RandomChoice

class torchvision.transforms.v2.RandomChoice(transforms: Sequence[Callable], p: Optional[List[float]] = None)

[BETA] Apply single transformation randomly picked from a list.

Note

The RandomChoice transform is in Beta stage, and while we do not expect disruptive breaking changes, some APIs may slightly change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753.

This transform does not support torchscript.

Parameters:

• transforms (sequence or torch.nn.Module) – list of transformations

• p (list of python:floats or None, optional) – probability of each transform being picked. If p doesn’t sum to 1, it is automatically normalized. If None (default), all transforms have the same probability.

Examples using RandomChoice:

How to use CutMix and MixUp

How to use CutMix and MixUp

forward(*inputs: Any) → Any

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.