Skip to content

Commit 47ff565

Browse files
committed
chore: fix clanker errors
1 parent 68b1504 commit 47ff565

2 files changed

Lines changed: 6 additions & 9 deletions

File tree

‎apps/computer-vision/app/pose_estimation/index.tsx‎

Lines changed: 1 addition & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -32,9 +32,7 @@ export default function PoseEstimationScreen() {
3232
const [layout, setLayout] = useState({ width: 0, height: 0 });
3333

3434
const model = usePoseEstimation({
35-
model: models.pose_estimation.rfdetr_keypoint_preview({
36-
backend: 'xnnpack',
37-
}),
35+
model: models.pose_estimation.rfdetr_keypoint_preview(),
3836
});
3937
const { setGlobalGenerating } = useContext(GeneratingContext);
4038

@@ -64,7 +62,6 @@ export default function PoseEstimationScreen() {
6462
if (imageUri) {
6563
try {
6664
const start = Date.now();
67-
// RF-DETR keypoint preview is a single-`forward` export, so no inputSize.
6865
const output = await model.forward(imageUri);
6966
setInferenceTime(Date.now() - start);
7067
setResults(output);

‎docs/docs/03-hooks/02-computer-vision/usePoseEstimation.md‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -129,15 +129,15 @@ See the full guide: [VisionCamera Integration](./visioncamera-integration.md).
129129

130130
## Supported models
131131

132-
| Model | Number of keypoints | Keypoint list | Multi-size Support |
133-
| ---------------------------------------------------------------------------------------------------------- | ------------------- | ----------------------------------------------------------- | ------------------ |
134-
| [YOLO26N-Pose](https://huggingface.co/software-mansion/react-native-executorch-yolo26-pose) | 17 | [COCO](../../06-api-reference/enumerations/CocoKeypoint.md) | Yes (384/512/640) |
135-
| [RF-DETR Keypoint (beta)](https://huggingface.co/software-mansion/react-native-executorch-rfdetr-keypoint) | 17 | [COCO](../../06-api-reference/enumerations/CocoKeypoint.md) | No |
132+
| Model | Number of keypoints | Keypoint list | Multi-size Support |
133+
| ------------------------------------------------------------------------------------------------------------- | ------------------- | ----------------------------------------------------------- | ------------------ |
134+
| [YOLO26N-Pose](https://huggingface.co/software-mansion/react-native-executorch-yolo26-pose) | 17 | [COCO](../../06-api-reference/enumerations/CocoKeypoint.md) | Yes (384/512/640) |
135+
| [RF-DETR Keypoint (preview)](https://huggingface.co/software-mansion/react-native-executorch-rfdetr-keypoint) | 17 | [COCO](../../06-api-reference/enumerations/CocoKeypoint.md) | No |
136136

137137
:::tip
138138
YOLO models support multiple input sizes (384px, 512px, 640px). Smaller sizes are faster but less accurate, while larger sizes are more accurate but slower. Choose based on your speed/accuracy requirements.
139139
:::
140140

141141
:::warning
142-
`rfdetr_keypoint_preview` is a **beta preview** export and may be re-exported under a different constant once a stable version ships. It is a single-input-size model (no `inputSize` option) and ships `xnnpack`, `coreml`, and `mlx` backends — pass `{ backend }` to override the platform default, e.g. `models.pose_estimation.rfdetr_keypoint_preview({ backend: 'mlx' })`.
142+
`rfdetr_keypoint_preview` is a **preview weights** export and may be re-exported under a different constant once a stable version ships. It is a single-input-size model (no `inputSize` option) and ships `xnnpack`, `coreml`, and `mlx` backends — pass `{ backend }` to override the platform default, e.g. `models.pose_estimation.rfdetr_keypoint_preview({ backend: 'mlx' })`.
143143
:::

0 commit comments

Comments
 (0)