Wrapper#

class torchaug.transforms.Wrapper(transforms, inplace=False)[source]#

Wrap transforms to handle tensor data.

Note

Iterates through transforms and their submodules.

If inplace attribute is found, it is set to True, inplace is handled at the wrapper level.

Note

If a transform makes a copy, the resulting tensor will not share the same underlying storage even if inplace is set to True.

Parameters:

transforms (list[Module] | Module) – A list of transform modules.
inplace (bool, optional) – Whether to perform the transforms inplace. If a transform makes a copy, the resulting tensor will not share the same underlying storage.
Default: False

forward(tensor)[source]#

Apply transforms on the tensor.

If inplace is True, clone the tensor.