class torchvision.transforms.v2.RandomGrayscale(p: float = 0.1)[source]

[BETA] Randomly convert image or videos to grayscale with a probability of p (default 0.1).


The RandomGrayscale transform is in Beta stage, and while we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue:, and you can also check out to learn more about the APIs that we suspect might involve future changes.

If the input is a torch.Tensor, it is expected to have […, 3 or 1, H, W] shape, where … means an arbitrary number of leading dimensions

The output has the same number of channels as the input.


p (float) – probability that image should be converted to grayscale.


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