Skip to content

Commit 299757c

Browse files
benITo47benITo47
committed
Upadte claude skills
1 parent af15501 commit 299757c

File tree

3 files changed

+32
-32
lines changed

3 files changed

+32
-32
lines changed

‎skills/canary/react-native-executorch/references/reference-cv.md‎

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@ For the latest available models reference exported models in [HuggingFace Classi
7373

7474
---
7575

76-
# useImageSegmentation
76+
# useSemanticSegmentation
7777

7878
**Purpose:** Classify each pixel in an image to detect objects on a per-pixel basis.
7979

@@ -83,12 +83,12 @@ For the latest available models reference exported models in [HuggingFace Classi
8383

8484
```typescript
8585
import {
86-
useImageSegmentation,
86+
useSemanticSegmentation,
8787
DEEPLAB_V3_RESNET50,
8888
DeeplabLabel,
8989
} from 'react-native-executorch';
9090

91-
const model = useImageSegmentation({ model: DEEPLAB_V3_RESNET50 });
91+
const model = useSemanticSegmentation({ model: DEEPLAB_V3_RESNET50 });
9292

9393
const imageUri = 'file:///Users/.../cute_cat.png';
9494

@@ -103,7 +103,7 @@ try {
103103
## Advanced Usage with Classes of Interest
104104

105105
```typescript
106-
const model = useImageSegmentation({ model: DEEPLAB_V3_RESNET50 });
106+
const model = useSemanticSegmentation({ model: DEEPLAB_V3_RESNET50 });
107107

108108
const handleSegmentation = async (imageUri: string) => {
109109
try {
@@ -139,10 +139,10 @@ For the latest available models check out exported models in [this HuggingFace S
139139

140140
## Additional references
141141

142-
- [useImageSegmentation docs](https://docs.swmansion.com/react-native-executorch/docs/hooks/computer-vision/useImageSegmentation)
143-
- [useImageSegmentation API reference](https://docs.swmansion.com/react-native-executorch/docs/api-reference/functions/useImageSegmentation)
142+
- [useSemanticSegmentation docs](https://docs.swmansion.com/react-native-executorch/docs/hooks/computer-vision/useImageSegmentation)
143+
- useSemanticSegmentation API reference](https://docs.swmansion.com/react-native-executorch/docs/api-reference/functions/useImageSegmentation)
144144
- [HuggingFace Segmentation collection](https://huggingface.co/collections/software-mansion/image-segmentation)
145-
- [Typescript API implementation of segmentation](https://docs.swmansion.com/react-native-executorch/docs/typescript-api/computer-vision/ImageSegmentationModule)
145+
- [Typescript API implementation of segmentation](https://docs.swmansion.com/react-native-executorch/docs/typescript-api/computer-vision/SemanticSegmentationModule)
146146

147147
---
148148

‎skills/react-native-executorch/SKILL.md‎

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ Perform image understanding and manipulation tasks entirely on-device.
133133

134134
- **Image Classification** - Categorize images into predefined classes
135135
- **Object Detection** - Locate and identify objects with bounding boxes
136-
- **Image Segmentation** - Pixel-level classification
136+
- **Semantic Segmentation** - Pixel-level classification
137137
- **Style Transfer** - Apply artistic styles to images
138138
- **Text-to-Image** - Generate images from text descriptions
139139
- **Image Embeddings** - Convert images to numerical vectors for similarity/search
@@ -463,23 +463,23 @@ The library provides core utilities for managing models and handling errors:
463463

