[Feature] Support RTMDet-Ins and improve RTMDet test config.

[RangiLyu]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

1. Support RTMDet-Ins
   

3. Update RTMDet with YOLO series test config:

    test_cfg=dict(
        nms_pre=30000,
        min_bbox_size=0,
        score_thr=0.001,
        nms=dict(type='nms', iou_threshold=0.65),
        max_per_img=300),

For a fair comparison, we update the test_cfg in RTMDet.

Modification

Add RTMDet-Ins
Update test_cfg
Support mask mosaic and mixup

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMCls.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[tascj]

The conversion overhead here is not negligible and it will slow down training. How about moving this to the data pipeline?

[RangiLyu]

You are right. We are considering moving this to PackDetInputs. But this modification is related to all instance segmentation methods. We will open another PR for the refactoring.

[zytx121]

LGTM

[ZwwWayne]

We can add comments in the config to indicate why and its outcome so that users can better understand it.