Add onnx export script for segment anything v2 (#22119)
### Description
Add ONNX export script for segment anything v2 (SAM2).
### Limitations
* Does not support video. Only support image right now.
* The decoder does not support batch inference.
### Credits
The demo that is based on [SAM2
notebook](https://github.com/facebookresearch/segment-anything-2/blob/main/notebooks/image_predictor_example.ipynb),
and modified to run with ORT.
The export of decoder is inspired by
https://github.com/vietanhdev/samexporter.
### Demo
Example output of demo:
### Motivation and Context
For support optimization of SAM2 image segmentation.
