CodeCamp2023-671

[yinfan98]

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

Motivation

about the CodeCamp, i realize the nms_match.

Modification

1. add the nms_match onnx backend ops ()
2. add the nms_match.py to support using nms_match with config

BC-breaking (Optional)

No

Use cases (Optional)

No

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 tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.

Additional

1. I dont add the uni-test in test_ops.py but make a test_nms_match_small.py
2. I alignment the result from PyTorch inference and ONNX inference
3. If necessary add uni-test, I need some example with add the nms_match uni-test in test_ops.py

[CLAassistant]

All committers have signed the CLA.

[OpenMMLab-Assistant-004]

Hi @yinfan98,

We'd like to express our appreciation for your valuable contributions to the mmdeploy. Your efforts have significantly aided in enhancing the project's quality.
It is our pleasure to invite you to join our community thorugh Discord_Special Interest Group (SIG) channel. This is a great place to share your experiences, discuss ideas, and connect with other like-minded people. To become a part of the SIG channel, send a message to the moderator, OpenMMLab, briefly introduce yourself and mention your open-source contributions in the #introductions channel. Our team will gladly facilitate your entry. We eagerly await your presence. Please follow this link to join us: ​https://discord.gg/UjgXkPWNqA.

If you're on WeChat, we'd also love for you to join our community there. Just add our assistant using the WeChat ID: openmmlabwx. When sending the friend request, remember to include the remark "mmsig + Github ID".

Thanks again for your awesome contribution, and we're excited to have you as part of our community!

[yinfan98]

Hi @grimoire @RunningLeon
Thank you for reviewing my code. I have addressed the identified errors and made the necessary changes. Could you please take a look at the updated code and provide another review? Your feedback is greatly appreciated.
Best regards,
yyfan

[grimoire]

LGTM after fix area2

[codecov]

Codecov Report

Attention: 66 lines in your changes are missing coverage. Please review.

Files	Coverage Δ
mmdeploy/mmcv/ops/__init__.py	100.00% <100.00%> (ø)
mmdeploy/mmcv/ops/nms.py	55.90% <33.33%> (-0.27%)	⬇️
mmdeploy/mmcv/ops/nms_match.py	17.94% <17.94%> (ø)

... and 18 files with indirect coverage changes

📢 Thoughts on this report? Let us know!.

[RunningLeon]

@yinfan98 pls. fix lint error.

[RunningLeon]

LGTM