Skip to content

Conversation

@balbasty
Copy link
Owner

This is an ungoing effort to reimplement most transforms in functional form.

The difference between cornucopia and cornucopia.functional is related to the different between torch.nn and torch.nn.functional. One if high-level, object-oriented and composable, whereas the other is purely functional.

High level randomized transforms, where hyper parameters are themselves random variables, will not be implemented in the functional library. However, it is easy to obtain the same result by passing the realization of random variables to the functional transforms.

The rationale is that a functional form is easier to understand by new users, and easier to play with when prototyping new complex transforms.

On the other hand, the object-oriented library is easier to manipulate by users who want to apply series of well-established augmentations.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants