README.md

---
title: YOLO12 - Specialized Object Detection
emoji: 👁
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 6.12.0
app_file: app.py
pinned: false
tags:
- Object Detection
- Instance Segmentation
- Pose Estimation
- Oriented Bounding Boxes (OBB)
- Image Classification
- YOLO12
- Computer Vision
short_description: Comprehensive YOLO12 app for computer vision tasks.
---

# YOLO12 Computer Vision Space

Welcome to the **YOLO12** Space! This application provides a unified interface to test and run the full suite of **Ultralytics YOLO12** models for various computer vision tasks.

## 🚀 Features
- **All-in-One Inference**: Support for images and videos in a single app.
- **Multiple Tasks**: Switch seamlessly between different modes:
    - 🎯 **Object Detection**: Locate and identify objects with bounding boxes.
    - 🎨 **Instance Segmentation**: Precise per-pixel outlines of objects.
    - 🦴 **Pose Estimation**: Detect human points and skeletons.
    - 📐 **Oriented Bounding Boxes (OBB)**: Detection for rotated objects (e.g., aerial or misaligned imagery).
    - 🏷️ **Classification**: Overall scene categorization.
- **Model Selection**: Choose from various model sizes (Nano, Small, Medium, Large, X-Large) to balance speed and accuracy.
- **Adjustable Parameters**: Fine-tune confidence thresholds, IoU (Intersection over Union), and max detections.

## 📦 Getting Started
1.  **Usage**: Upload an image or video, select your preferred model variant and image size, then hit **"Detect Objects"**.
2.  **Examples**: Check out the gallery at the bottom of the "Image" tab for pre-loaded scenarios to see the models in action.

## 🛠️ Technology Stack
- **Framework**: [Ultralytics Hub](https://github.com/ultralytics/ultralytics) (YOLO12 Engine)
- **UI**: [Gradio](https://gradio.app)
- **Deployment**: [Hugging Face Spaces](https://huggingface.co/spaces)

---
*Created by Atalay Denknalbant - Modified for YOLO12*