Grayscale — Torchvision 0.22 documentation (original) (raw)

class torchvision.transforms.v2.Grayscale(num_output_channels: int = 1)[source]¶

Convert images or videos to grayscale.

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

Parameters:

num_output_channels (int) – (1 or 3) number of channels desired for output image

Examples using Grayscale:

transform(inpt: Any, params: Dict[str, Any]) → Any[source]¶

Method to override for custom transforms.

See How to write your own v2 transforms