Metadata-Version: 2.4
Name: epic-rabbit
Version: 1.0.1
Summary: Core engine for Armanid object detection — by Epic Rabbit
Author-email: Arman Guriyan <arman@epicrabbit.io>
License: MIT
Project-URL: Homepage, https://epicrabbit.io
Project-URL: Repository, https://github.com/epicrabbit/armanid
Project-URL: Documentation, https://docs.epicrabbit.io
Keywords: object-detection,computer-vision,armanid,epic-rabbit,deep-learning
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=1.8.0
Requires-Dist: torchvision>=0.9.0
Requires-Dist: numpy>=1.22.2
Requires-Dist: pillow>=7.1.2
Requires-Dist: pyyaml>=5.3.1
Requires-Dist: requests>=2.23.0
Requires-Dist: opencv-python>=4.6.0
Requires-Dist: tqdm>=4.64.0
Requires-Dist: psutil
Requires-Dist: py-cpuinfo
Requires-Dist: scipy>=1.4.1
Requires-Dist: matplotlib>=3.3.0
Dynamic: license-file

# Epic Rabbit

**Core detection engine for Armanid — by Epic Rabbit**

Epic Rabbit is the high-performance engine that powers the Armanid object detection library. It provides a complete, standalone computer vision backend with no external detection framework dependencies.

## Installation

```bash
pip install epic-rabbit
pip install armanid
```

## Quick Start

```python
from armanid import Armanid

model = Armanid("armanid-nano")
results = model.detect("image.jpg")
results[0].show()
```

## Webcam Detection

```python
from armanid import Armanid
from armanid.utils import run_webcam

model = Armanid("armanid-nano")
run_webcam(model, cam_index=0, conf=0.25)
```

## Available Models

| Model | Size | Speed |
|-------|------|-------|
| armanid-nano | ~6MB | Fastest |
| armanid-small | ~22MB | Fast |
| armanid-medium | ~50MB | Balanced |
| armanid-large | ~84MB | Accurate |
| armanid-xlarge | ~131MB | Most Accurate |

## Features

- Object Detection
- Instance Segmentation
- Pose Estimation
- Object Tracking
- Train on custom datasets
- Export to ONNX, TFLite, CoreML

## License

MIT License — Epic Rabbit
