pytorch / pytorch/vision

`interpolation` parameter of `AugMix()` wrongly explains `Default is InterpolationMode.NEAREST` instead of `InterpolationMode.BILINEAR`

Open
#9,074 2 comments 0 reactions 1 assignee View on GitHub

@AntoineSimoulin is already working on this.

Since May 21, 2025.

Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

📚 The doc issue

According to the source code of AugMix(), the default type of interpolation parameter is BILINEAR as shown below:

def __init__(
        self,
        severity: int = 3,
        mixture_width: int = 3,
        chain_depth: int = -1,
        alpha: float = 1.0,
        all_ops: bool = True,
        interpolation: Union[InterpolationMode, int] = InterpolationMode.BILINEAR,
        fill: Union[_FillType, dict[Union[type, str], _FillType]] = None,
    ) -> None:
    ...

But interpolation parameter wrongly explains Default is InterpolationMode.NEAREST instead of InterpolationMode.BILINEAR as shown below:

Parameters:
...

  • interpolation (InterpolationMode, optional) – ... Default is InterpolationMode.NEAREST. ...
Suggest a potential alternative/fix

So it should be as shown below:

Parameters:
...

  • interpolation (InterpolationMode, optional) – ... Default is InterpolationMode.BILINEAR. ...

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.