464464
## Quick Reference by Hook
465465

466-
| Hook | Purpose | Reference |
467-
| ---------------------- | ----------------------------------------- | ----------------------------------------------------- |
468-
| `useLLM` | Text generation, chat, function calling | [reference-llms.md](./references/reference-llms.md) |
469-
| `useClassification` | Image categorization | [reference-cv.md](./references/reference-cv.md) |
470-
| `useObjectDetection` | Object localization | [reference-cv.md](./references/reference-cv.md) |
471-
| `useImageSegmentation` | Pixel-level classification | [reference-cv.md](./references/reference-cv.md) |
472-
| `useStyleTransfer` | Artistic image filters | [reference-cv-2.md](./references/reference-cv-2.md) |
473-
| `useTextToImage` | Image generation | [reference-cv-2.md](./references/reference-cv-2.md) |
474-
| `useImageEmbeddings` | Image similarity/search | [reference-cv-2.md](./references/reference-cv-2.md) |
475-
| `useOCR` | Text recognition (horizontal) | [reference-ocr.md](./references/reference-ocr.md) |
476-
| `useVerticalOCR` | Text recognition (vertical, experimental) | [reference-ocr.md](./references/reference-ocr.md) |
477-
| `useSpeechToText` | Audio transcription | [reference-audio.md](./references/reference-audio.md) |
478-
| `useTextToSpeech` | Voice synthesis | [reference-audio.md](./references/reference-audio.md) |
479-
| `useVAD` | Voice activity detection | [reference-audio.md](./references/reference-audio.md) |
480-
| `useTextEmbeddings` | Text similarity/search | [reference-nlp.md](./references/reference-nlp.md) |
481-
| `useTokenizer` | Text to tokens conversion | [reference-nlp.md](./references/reference-nlp.md) |
482-
| `useExecutorchModule` | Custom model inference (advanced) | [core-utilities.md](./references/core-utilities.md) |
466+
| Hook | Purpose | Reference |
467+
| ------------------------- | ----------------------------------------- | ----------------------------------------------------- |
468+
| `useLLM` | Text generation, chat, function calling | [reference-llms.md](./references/reference-llms.md) |
469+
| `useClassification` | Image categorization | [reference-cv.md](./references/reference-cv.md) |
470+
| `useObjectDetection` | Object localization | [reference-cv.md](./references/reference-cv.md) |
471+
| `useSemanticSegmentation` | Pixel-level classification | [reference-cv.md](./references/reference-cv.md) |
472+
| `useStyleTransfer` | Artistic image filters | [reference-cv-2.md](./references/reference-cv-2.md) |
473+
| `useTextToImage` | Image generation | [reference-cv-2.md](./references/reference-cv-2.md) |
474+
| `useImageEmbeddings` | Image similarity/search | [reference-cv-2.md](./references/reference-cv-2.md) |
475+
| `useOCR` | Text recognition (horizontal) | [reference-ocr.md](./references/reference-ocr.md) |
476+
| `useVerticalOCR` | Text recognition (vertical, experimental) | [reference-ocr.md](./references/reference-ocr.md) |
477+
| `useSpeechToText` | Audio transcription | [reference-audio.md](./references/reference-audio.md) |
478+
| `useTextToSpeech` | Voice synthesis | [reference-audio.md](./references/reference-audio.md) |
479+
| `useVAD` | Voice activity detection | [reference-audio.md](./references/reference-audio.md) |
480+
| `useTextEmbeddings` | Text similarity/search | [reference-nlp.md](./references/reference-nlp.md) |
481+
| `useTokenizer` | Text to tokens conversion | [reference-nlp.md](./references/reference-nlp.md) |
482+
| `useExecutorchModule` | Custom model inference (advanced) | [core-utilities.md](./references/core-utilities.md) |
483483

484484
---
485485

‎skills/react-native-executorch/references/reference-cv.md‎

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@ For the latest available models reference exported models in [HuggingFace Classi
7373

7474
---
7575

76-
# useImageSegmentation
76+
# useSemanticSegmentation
7777

7878
**Purpose:** Classify each pixel in an image to detect objects on a per-pixel basis.
7979

@@ -83,12 +83,12 @@ For the latest available models reference exported models in [HuggingFace Classi
8383

8484
```typescript
8585
import {
86-
useImageSegmentation,
86+
useSemanticSegmentation,
8787
DEEPLAB_V3_RESNET50,
8888
DeeplabLabel,
8989
} from 'react-native-executorch';
9090

91-
const model = useImageSegmentation({ model: DEEPLAB_V3_RESNET50 });
91+
const model = useSemanticSegmentation({ model: DEEPLAB_V3_RESNET50 });
9292

9393
const imageUri = 'file:///Users/.../cute_cat.png';
9494

@@ -103,7 +103,7 @@ try {
103103
## Advanced Usage with Classes of Interest
104104

105105
```typescript
106-
const model = useImageSegmentation({ model: DEEPLAB_V3_RESNET50 });
106+
const model = useSemanticSegmentation({ model: DEEPLAB_V3_RESNET50 });
107107

108108
const handleSegmentation = async (imageUri: string) => {
109109
try {
@@ -139,10 +139,10 @@ For the latest available models check out exported models in [this HuggingFace S
139139

140140
## Additional references
141141

142-
- [useImageSegmentation docs](https://docs.swmansion.com/react-native-executorch/docs/hooks/computer-vision/useImageSegmentation)
143-
- [useImageSegmentation API reference](https://docs.swmansion.com/react-native-executorch/docs/api-reference/functions/useImageSegmentation)
142+
- [useSemanticSegmentation docs](https://docs.swmansion.com/react-native-executorch/docs/hooks/computer-vision/useImageSegmentation)
143+
- [useSemanticSegmentation API reference](https://docs.swmansion.com/react-native-executorch/docs/api-reference/functions/useImageSegmentation)
144144
- [HuggingFace Segmentation collection](https://huggingface.co/collections/software-mansion/image-segmentation)
145-
- [Typescript API implementation of segmentation](https://docs.swmansion.com/react-native-executorch/docs/typescript-api/computer-vision/ImageSegmentationModule)
145+
- [Typescript API implementation of segmentation](https://docs.swmansion.com/react-native-executorch/docs/typescript-api/computer-vision/SemanticSegmentationModule)
146146

147147
---
148148

0 commit comments

Comments
 (0)