A Curriculum Learning Toolkit for Deep Learning Tasks built on top of autrainer.
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.
It is recommended to install aucurriculum within a virtual environment. To create a new virtual environment, refer to the Python venv documentation.
Next, install aucurriculum using pip.
pip install aucurriculumTo install aucurriculum from source, refer to the contribution guide.
To get started using aucurriculum, the quickstart guide outlines the creation of a simple training configuration and tutorials 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 or the CLI wrapper.
If you use aucurriculum in your research, please consider citing the following paper:
@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}