Metadata-Version: 2.4
Name: aucurriculum
Version: 0.1.2
Summary: A Curriculum Learning Toolkit for Deep Learning Tasks built on top of autrainer.
License: MIT
License-File: LICENSE
Keywords: curriculum learning,autrainer,computer audition,deep learning,artificial intelligence,pytorch,hydra-core,command-line,yaml
Author: Simon Rampp
Author-email: simon.rampp@tum.de
Requires-Python: >=3.9,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Dist: autrainer (==0.4.0)
Project-URL: Documentation, https://autrainer.github.io/aucurriculum/
Project-URL: Repository, https://github.com/autrainer/aucurriculum
Description-Content-Type: text/markdown

<div align="center">
  <img src="https://autrainer.github.io/aucurriculum/_images/logo_banner.png" alt="aucurriculum — A Curriculum Learning Toolkit for Deep Learning Tasks built on top of autrainer">
</div>

# aucurriculum

[![aucurriculum PyPI Version](https://img.shields.io/pypi/v/aucurriculum?logo=pypi&logoColor=b4befe&color=b4befe)](https://pypi.org/project/aucurriculum/)
[![aucurriculum Python Versions](https://img.shields.io/pypi/pyversions/aucurriculum?logo=python&logoColor=b4befe&color=b4befe)](https://pypi.org/project/aucurriculum/)
[![aucurriculum GitHub License](https://img.shields.io/badge/license-MIT-b4befe?logo=c)](https://github.com/autrainer/aucurriculum/blob/main/LICENSE)

A Curriculum Learning Toolkit for Deep Learning Tasks built on top of [autrainer](https://github.com/autrainer/autrainer).

## Installation

To install _aucurriculum_, first ensure that PyTorch (along with torchvision and torchaudio) version 2.0 or higher is installed.
For installation instructions, refer to the [PyTorch website](https://pytorch.org/get-started/locally/).

It is recommended to install _aucurriculum_ within a virtual environment.
To create a new virtual environment, refer to the [Python venv documentation](https://docs.python.org/3/library/venv.html).

Next, install _aucurriculum_ using _pip_.

```bash
pip install aucurriculum
```

To install _aucurriculum_ from source, refer to the [contribution guide](https://autrainer.github.io/aucurriculum/development/contributing.html).

## Next Steps

To get started using _aucurriculum_, the [quickstart guide](https://autrainer.github.io/aucurriculum/usage/quickstart.html) outlines the creation of a simple training configuration
and [tutorials](https://autrainer.github.io/aucurriculum/usage/tutorials.html) provide examples for implementing custom scoring and pacing functions including their configurations.

For a complete list of available CLI commands, refer to the [CLI reference](https://autrainer.github.io/aucurriculum/usage/cli_reference.html) or the [CLI wrapper](https://autrainer.github.io/aucurriculum/usage/cli_wrapper.html).

## Citation

If you use _aucurriculum_ in your research, please consider citing the following [paper](https://ieeexplore.ieee.org/document/11729720):

```bibtex
@inproceedings{rampp2026difficulty,
  title         = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
  author        = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj{\"o}rn W.},
  booktitle     = {2026 International Joint Conference on Neural Networks (IJCNN)},
  year          = {2026},
  pages         = {1--8},
  doi           = {10.1109/IJCNN69854.2026.11729720},
  eprint        = {2411.00973},
  archivePrefix = {arXiv}
}
```

