class torchvision.transforms.v2.Normalize(mean: Sequence[float], std: Sequence[float], inplace: bool = False)[source]

[BETA] Normalize a tensor image or video with mean and standard deviation.


The Normalize 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:

This transform does not support PIL Image. Given mean: (mean[1],...,mean[n]) and std: (std[1],..,std[n]) for n channels, this transform will normalize each channel of the input torch.*Tensor i.e., output[channel] = (input[channel] - mean[channel]) / std[channel]


This transform acts out of place, i.e., it does not mutate the input tensor.

  • mean (sequence) – Sequence of means for each channel.

  • std (sequence) – Sequence of standard deviations for each channel.

  • inplace (bool,optional) – Bool to make this operation in-place.

Examples using Normalize:

Getting started with transforms v2

Getting started with transforms v2

How to use CutMix and MixUp

How to use CutMix and MixUp

How to write your own v2 transforms

How to write your own v2 transforms


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