Grayscale¶
- class torchvision.transforms.v2.Grayscale(num_output_channels: int = 1)[source]¶
[BETA] Convert images or videos to grayscale.
Note
The Grayscale 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.
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
:Illustration of transforms