support multiple losses supervise the same prediction

[Junjun2016]

support multiple losses supervise the same prediction

[codecov]

Codecov Report

Merging #244 (ba7eaeb) into master (2bd51e6) will increase coverage by 0.16%.
The diff coverage is 90.74%.

@@            Coverage Diff             @@
##           master     #244      +/-   ##
==========================================
+ Coverage   84.43%   84.59%   +0.16%     
==========================================
  Files          90       90              
  Lines        4361     4400      +39     
  Branches      688      707      +19     
==========================================
+ Hits         3682     3722      +40     
  Misses        537      537              
+ Partials      142      141       -1     

Flag	Coverage Δ
unittests	84.59% <90.74%> (+0.16%)	⬆️

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

Impacted Files	Coverage Δ
mmseg/datasets/pipelines/__init__.py	100.00% <ø> (ø)
mmseg/models/losses/cross_entropy_loss.py	78.12% <73.33%> (+2.68%)	⬆️
mmseg/models/decode_heads/decode_head.py	90.52% <84.61%> (-1.15%)	⬇️
mmseg/core/evaluation/metrics.py	94.11% <94.11%> (ø)
mmseg/datasets/custom.py	87.42% <95.23%> (+1.53%)	⬆️
mmseg/core/evaluation/__init__.py	100.00% <100.00%> (ø)
mmseg/core/seg/sampler/ohem_pixel_sampler.py	94.87% <100.00%> (+0.27%)	⬆️
mmseg/datasets/pipelines/transforms.py	97.78% <100.00%> (+0.94%)	⬆️
mmseg/models/decode_heads/point_head.py	96.63% <100.00%> (+0.05%)	⬆️
... 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 2bd51e6...8597a5c. Read the comment docs.

[hellock]

Task linked: CU-ggz63w multi-loss