FEAT: functional library #28
Draft
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is an ungoing effort to reimplement most transforms in functional form.
The difference between
cornucopiaandcornucopia.functionalis related to the different betweentorch.nnandtorch.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.