Metadata-Version: 2.3
Name: idsprites
Version: 1.0.1
Summary: Easily generate simple continual learning benchmarks.
Author-email: Sebastian Dziadzio <dziadzio@hey.com>
License-File: LICENSE
Requires-Python: >=3.10
Requires-Dist: imageio>=2.13.0
Requires-Dist: matplotlib>=3.8.2
Requires-Dist: numba>=0.58.1
Requires-Dist: numpy>=1.26.2
Requires-Dist: omegaconf>=2.3.0
Requires-Dist: opencv-python>=4.8.1
Requires-Dist: scikit-learn>=1.3.2
Requires-Dist: scipy>=1.11.4
Requires-Dist: torch>=2.1.2
Requires-Dist: tqdm>=4.66.1
Description-Content-Type: text/markdown

# ♾ Infinite dSprites

Easily generate simple continual learning benchmarks. Inspired by [dSprites](https://github.com/google-deepmind/dsprites-dataset).

![A grid of 2D shapes undergoing rotation, translation, and scaling.](img/shapes.gif)

## Install

Install the package from PyPI:

```bash
python -m pip install idsprites
```

Verify the installation:

```bash
python -c "import idsprites"
```

## Usage

See the [examples](examples) directory for notebooks demonstrating how to use the package.

## Contribute

Clone the repo:

```bash
git clone git@github.com:sbdzdz/idsprites.git
cd idsprites
```

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

```bash
python -m virtualenv venv
source venv/bin/activate

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