Skip to content

Latest commit

 

History

History
57 lines (38 loc) · 1.24 KB

README.md

File metadata and controls

57 lines (38 loc) · 1.24 KB

♾ Infinite dSprites

Easily generate simple continual learning benchmarks. Inspired by dSprites.

A grid of 2D shapes undergoing rotation, translation, and scaling.

Install

Install the package from PyPI:

python -m pip install idsprites

Verify the installation:

python -c "import idsprites"

Usage

See the examples directory for notebooks demonstrating how to use the package.

Contribute

Clone the repo:

git clone [email protected]:sbdzdz/idsprites.git
cd idsprites

It's a good idea to install the package in interactive mode inside a virtual environment:

python -m virtualenv venv
source venv/bin/activate

python -m pip install -r requirements.txt
python -m pip install -e .

Citation

If you use this work in your research, please consider citing:

@article{dziadzio2023disentangled,
  title={Disentangled Continual Learning: Separating Memory Edits from Model Updates},
  author={Dziadzio, Sebastian and Y{\i}ld{\i}z, {\c{C}}a{\u{g}}atay and van de Ven, Gido M and Trzci{\'n}ski, Tomasz and Tuytelaars, Tinne and Bethge, Matthias},
  journal={arXiv preprint arXiv:2312.16731},
  year={2023}
}

Thanks!