YOLO Fruit Classification

A computer vision project that demonstrates fruit detection and classification using YOLO (You Only Look Once) object detection models.
This repository contains step-by-step experiments in a Jupyter Notebook for preparing data, training a YOLO model, and running inference on fruit images.

---

🧠 Project Overview

Object detection is the process of identifying and localizing objects within images.
This project applies YOLO, a state-of-the-art object detection architecture, to classify fruit types and/or detect fruits in images.
YOLO models are optimized for real-time inference and efficiency while maintaining strong accuracy.:contentReference[oaicite:1]{index=1}

Key goals of this project include:

• Preparing a custom image dataset for fruit detection
• Labeling and formatting data for YOLO training
• Training a YOLO model (such as YOLOv8 or similar)
• Evaluating model performance
• Running inference to detect fruit in sample images

---

📁 Repository Structure

FruitClassification_YOLO/
├── Notebook.ipynb           # Main Jupyter Notebook with experiments
├── dataset/                 # Dataset directory (images, labels)
├── models/                  # Trained model weights (if included)
├── requirements.txt         # Python dependencies (optional)
└── README.md                # Project documentation

---

🛠 Prerequisites

1. Ensure you have Python 3.8 or later installed.

2. Install dependencies (example, add packages as needed):

   pip install ultralytics opencv-python matplotlib numpy
   

• The ultralytics package provides a YOLOv8 implementation and necessary training/inference utilities.