Add MVTec LOCO dataset

[samet-akcay]

Add MVTec LOCO Dataset Support

Description

This PR adds support for the MVTec LOCO dataset in the Anomalib framework. The implementation includes dataset and datamodule classes, along with example configurations and tests.

Changes

• Added new dataset implementation: src/anomalib/data/datasets/image/mvtec_loco.py
• Added new datamodule implementation: src/anomalib/data/datamodules/image/mvtec_loco.py
• Added example configuration: examples/configs/data/mvtec_loco.yaml
• Added example usage script: examples/api/02_data/mvtec_loco.py
• Added unit tests: tests/unit/data/datamodule/image/test_mvtec_loco.py
• Updated necessary __init__.py files to expose new modules
• Enhanced test helpers in tests/helpers/data.py

Example Usage

Here's how to use the MVTec LOCO dataset in your projects:

from anomalib.data import MVTecLOCO

# Basic usage with default settings
datamodule = MVTecLOCO(
    root="./datasets/MVTec_LOCO",
    category="breakfast_box",
)
datamodule.prepare_data()
datamodule.setup()

# Advanced configuration with custom settings
datamodule = MVTecLOCO(
    root="./datasets/MVTec_LOCO",
    category="juice_bottle",
    train_batch_size=32,
    eval_batch_size=32,
    num_workers=8,
    val_split_mode="from_test",  # Create validation set from test set
    val_split_ratio=0.5,  # Use 50% of test set for validation
)

# Using with a model
from anomalib.engine import Engine
from anomalib.models import Patchcore

model = Patchcore(backbone="wide_resnet50_2", layers=["layer3"], coreset_sampling_ratio=0.1)
engine = Engine()
engine.fit(model=model, datamodule=datamodule)
predictions = engine.predict(model=model, datamodule=datamodule)

The dataset supports 5 categories of industrial objects:

• breakfast_box
• juice_bottle
• pushpins
• screw_bag
• splicing_connectors

Each category contains various types of logical and structural anomalies for training and testing.

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.

[ashwinvaidya17]

🎉