default_collate

torchaug.data.dataloader.default_collate(batch)

Take in a batch of data and put the elements within the batch into a tensor or ta_tensor with an additional outer dimension - batch size if relevant.

The exact output type can be a torch.Tensor, a Sequence of torch.Tensor, a Collection of torch.Tensor, TATensor, a Sequence of TATensor, a Collection of TATensor, or left unchanged, depending on the input type. This is used as the default function for collation when batch_size or batch_sampler is defined in DataLoader.

Here is the general input type (based on the type of the element within the batch) to output type mapping:

• torch.Tensor -> torch.Tensor (with an added outer dimension batch size)

• Image -> BatchImages

• Video -> BatchVideos

• BoundingBoxes -> BatchBoundingBoxes

• Mask -> BatchMasks

• BatchImages -> BatchImages

• BatchVideos -> BatchVideos

• BatchBoundingBoxes -> BatchBoundingBoxes

• BatchMasks -> BatchMasks

• NumPy Arrays -> torch.Tensor

• float -> torch.Tensor

• int -> torch.Tensor

• str -> str (unchanged)

• bytes -> bytes (unchanged)

• Mapping[K, V_i] -> Mapping[K, default_collate([V_1, V_2, …])]

• NamedTuple[V1_i, V2_i, …] -> NamedTuple[default_collate([V1_1, V1_2, …]), default_collate([V2_1, V2_2, …]), …]

• Sequence[V1_i, V2_i, …] -> Sequence[default_collate([V1_1, V1_2, …]), default_collate([V2_1, V2_2, …]), …]

Parameters:

batch – a single batch to be collated