tonic 0.2.0

Spike manipulation and augmentation

Tonic provides publicly available spike-based datasets and a pipeline of data augmentation methods based on PyTorch, which enables multithreaded dataloading and shuffling as well as batching.

Have a look at the list of supported datasets and transformations!

Install

pip install tonic

Quickstart

import tonic
import tonic.transforms as transforms

transform = transforms.Compose([transforms.TimeJitter(variance=10),
                                transforms.FlipLR(flip_probability=0.5),
                                transforms.ToTimesurface(surface_dimensions=(7,7), tau=5e3),])

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

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

for surfaces, target in iter(testloader):
    print("{} surfaces for target {}".format(len(surfaces), target))

Documentation

You can find the full documentation on Tonic here.