software-mansion/react-native-executorch-style-transfer-udnie
0308
1---2license: bsd-3-clause3pipeline_tag: image-to-image4library_name: executorch5---6 7# style-transfer-udnie8 9This repository hosts the **style-transfer-udnie** models exported for the10[React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch)11library as ExecuTorch `.pte` programs, ready to run on device.12 13Upstream model: [style transfer](https://github.com/pytorch/examples/tree/main/fast_neural_style)14 15## Variants16 17| Path | Backend | Precision |18| --- | --- | --- |19| `coreml/style_transfer_udnie_coreml_fp16.pte` | coreml | fp16 |20| `xnnpack/style_transfer_udnie_xnnpack_fp32.pte` | xnnpack | fp32 |21| `xnnpack/style_transfer_udnie_xnnpack_int8.pte` | xnnpack | int8 |22 23## Unshipped backends24 25A backend directory carrying a `NOTES.md` and no `.pte` was exported and26not published. Its note records what went wrong.27 28- `mlx` ([why](https://huggingface.co/software-mansion/react-native-executorch-style-transfer-udnie/blob/main/mlx/NOTES.md))29 30## Repository structure31 32```33LICENSE 3.4 kB34config.json 42 B35coreml/config.json 889 B36coreml/style_transfer_udnie_coreml_fp16.pte 3.6 MB37mlx/NOTES.md 2.6 kB38xnnpack/config.json 1.4 kB39xnnpack/style_transfer_udnie_xnnpack_fp32.pte 6.5 MB40xnnpack/style_transfer_udnie_xnnpack_int8.pte 1.8 MB41```42 43## Compatibility44 45These files are published for the **ExecuTorch v1.4.1** runtime. ExecuTorch46gives no forward compatibility guarantee, so an older runtime may fail to load47them.48 49To use them in React Native ExecuTorch, pass the model constant shipped in the50library's model registry to the corresponding task pipeline. See the51[documentation](https://docs.swmansion.com/react-native-executorch/docs/fundamentals/downloading-models).52 53To load these files in your own ExecuTorch runtime, read the54[compatibility note](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md)55first.56 