All transforms need to work on batches as well as the whole dataset

[KonstantinWilleke]

The Transforms for the dataset classes in mlutils.data.datasets are usually applied for a single entity. Since the dataset can be called either as a batch, or accessing the whole dataset (data.dataset[:].images for example), the transforms should work in both cases.

This behavior is true for the Normalizer, Sampler, ToTensor, AddBehaviorAsChannels. The other Transforms have to be tested, and all new transforms also have to adhere to this convention.

[pollytur]

I thought that transforms are applied anytime __getittem__ is called, so even when calling data.dataset[:] it internally calls __getittem__, so transforms should be applied. Am I missing something? Have we seen the examples, when it's an issue?