Update iou_loss.py

[PeterVennerstrom]

Fix NaN issue when predicted [x1,y1,x2,y2] box has no area e.g. [30., 75., 30., 75.]. Predicted boxes of zero area occur early in training of some anchor free detectors.

[CLAassistant]

All committers have signed the CLA.

[codecov]

Codecov Report

Merging #3394 into master will decrease coverage by 0.05%.
The diff coverage is 0.00%.

@@            Coverage Diff             @@
##           master    #3394      +/-   ##
==========================================
- Coverage   57.97%   57.92%   -0.06%     
==========================================
  Files         202      202              
  Lines       13491    13491              
  Branches     2282     2282              
==========================================
- Hits         7822     7815       -7     
- Misses       5310     5315       +5     
- Partials      359      361       +2     

Flag	Coverage Δ
#unittests	57.92% <0.00%> (-0.06%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmdet/models/losses/iou_loss.py	29.94% <0.00%> (ø)
mmdet/models/roi_heads/test_mixins.py	48.38% <0.00%> (-5.38%)	⬇️
mmdet/datasets/pipelines/transforms.py	72.85% <0.00%> (-0.32%)	⬇️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update b88f538...c9e83f8. Read the comment docs.

[OpenMMLab-Assistant003]

Dear PeterVennerstrom,
First of all, we want to express our gratitude for your significant PR in the MMDetection project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR.
If you are Chinese or have WeChat，welcome to join our community on WeChat. You can add our assistant ：openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends：）
We would also like to invite you to join our Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. We look forward to seeing you there! Join us ：https://discord.gg/raweFPmdzG
Thank you again for your contribution❤
Best regards！ @PeterVennerstrom