add Faster rcnn c5

[GT9505]

The C5 with mstrain and 1x schedule achieves 37.4 mAP, which is the same as model in Detectron2 (37.3 mAP).

[codecov]

Codecov Report

Merging #4043 into master will decrease coverage by 0.00%.
The diff coverage is 71.42%.

@@            Coverage Diff             @@
##           master    #4043      +/-   ##
==========================================
- Coverage   61.91%   61.91%   -0.01%     
==========================================
  Files         224      225       +1     
  Lines       16634    16639       +5     
  Branches     2811     2814       +3     
==========================================
+ Hits        10299    10302       +3     
- Misses       5836     5838       +2     
  Partials      499      499              

Flag	Coverage Δ
unittests	61.91% <71.42%> (-0.01%)	⬇️

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

Impacted Files	Coverage Δ
mmdet/core/anchor/anchor_generator.py	78.98% <ø> (ø)
mmdet/models/dense_heads/atss_head.py	27.94% <ø> (-0.02%)	⬇️
mmdet/models/dense_heads/gfl_head.py	27.35% <ø> (-0.04%)	⬇️
mmdet/models/dense_heads/vfnet_head.py	31.48% <ø> (+0.07%)	⬆️
mmdet/core/utils/dist_utils.py	25.64% <16.66%> (-1.64%)	⬇️
mmdet/models/necks/channel_mapper.py	84.21% <84.21%> (ø)
mmdet/core/utils/__init__.py	100.00% <100.00%> (ø)
mmdet/models/necks/__init__.py	100.00% <100.00%> (ø)
mmdet/models/detectors/cornernet.py	94.87% <0.00%> (-5.13%)	⬇️
mmdet/models/dense_heads/corner_head.py	74.86% <0.00%> (-1.92%)	⬇️
... and 1 more

---

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 bd3306f...7bf2a48. Read the comment docs.