---
license: agpl-3.0
tags:
  - yolo
  - object-detection
  - recaptcha
  - ultralytics
  - computer-vision
  - image-classification
library_name: ultralytics
pipeline_tag: object-detection
---

<div align="center">

# 🔐 Revpass

### YOLOv26s Fine-tuned for Google reCAPTCHA Detection

[![Python](https://img.shields.io/badge/Python-3.8+-3776AB?style=flat-square&logo=python&logoColor=white)](https://www.python.org/)
[![YOLO](https://img.shields.io/badge/YOLO-v26s-00FFFF?style=flat-square&logo=yolo&logoColor=black)](https://github.com/ultralytics/ultralytics)
[![License](https://img.shields.io/badge/License-AGPL--3.0-663399?style=flat-square)](LICENSE)
[![HuggingFace](https://img.shields.io/badge/🤗-Model-FFD21E?style=flat-square)](https://huggingface.co/saifyxpro/Revpass)
[![CPU Optimized](https://img.shields.io/badge/CPU-Optimized-00D26A?style=flat-square&logo=intel&logoColor=white)](https://huggingface.co/saifyxpro/Revpass)

**High-performance object detection model specialized for reCAPTCHA v2/v3 image recognition**

</div>

---

## 📊 Performance Metrics

| Metric        | Score     |
| ------------- | --------- |
| **mAP50**     | **95.4%** |
| **mAP50-95**  | **71.2%** |
| **Precision** | **89.7%** |
| **Recall**    | **91.5%** |

> Trained on **10,390 reCAPTCHA images** (103 epochs, 1.46 hours, NVIDIA RTX PRO 6000 96GB)

---

## 🎯 Demo Results

![Prediction Examples](./test_predictions.png)

*Sample predictions on validation set showing high-confidence detections across all 11 classes*

---

## 🏷️ Supported Classes (11)

```
bicycle, bridge, bus, car, chimney, crosswalk, 
fire_hydrant, motorcycle, palm_tree, stairs, traffic_light
```

---

## 🚀 Quick Start

### Installation

```bash
pip install ultralytics
```

### Usage

```python
from ultralytics import YOLO

# Load model from HuggingFace
model = YOLO("hf://saifyxpro/Revpass")

# Run inference
results = model("captcha_tile.jpg", conf=0.25)

# Print predictions
for r in results:
    for box in r.boxes:
        class_name = model.names[int(box.cls[0])]
        confidence = float(box.conf[0])
        print(f"{class_name}: {confidence:.2%}")
```

### Example Output

```python
palm_tree: 99%
bus: 98%
traffic_light: 99%
fire_hydrant: 98%
```

---

## 🔧 Training Details

| Parameter             | Value                      |
| --------------------- | -------------------------- |
| **Base Model**        | YOLOv26s                   |
| **Dataset**           | Google reCAPTCHA (Kaggle)  |
| **Training Images**   | 8,832                      |
| **Validation Images** | 1,558                      |
| **Epochs**            | 150 (stopped at 103)       |
| **Batch Size**        | 64                         |
| **Image Size**        | 640x640                    |
| **Optimizer**         | AdamW                      |
| **Learning Rate**     | 0.001 → 0.00001            |
| **GPU**               | NVIDIA RTX PRO 6000 (96GB) |
| **Training Time**     | 1.46 hours                 |

### Augmentation Strategy

- HSV color jittering
- Random translation & scaling
- Horizontal flipping
- Mosaic augmentation
- MixUp (10%)
- Copy-Paste (10%)

---

## 💻 CPU Optimization

This model is **optimized for CPU inference** while being trained on a high-end GPU for maximum quality:

- ✅ YOLOv26s architecture (small, fast)
- ✅ ONNX export support
- ✅ Efficient inference on consumer hardware
- ✅ No GPU required for deployment

### Export to ONNX

```python
model = YOLO("hf://saifyxpro/Revpass")
model.export(format="onnx", imgsz=640, simplify=True)
```

---

## 📈 Training Curves

The model achieved convergence at epoch 103 with early stopping (patience=30):

- **Best mAP50**: 95.4% (epoch 103)
- **Final Loss**: 0.42
- **Validation Stability**: High consistency in final 20 epochs

---

## 🎓 Use Cases

> **⚠️ EDUCATIONAL PURPOSE ONLY**
> 
> This model is designed for **research and educational purposes** to demonstrate:
> - Fine-tuning YOLO models on custom datasets
> - Object detection for specialized domains
> - High-performance training on large GPUs
> 
> **Do not use for unauthorized access or bypassing security measures.**

---

## 📦 Model Files

- `best.pt` - PyTorch weights (22.5 MB)
- `data.yaml` - Dataset configuration
- `README.md` - This file
- `test_predictions.png` - Demo results

---

## 🙏 Acknowledgments

- **Ultralytics** for the amazing YOLO framework
- **Kaggle** for hosting the reCAPTCHA dataset
- **HuggingFace** for model hosting infrastructure

---

## 📄 License

This project is licensed under **AGPL-3.0**. See [LICENSE](LICENSE) for details.

---

## 🔗 Links

- **Model**: [HuggingFace Hub](https://huggingface.co/saifyxpro/Revpass)
- **Framework**: [Ultralytics YOLO](https://github.com/ultralytics/ultralytics)
- **Dataset**: [Google reCAPTCHA (Kaggle)](https://www.kaggle.com/datasets/sanjeetsinghnaik/google-recaptcha)

---

<div align="center">

**Built with ❤️ using Ultralytics YOLOv26s**

[![Star on HuggingFace](https://img.shields.io/badge/⭐-Star%20on%20HuggingFace-FFD21E?style=for-the-badge)](https://huggingface.co/saifyxpro/Revpass)

</div>