🚀 Add Real-IAD dataset

[samet-akcay]

📝 Description

This PR integrates the Real-IAD (Real Industrial Anomaly Detection) dataset into Anomalib. Real-IAD is a large-scale industrial anomaly detection dataset containing 30 categories of industrial objects, with both normal and anomalous samples captured from 5 different camera viewpoints.

Key Features

1. Dataset Support

   • 30 industrial object categories
   • Multiple image resolutions (256x256, 512x512, 1024x1024)
   • Multi-view support (5 camera angles)
   • Both classification and segmentation tasks
   • Flexible JSON metadata organization

2. Core Components

   • RealIADDataset: PyTorch Dataset implementation
   • RealIAD: PyTorch Lightning DataModule
   • JSON-based metadata handling for flexible dataset organization
   • Support for different dataset versions (base, single-view, FUIAD)

3. Integration Features

   • Automatic resolution handling (both string and integer inputs)
   • Comprehensive input validation
   • Flexible metadata file selection
   • Dynamic train/test split management
   • Automatic task type detection (classification/segmentation)

Implementation Details

Key Features

• Resolution Support: Multiple predefined resolutions (256, 512, 1024)
• Metadata Flexibility: Support for different metadata versions
  • Base metadata (multi-view)
  • Single-view metadata
  • FUIAD metadata versions
• Data Organization: Clear directory structure for normal/abnormal samples
• Validation: Comprehensive input validation and error handling

Usage Examples

# Basic usage
datamodule = RealIAD(
    root="./datasets/Real-IAD",
    category="audiojack",
    resolution=256
)

# Using different metadata version
datamodule = RealIAD(
    category="button_battery",
    resolution=1024,
    json_path="realiad_jsons/realiad_jsons_sv/{category}.json"
)

✨ Changes

Select what type of change your PR is:

• 🐞 Bug fix (non-breaking change which fixes an issue)
• 🔨 Refactor (non-breaking change which refactors the code base)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📚 Documentation update
• 🔒 Security update

✅ Checklist

Before you submit your pull request, please make sure you have completed the following steps:

• 📋 I have summarized my changes in the CHANGELOG and followed the guidelines for my type of change (skip for minor changes, documentation updates, and test enhancements).
• 📚 I have made the necessary updates to the documentation (if applicable).
• 🧪 I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).

For more information about code review checklists, see the Code Review Checklist.