Datasets¶
EMG datasets¶
- class dynapsetorch.datasets.EMG.RoshamboDataset(save_to: str, transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, upsample: Optional[int] = 5, channels: Optional[Sequence[int]] = [0, 1, 2, 3, 4, 5, 6, 7])[source]¶
Bases:
Dataset
EMG from forearm datasets for roshambo hand gestures recognition
@dataset{donati_elisa_2019_3194792, author = {Donati, Elisa}, title = {EMG from forearm datasets for hand gestures recognition}, month = may, year = 2019, publisher = {Zenodo}, doi = {10.5281/zenodo.3194792}, url = {https://doi.org/10.5281/zenodo.3194792} }
- Parameters:
save_to (string) – Location to save files to on disk.
train (bool) – If True, uses training subset, otherwise testing subset.
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.
transforms (callable, optional) – A callable of transforms that is applied to both data and labels at the same time.
upsample (int) – Upsample factor used to resample the EMG signal (default: 5 ~ 1KHz)
- Returns:
A dataset object that can be indexed or iterated over. One sample returns a tuple of (sensor readings, targets).