torchtime.datasets¶
Torchtime provides many built-in datasets in the torchtime.datasets
module, as well as utility classes for building your own datasets.
Built-in datasets¶
All datasets are subclasses of torch.utils.data.Dataset
i.e, they have __getitem__ and __len__ methods implemented.
Hence, they can all be passed to a torch.utils.data.DataLoader
which can load multiple samples in parallel using torch.multiprocessing workers.
For example:
ucr_data = torchtime.datasets.UCR('path/to/ucr_root/', name='AbnormalHeartbeat')
data_loader = torch.utils.data.DataLoader(ucr_data,
batch_size=4,
shuffle=True,
num_workers=args.nThreads)
All the datasets have almost similar API. They all have two common arguments:
transform and target_transform to transform the input and target respectively.
You can also create your own datasets using the provided base classes.
Time Series Classification¶
UEA & UCR Time Series Classification Repository [Dau et al., 2019]. |
Base classes for custom datasets¶
Base class for making datasets which are compatible with torchtime. |
|
Base class for creating datasets which are compatible with torchtime from |