Add Red Dino

[mducducd]

Adding Red Dino (large) as feature extractor

[Copilot]

Pull request overview

Adds the RedDino (large) model as a new feature extractor option in STAMP’s preprocessing pipeline, wiring it into configuration/dispatch and documenting it for users.

Changes:

• Introduces a new red_dino extractor implementation (RedDino-large) and class-token-only wrapper.
• Registers ExtractorName.RED_DINO and adds extractor dispatch in preprocessing.extract_.
• Updates docs to list RedDino as a supported feature extractor; also includes minor UNI2 typing/import adjustments.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
src/stamp/preprocessing/extractor/uni2.py	Updates UNI2 imports/types and transform typing.
src/stamp/preprocessing/extractor/reddino.py	Implements the RedDino-large extractor and output wrapper.
src/stamp/preprocessing/config.py	Adds RED_DINO to ExtractorName.
src/stamp/preprocessing/__init__.py	Routes ExtractorName.RED_DINO to the new extractor factory.
getting-started.md	Documents RedDino as a supported extractor and adds a link reference.

Comments suppressed due to low confidence (1)

src/stamp/preprocessing/extractor/uni2.py:14

• This error message points users to install stamp[uni2], but there is no uni2 optional-dependency extra defined in pyproject.toml. Consider updating the message to reference an existing extra (e.g. cpu/gpu) or remove the extra-specific guidance so installation instructions remain accurate.

    raise ModuleNotFoundError(
        "uni2 dependencies not installed."
        " Please reinstall stamp using `pip install 'stamp[uni2]'`"
    ) from e

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

@mducducd I've opened a new pull request, #153, to work on those changes. Once the pull request is ready, I'll request review from you.