Datasets

Class for loading data into Pytorch float tensor

From: https://gitlab.com/acasamitjana/latentmodels_ad

class multiviewae.base.datasets.MVDataset(data, n_views, labels=None, return_index=False, transform=None)[source]

PyTorch Dataset for storing and accessing multi-view data.

Parameters

  • data (list) – Input data. list of torch.Tensors.

  • labels (np.array) – Dataset labels.

  • return_index (bool) – Whether to return batch index labels.

  • transform (torchvision.transforms) – Torchvision transformation to apply to the data. Default is None.

class multiviewae.base.datasets.IndexMVDataset(data, n_views, labels=None, filename='', data_dir='')[source]