[FIX] Add pretrained pwc-model when train pwc-plus

[lhao0301]

add pretrained pwc-model when finetune on mix-dataset [kitti2015/sintel/hd1k]

[codecov]

Codecov Report

Merging #99 (6a627ee) into master (cd82b73) will increase coverage by 0.49%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master      #99      +/-   ##
==========================================
+ Coverage   67.83%   68.32%   +0.49%     
==========================================
  Files          86       87       +1     
  Lines        4896     4934      +38     
  Branches      705      709       +4     
==========================================
+ Hits         3321     3371      +50     
+ Misses       1467     1453      -14     
- Partials      108      110       +2     

Flag	Coverage Δ
unittests	68.32% <ø> (+0.49%)	⬆️

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

Impacted Files	Coverage Δ
mmflow/utils/logger.py	100.00% <0.00%> (ø)
mmflow/utils/__init__.py	100.00% <0.00%> (ø)
mmflow/datasets/__init__.py	100.00% <0.00%> (ø)
mmflow/utils/collect_env.py	20.00% <0.00%> (ø)
mmflow/core/hooks/__init__.py	100.00% <0.00%> (ø)
mmflow/models/losses/__init__.py	100.00% <0.00%> (ø)
mmflow/core/hooks/multistagelr_updater.py	100.00% <0.00%> (ø)
mmflow/core/hooks/liteflownet_stage_loading.py	50.00% <0.00%> (ø)
mmflow/models/losses/smooth_loss.py	94.59% <0.00%> (ø)
mmflow/datasets/pipelines/transforms.py	80.50% <0.00%> (+2.33%)	⬆️

---

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 cd82b73...6a627ee. Read the comment docs.