CPSC2019Dataset

class torch_ecg.databases.datasets.CPSC2019Dataset(config: torch_ecg.cfg.CFG, training: bool = True, lazy: bool = False, **reader_kwargs: Any)

Bases: torch_ecg.utils.misc.ReprMixin, torch.utils.data.dataset.Dataset

Data generator for feeding data into pytorch models using the CPSC2019 database.

Parameters

• config (dict) –

  Configurations for the dataset, ref. CPSC2019TrainCfg. A simple example is as follows:

  >>> config = deepcopy(CPSC2019TrainCfg)
  >>> config.db_dir = "some/path/to/db"
  >>> dataset = CPSC2019Dataset(config, training=True, lazy=False)
  

• training (bool, default True) – If True, the training set will be loaded, otherwise the test (val) set will be loaded.

• lazy (bool, default True) – If True, the data will not be loaded immediately, instead, it will be loaded on demand.

• **reader_kwargs (dict, optional) – Keyword arguments for the database reader class.

extra_repr_keys() → List[str]

Extra keys for __repr__() and __str__().

property labels: numpy.ndarray

Cached labels, only available when lazy=False or preloading is performed manually.

property signals: numpy.ndarray

Cached signals, only available when lazy=False or preloading is performed manually.