739 refactor losses

[mathpluscode]

Description

Fixes #739

Type of change

What types of changes does your code introduce to DeepReg?

Please check the boxes that apply after submitting the pull request.

• [ ] Bugfix (non-breaking change which fixes an issue)
• [ ] Code style update (formatting, renaming)
• [ ] Refactoring (no functional changes, no api changes)
• [ ] Documentation Update (fix or improvement on the documentation)
• [ ] New feature (non-breaking change which adds functionality)
• [ ] Other (if none of the other choices apply)

Checklist

Please check the boxes that apply after submitting the pull request.

If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your code.

• [ ] I have installed pre-commit using pre-commit install and formatted all changed files. If you are not certain, run pre-commit run --all-files.
• [ ] My commits' message styles matches our requested structure, e.g. Issue #<issue number>: detailed message.
• [ ] I have updated the change log file regarding my changes.
• [ ] I have added tests that prove my fix is effective or that my feature works
• [ ] I have added necessary documentation (if appropriate)

[codecov[bot]]

Codecov Report

Merging #740 (ed9a204) into main (de3728c) will not change coverage. The diff coverage is 100.00%.

@@            Coverage Diff            @@
##              main      #740   +/-   ##
=========================================
  Coverage   100.00%   100.00%           
=========================================
  Files           39        40    +1     
  Lines         2464      2468    +4     
=========================================
+ Hits          2464      2468    +4     

Impacted Files	Coverage Δ
deepreg/dataset/preprocess.py	100.00% <ø> (ø)
deepreg/loss/__init__.py	100.00% <ø> (ø)
deepreg/model/network.py	100.00% <ø> (ø)
deepreg/loss/deform.py	100.00% <100.00%> (ø)
deepreg/loss/image.py	100.00% <100.00%> (ø)
deepreg/loss/kernel.py	100.00% <100.00%> (ø)
deepreg/loss/label.py	100.00% <100.00%> (ø)
deepreg/loss/util.py	100.00% <100.00%> (ø)
deepreg/registry.py	100.00% <100.00%> (ø)
deepreg/util.py	100.00% <100.00%> (ø)
... 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 de3728c...ed9a204. Read the comment docs.

[mathpluscode]

@YipengHu @kate-sann5100 could you review this PR, I did some refactoring:

• Multi-scale is now a mixin class, so that we do not have to define the scales and kernel params when defining each loss.
• The reduction arg is removed from loss init, and we define it when building loss.

I've checked on the demo with 1 GPU or 2 GPUs, the losses range are good.