Add sam2

[zyd-ustc]

What does this PR do?

Adds
1.Sam2 model

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 introduces the Segment Anything Model 2 (SAM2) into the MindOne project, providing a comprehensive set of components for image segmentation. It includes the full model architecture, a fast image processor, and a unified input processor, all meticulously adapted to function within the MindSpore framework. This integration aims to expand MindOne's capabilities in advanced computer vision tasks, particularly in robust and flexible image segmentation.

Highlights

• SAM2 Model Integration: The core SAM2 model architecture, including its vision encoder, prompt encoder, and mask decoder, has been integrated and adapted for the MindSpore framework.
• Image Processing: A dedicated image processor (Sam2ImageProcessorFast) is introduced to handle image preprocessing, mask filtering, and post-processing, ensuring compatibility with MindSpore.
• Unified Input Processing: A Sam2Processor class is added to streamline the handling of various inputs (images, points, labels, bounding boxes), including validation, padding, and normalization.
• MindSpore Adaptation: The entire SAM2 implementation is carefully adapted from the HuggingFace Transformers library to ensure seamless operation within the MindSpore ecosystem.

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 SAM2 model, including its modeling, image processor, and processor components. My review has identified several critical issues that need to be addressed. These include an import typo, incorrect method names for nn.Cell subclasses (forward instead of construct), an AttributeError due to a missing self assignment, and the use of PyTorch-specific device keyword arguments in MindSpore tensor creation functions, which will lead to errors. Additionally, there's a medium-severity issue where a tensor type conversion has no effect. These issues suggest the code was ported from PyTorch but not fully adapted to MindSpore's API and may not have been tested. I recommend a thorough review for similar porting errors.