tonic.datasets.ntidigits18

tonic.datasets.ntidigits18#

Module Contents#

Classes#

NTIDIGITS18

N-TIDIGITS18 Dataset
class tonic.datasets.ntidigits18.NTIDIGITS18(save_to: str, train: bool = True, single_digits=False, transform: Optional[Callable] = None, target_transform: Optional[Callable] = None)[source]#

Bases: tonic.dataset.Dataset

N-TIDIGITS18 Dataset Cochlea Spike Dataset.

@article{anumula2018feature,
  title={Feature representations for neuromorphic audio spike streams},
  author={Anumula, Jithendar and Neil, Daniel and Delbruck, Tobi and Liu, Shih-Chii},
  journal={Frontiers in neuroscience},
  volume={12},
  pages={23},
  year={2018},
  publisher={Frontiers Media SA}
}
Parameters:

  • save_to (string) – Location to save files to on disk. Will put files in an ‘hsd’ subfolder.

  • train (bool) – If True, uses training subset, otherwise testing subset.

  • single_digits (bool) – If True, only returns samples with single digits (o, 1, 2, 3, 4, 5, 6, 7, 8, 9, z), with class 0 for ‘o’ and 11 for ‘z’.

  • transform (callable, optional) – A callable of transforms to apply to the data.

  • target_transform (callable, optional) – A callable of transforms to apply to the targets/labels.

Returns:

A dataset object that can be indexed or iterated over. One sample returns a tuple of (events, targets).

base_url = 'https://www.dropbox.com/scl/fi/1x4lxt9yyw25sc3tez8oi/n-tidigits.hdf5?e=2&rlkey=w8gi5udvib2zqzosus...'#
filename = 'n-tidigits.hdf5'#
file_md5 = '360a2d11e5429555c9197381cf6b58e0'#
folder_name = ''#
sensor_size = (64, 1, 1)#
dtype#
ordering#
class_map#
download() → None[source]#

Downloads from a given url, places into target folder and verifies the file hash.

Return type:

None

__getitem__(index)[source]#
__len__()[source]#
Contents