tonic 0.3.6

Event-based datasets and transformations based on pyTorch vision.

Battling with all the different file formats of publicly available neuromorphic datasets? No more! Tonic is a tool to facilitate the download, manipulation and loading of event-based/spike-based data. Have a look at the list of supported datasets and transformations! It's based on PyTorch Vision for an intuitive interface, so that you spend less time worrying about how to read files and more time on things that matter.

Install

pip install tonic

Quickstart

import tonic
import tonic.transforms as transforms

transform = transforms.Compose([transforms.Denoise(time_filter=10000),
                                transforms.TimeJitter(std=10),])

testset = tonic.datasets.NMNIST(save_to='./data',
                                train=False,
                                transform=transform)

testloader = tonic.datasets.DataLoader(testset, shuffle=True)

events, target = next(iter(testloader))

Documentation

You can find the full documentation on Tonic including examples on this site.