Skip to content

potential transform issue #5

@hkaraoguz

Description

@hkaraoguz

Hi,
In this part of the code

transforms.Normalize([0.485, 0.456, 0.406, 0], [0.229, 0.224, 0.225, 1])

the transforms are applied to both the image and label masks but I think the masks should not be normalized. There is an example implementation that avoids normalizing the masks: You can follow the thread here:

https://github.com/pytorch/vision/blob/3c81d474a2525b11356ca1dde299a9b1ab3715c6/references/segmentation/transforms.py#L85
https://discuss.pytorch.org/t/where-are-the-masks-unnormalized-for-segmentation-in-torchvision-train-file/48113

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions