Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# AutoAnotationModel
|
| 2 |
+
|
| 3 |
+
This repository contains the custom model checkpoint `Model.pth` and a powerful annotation pipeline developed by **Rajkumar G** for real-time object auto-annotation and YOLO dataset generation.
|
| 4 |
+
|
| 5 |
+
## 🔧 What This Is
|
| 6 |
+
|
| 7 |
+
`AutoAnotationModel` enables:
|
| 8 |
+
- ⚙️ Multi-class object detection using template-based region matching
|
| 9 |
+
- 🧠 Intelligent segmentation refinement using custom logic
|
| 10 |
+
- 🖼️ Live visual preview of annotations through a Flask web application
|
| 11 |
+
- 📤 YOLO-format `.txt` export for training detection models
|
| 12 |
+
- 📦 Exportable annotation packages including image + labels
|
| 13 |
+
|
| 14 |
+
The model and its web interface are used in applications like:
|
| 15 |
+
- Bin/Cover detection
|
| 16 |
+
- Mechanical part annotation
|
| 17 |
+
- Industrial dataset creation
|
| 18 |
+
- Real-time inspection and labeling
|
| 19 |
+
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
## 🧠 Model Information
|
| 23 |
+
|
| 24 |
+
- **Model Name:** `Model.pth`
|
| 25 |
+
- **Hosted on:** [Hugging Face - Rajkumar57/AutoAnotationModel](https://huggingface.co/Rajkumar57/AutoAnotationModel)
|
| 26 |
+
- **Created by:** Rajkumar G
|
| 27 |
+
- **Frameworks Used:** Python, PyTorch, OpenCV, Flask
|
| 28 |
+
- **Use Case:** Real-time annotation & YOLO label generation
|
| 29 |
+
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
+
## 🚀 How to Use the Model
|
| 33 |
+
|
| 34 |
+
```python
|
| 35 |
+
from huggingface_hub import hf_hub_download
|
| 36 |
+
from segment_anything import sam_model_registry, SamPredictor
|
| 37 |
+
import torch
|
| 38 |
+
|
| 39 |
+
# Download model from Hugging Face Hub
|
| 40 |
+
model_path = hf_hub_download(repo_id="Rajkumar57/AutoAnotationModel", filename="Model.pth")
|
| 41 |
+
|
| 42 |
+
# Load model
|
| 43 |
+
model = sam_model_registry["vit_h"](checkpoint=model_path)
|
| 44 |
+
model = model.to("cuda" if torch.cuda.is_available() else "cpu")
|
| 45 |
+
predictor = SamPredictor(model)
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
## 🌟 Key Features of My Annotation System
|
| 51 |
+
|
| 52 |
+
- ✅ Web interface for user-defined class names and class IDs
|
| 53 |
+
- 📁 Upload template images for each class
|
| 54 |
+
- 🔍 Automatic region detection and segmentation
|
| 55 |
+
- 📤 YOLO-format `.txt` annotation generation
|
| 56 |
+
- 📸 Annotated image previews
|
| 57 |
+
- 📦 One-click export as `.zip`
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
## 📁 Files Included
|
| 62 |
+
|
| 63 |
+
| File | Description |
|
| 64 |
+
|-------------|----------------------------------------------|
|
| 65 |
+
| `Model.pth` | Custom-trained model for annotation tasks |
|
| 66 |
+
| `README.md` | Documentation for usage |
|
| 67 |
+
|
| 68 |
+
---
|
| 69 |
+
|
| 70 |
+
## 👨💻 Author
|
| 71 |
+
|
| 72 |
+
**Rajkumar G**
|
| 73 | |
| 74 |
+
🔗 [LinkedIn](https://linkedin.com/in/rajkumar) | [GitHub](https://github.com/rajkumar)
|
| 75 |
+
|
| 76 |
+
---
|
| 77 |
+
|
| 78 |
+
## 📜 License
|
| 79 |
+
|
| 80 |
+
This model and pipeline were fully created by **Rajkumar G** and are released strictly for **academic and research purposes only**.
|
| 81 |
+
|
| 82 |
+
For commercial use, integration support, or contributions, feel free to reach out directly.
|
| 83 |
+
|
| 84 |
+
---
|
| 85 |
+
|
| 86 |
+
*Proudly developed and maintained by Rajkumar G. If you use this project, kindly give credit or cite this repository.*
|