class torchvision.transforms.v2.RandomErasing(p: float = 0.5, scale: Tuple[float, float] = (0.02, 0.33), ratio: Tuple[float, float] = (0.3, 3.3), value: float = 0.0, inplace: bool = False)[source]

[BETA] Randomly select a rectangle region in the input image or video and erase its pixels.


The RandomErasing 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:

This transform does not support PIL Image. ‘Random Erasing Data Augmentation’ by Zhong et al. See

  • p (float, optional) – probability that the random erasing operation will be performed.

  • scale (tuple of python:float, optional) – range of proportion of erased area against input image.

  • ratio (tuple of python:float, optional) – range of aspect ratio of erased area.

  • value (number or tuple of numbers) – erasing value. Default is 0. If a single int, it is used to erase all pixels. If a tuple of length 3, it is used to erase R, G, B channels respectively. If a str of ‘random’, erasing each pixel with random values.

  • inplace (bool, optional) – boolean to make this transform inplace. Default set to False.


Erased input.


>>> from torchvision.transforms import v2 as transforms
>>> transform = transforms.Compose([
>>>   transforms.RandomHorizontalFlip(),
>>>   transforms.PILToTensor(),
>>>   transforms.ConvertImageDtype(torch.float),
>>>   transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
>>>   transforms.RandomErasing(),
>>> ])
static get_params(img: Tensor, scale: Tuple[float, float], ratio: Tuple[float, float], value: Optional[List[float]] = None) Tuple[int, int, int, int, Tensor][source]

Get parameters for erase for a random erasing.

  • img (Tensor) – Tensor image to be erased.

  • scale (sequence) – range of proportion of erased area against input image.

  • ratio (sequence) – range of aspect ratio of erased area.

  • value (list, optional) – erasing value. If None, it is interpreted as “random” (erasing each pixel with random values). If len(value) is 1, it is interpreted as a number, i.e. value[0].


params (i, j, h, w, v) to be passed to erase for random erasing.

Return type:



Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources