Awesome

EvalOCL

This repository contains the code for the paper:

Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
Hasan Abed Al Kader Hammoud*, Ameya Prabhu*, Ser-Nam Lim, Philip H.S. Torr, Adel Bibi, Bernard Ghanem [Arxiv] [PDF] [Bibtex]

Installation and Dependencies

• Install all requirements required to run the code on a Python 3.9 environment by:

# First, activate a new virtual environment
pip3 install -r requirements.txt

Downloading Data

• Follow instructions from here for downloading datasets.

Usage

• Download the ordering files required from this repository into opt.order_file_dir per dataset.

If you discover any bugs in the code please contact me, I will cross-check them with my nightmares.

Citation

We hope Near-Future Accuracy is a reliable measure, and this codebase is useful for your cool CL work! We have tried to keep the codebase simple, readable but very compute/memory efficient. To cite our work:

@article{hammoud2023rapid,
      title={Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?}, 
      author={Hasan Abed Al Kader Hammoud and Ameya Prabhu and Ser-Nam Lim and Philip H. S. Torr and Adel Bibi and Bernard Ghanem},
      year={2023},
      journal={arXiv preprint arXiv:2305.09275},
}