towhee.models.utils.video_transforms.NormalizeVideo¶

class towhee.models.utils.video_transforms.NormalizeVideo(mean, std, inplace=False)[source]¶

Bases: object

Original code from torchvision: https://github.com/pytorch/vision/tree/main/torchvision/transforms

Normalize the video clip by mean subtraction and division by standard deviation :param mean: pixel RGB mean :type mean: 3-tuple :param std: pixel RGB standard deviation :type std: 3-tuple :param inplace: whether do in-place normalization :type inplace: boolean

Methods

__call__(clip)[source]¶

Parameters:: clip (torch.tensor) – video clip to be normalized. Size is (C, T, H, W)

__init__(mean, std, inplace=False)[source]¶

__repr__() → str[source]¶: Return repr(self).