Transform¶

class torchaug.transforms.Transform(batch_inplace=False, num_chunks=1, permute_chunks=False, batch_transform=False)[source]¶

Base class for all transforms.

For more details, please see Transforms Tutorial.

Parameters:

batch_inplace (bool, optional) – whether to apply the batch transform in-place. Does not prevent functionals to make copy but can reduce time and memory consumption. Default: False
num_chunks (int, optional) – number of chunks to split the batched input into. Default: 1
permute_chunks (bool, optional) – whether to permute the chunks. Default: False
batch_transform (bool, optional) – whether to apply the transform in batch mode. Default: False

extra_repr(exclude_names=[])[source]¶

Set the extra representation of the transform.