AutoAugment

class torchvision.transforms.v2.AutoAugment(policy: AutoAugmentPolicy = AutoAugmentPolicy.IMAGENET, interpolation: Union[InterpolationMode, int] = InterpolationMode.NEAREST, fill: Union[int, float, Sequence[int], Sequence[float], None, Dict[Union[Type, str], Optional[Union[int, float, Sequence[int], Sequence[float]]]]] = None)

[BETA] AutoAugment data augmentation method based on “AutoAugment: Learning Augmentation Strategies from Data”.

Note

The AutoAugment 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 transformation works on images and videos only.

If the input is torch.Tensor, it should be of type torch.uint8, and it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Parameters:

• policy (AutoAugmentPolicy, optional) – Desired policy enum defined by torchvision.transforms.autoaugment.AutoAugmentPolicy. Default is AutoAugmentPolicy.IMAGENET.

• interpolation (InterpolationMode, optional) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.NEAREST. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported.

• fill (sequence or number, optional) – Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively.

Examples using AutoAugment:

Illustration of transforms

Illustration of transforms

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.

static get_params(transform_num: int) → Tuple[int, Tensor, Tensor]

Get parameters for autoaugment transformation

Returns:

params required by the autoaugment transformation