Add Sam2 video

[zyd-ustc]

What does this PR do?

Adds # (feature)
1.add sam2_video model
2.add sam2_video processor

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you make sure to update the documentation with your changes? E.g. record bug fixes or new features in What's New. Here are the
  documentation guidelines
• Did you build and run the code without any errors?
• Did you report the running environment (NPU type/MS version) and performance in the doc? (better record it for data loading, model inference, or training tasks)
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@xxx

[gemini-code-assist]

Summary of Changes

Hello @zyd-ustc, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates the SAM2 video modeling capabilities into the mindone transformers library. It introduces a new Sam2VideoProcessor that unifies image and video processing, enabling the handling of complex inputs like points, bounding boxes, and masks across video frames. This enhancement allows for robust video segmentation and object tracking functionalities within the framework.

Highlights

• SAM2 Video Model Introduction: This pull request introduces the core components for the SAM2 video model, enabling video-specific segmentation capabilities within the mindone transformers library.
• Comprehensive Sam2VideoProcessor: A new Sam2VideoProcessor is added, designed to handle both image and video inputs. It processes 2D points, bounding boxes, and masks, and manages inference sessions for video segmentation tasks.
• Specialized Video Processing: A dedicated Sam2VideoVideoProcessor is implemented to efficiently manage video preprocessing (resizing, rescaling, normalization) and post-processing of masks, ensuring optimal input for the SAM2 video model.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces the Sam2VideoProcessor and Sam2VideoVideoProcessor for video modeling with SAM2. The changes include the necessary processing logic for handling video inputs, including points, boxes, and masks. The implementation is quite comprehensive.

My review focuses on improving code clarity, maintainability, and adherence to best practices. I've suggested:

• Using explicit imports instead of wildcards to improve code readability.
• Replacing copy.deepcopy with the more idiomatic and efficient .clone() for tensor copying.
• Correcting a malformed docstring.
• Removing an unused import.

These changes should help improve the overall quality of the new code.

[gemini-code-assist]

The docstring for this method appears to be malformed. The first line is incorrectly indented, and there's a stray period at the end. This should be corrected for better documentation clarity.

        """Validate a single input by ensuring proper nesting and raising an error if the input is not valid.

        Args:
            data (`ms.Tensor`, `np.ndarray`, or `list`):
                Input data to process.
            expected_depth (`int`):
                Expected nesting depth.
            input_name (`str`):
                Name of the input for error messages.
            expected_format (`str`):
                The expected format of the input.
            expected_coord_size (`int`, *optional*):
                Expected coordinate size (2 for points, 4 for boxes, None for labels).
        """