OnnxValueMapType
const result = session.run(input, ['num_detection:0', 'detection_classes:0'])
Refer to ONNX Runtime JavaScript examples 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 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 for the list of supported operators and types.
License
License information can be found here.