---
datasets:
- PaPieta/MozzaVID_Small
- PaPieta/MozzaVID_Base
- PaPieta/MozzaVID_Large
license: mit
pipeline_tag: image-classification
tags:
- volumetric
- 3D
- X-ray_tomography
- mozzarella
- cheese
- food_science
---

# MozzaVID: Mozzarella Volumetric Image Dataset

This repository contains model checkpoints evaluated on the **MozzaVID** dataset, as presented in the paper "[MozzaVID: Mozzarella Volumetric Image Dataset](https://huggingface.co/papers/2412.04880)".

MozzaVID is a large, clean, and versatile volumetric classification dataset containing X-ray computed tomography (CT) images of mozzarella microstructure. It enables the classification of 25 cheese types and 149 cheese samples across three different resolutions.

- **Paper:** [arXiv:2412.04880](https://arxiv.org/abs/2412.04880)
- **Project Website:** [MozzaVID Project Page](https://papieta.github.io/MozzaVID/)
- **Repository:** [GitHub - PaPieta/MozzaVID](https://github.com/PaPieta/MozzaVID)

## Data

The dataset is available on Hugging Face in WebDataset format:
* [Small split](https://huggingface.co/datasets/PaPieta/MozzaVID_Small)
* [Base split](https://huggingface.co/datasets/PaPieta/MozzaVID_Base)
* [Large split](https://huggingface.co/datasets/PaPieta/MozzaVID_Large)

Raw data can also be accessed via the [DTU archive](https://archive.compute.dtu.dk/files/public/projects/MozzaVID/).

## Usage

For details on model training and evaluation, please visit the [official GitHub repository](https://github.com/PaPieta/MozzaVID). The repository provides scripts such as `evaluate_model.py` and `train_model.py` to work with these checkpoints.

## Citation

If you use the dataset or models in your work, please consider citing the following publication:

```bibtex
@misc{pieta2024b,
  title={MozzaVID: Mozzarella Volumetric Image Dataset},
  author={Pawel Tomasz Pieta and Peter Winkel Rasmussen and Anders Bjorholm Dahl and Jeppe Revall Frisvad and Siavash Arjomand Bigdeli and Carsten Gundlach and Anders Nymark Christensen},
  year={2024},
  howpublished={arXiv:2412.04880 [cs.CV]},
  eprint={2412.04880},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2412.04880},
}
```