UniformTemporalSubsample

class torchvision.transforms.v2.UniformTemporalSubsample(num_samples: int)

Uniformly subsample num_samples indices from the temporal dimension of the video.

Videos are expected to be of shape [..., T, C, H, W] where T denotes the temporal dimension.

When num_samples is larger than the size of temporal dimension of the video, it will sample frames based on nearest neighbor interpolation.

Parameters:

num_samples (int) – The number of equispaced samples to be selected

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

Method to override for custom transforms.

See How to write your own v2 transforms