Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/neuromorphs/tonic
Publicly available event datasets and transforms.
https://github.com/neuromorphs/tonic
augmentation datasets event-based neuromorphic spikes transformations
Last synced: 2 months ago
JSON representation
Publicly available event datasets and transforms.
- Host: GitHub
- URL: https://github.com/neuromorphs/tonic
- Owner: neuromorphs
- License: gpl-3.0
- Created: 2019-07-11T22:28:33.000Z (almost 5 years ago)
- Default Branch: develop
- Last Pushed: 2024-03-19T18:30:19.000Z (3 months ago)
- Last Synced: 2024-03-20T19:13:19.162Z (3 months ago)
- Topics: augmentation, datasets, event-based, neuromorphic, spikes, transformations
- Language: Python
- Homepage: https://tonic.readthedocs.io
- Size: 3.81 MB
- Stars: 185
- Watchers: 16
- Forks: 43
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Lists
- awesome-machine-learning - Tonic - A library that makes downloading publicly available neuromorphic datasets a breeze and provides event-based data transformation/augmentation pipelines. (Python / General-Purpose Machine Learning)
- awesome-machine-learning - Tonic - A library that makes downloading publicly available neuromorphic datasets a breeze and provides event-based data transformation/augmentation pipelines. (Python / General-Purpose Machine Learning)
- awesome-machine-learning - Tonic - A library that makes downloading publicly available neuromorphic datasets a breeze and provides event-based data transformation/augmentation pipelines. (Python / General-Purpose Machine Learning)
- awesome-machine-learning - Tonic - A library that makes downloading publicly available neuromorphic datasets a breeze and provides event-based data transformation/augmentation pipelines. (Python / General-Purpose Machine Learning)
README
[](https://pypi.org/project/tonic/)
[](https://codecov.io/gh/neuromorphs/tonic)
[](https://tonic.readthedocs.io/en/latest/?badge=latest)
[](https://github.com/neuromorphs/tonic/pulse)
[](https://mybinder.org/v2/gh/neuromorphs/tonic/main?labpath=docs%2Ftutorials)
[](https://doi.org/10.5281/zenodo.5079802)
[](https://discord.gg/qubbM4uPuA)
**Tonic** is a tool to facilitate the download, manipulation and loading of event-based/spike-based data. It's like PyTorch Vision but for neuromorphic data!
## Documentation
You can find the full documentation on Tonic [on this site](https://tonic.readthedocs.io/en/latest/index.html).
* [A first example](https://tonic.readthedocs.io/en/latest/getting_started/nmnist.html) to get a feeling for how Tonic works.
* [Run tutorials in your browser](https://mybinder.org/v2/gh/neuromorphs/tonic/main?labpath=docs%2Ftutorials) quick and easy.
* [List of datasets](https://tonic.readthedocs.io/en/main/datasets.html).
* [List of transformations](https://tonic.readthedocs.io/en/main/auto_examples/index.html).
* [About](https://tonic.readthedocs.io/en/latest/about/info.html) this project.
* [Release notes](https://tonic.readthedocs.io/en/latest/about/release_notes.html) on version changes.
## Install
```bash
pip install tonic
```
or (thanks to [@Tobias-Fischer](https://github.com/Tobias-Fischer))
```
conda install -c conda-forge tonic
```
For the latest pre-release on the develop branch that passed the tests:
```
pip install tonic --pre
```
This package has been tested on:
| Linux | [](https://github.com/neuromorphs/tonic)|
|----------|-------------------------------------------------------------------------------------------------------------------------------------------|
| **Windows** | [](https://github.com/neuromorphs/tonic) |
## Quickstart
If you're looking for a minimal example to run, this is it!
```python
import tonic
import tonic.transforms as transforms
sensor_size = tonic.datasets.NMNIST.sensor_size
transform = transforms.Compose(
[
transforms.Denoise(filter_time=10000),
transforms.ToFrame(sensor_size=sensor_size, time_window=3000),
]
)
testset = tonic.datasets.NMNIST(save_to="./data", train=False, transform=transform)
from torch.utils.data import DataLoader
testloader = DataLoader(
testset,
batch_size=10,
collate_fn=tonic.collation.PadTensors(batch_first=True),
)
frames, targets = next(iter(testloader))
```
## Discussion and questions
Have a question about how something works? Ideas for improvement? Feature request? Please get in touch on the #tonic [Discord channel](https://discord.gg/V6FHBZURkg)
or alternatively here on GitHub via the [Discussions](https://github.com/neuromorphs/tonic/discussions) page!
## Contributing
Please check out the [contributions](https://tonic.readthedocs.io/en/latest/about/contribute.html) page for details.
## Sponsoring
The development of this library is supported by
## Citation
If you find this package helpful, please consider citing it:
```BibTex
@software{lenz_gregor_2021_5079802,
author = {Lenz, Gregor and
Chaney, Kenneth and
Shrestha, Sumit Bam and
Oubari, Omar and
Picaud, Serge and
Zarrella, Guido},
title = {Tonic: event-based datasets and transformations.},
month = jul,
year = 2021,
note = {{Documentation available under
https://tonic.readthedocs.io}},
publisher = {Zenodo},
version = {0.4.0},
doi = {10.5281/zenodo.5079802},
url = {https://doi.org/10.5281/zenodo.5079802}
}
```