Issue #690: fix negative variance issue and add accurate test

[mathpluscode]

Description

Please include a summary of the change and which issue is fixed. Please also include
relevant motivation and context. List any dependencies that are required for this
change.

Fixes #690

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]

Codecov Report

Merging #733 (531b681) into main (2cddc38) will not change coverage.
The diff coverage is 100.00%.

@@            Coverage Diff            @@
##              main      #733   +/-   ##
=========================================
  Coverage   100.00%   100.00%           
=========================================
  Files           38        39    +1     
  Lines         2445      2455   +10     
=========================================
+ Hits          2445      2455   +10     

Impacted Files	Coverage Δ
deepreg/loss/util.py	100.00% <ø> (ø)
deepreg/model/network.py	100.00% <ø> (ø)
deepreg/constant.py	100.00% <100.00%> (ø)
deepreg/dataset/loader/interface.py	100.00% <100.00%> (ø)
deepreg/loss/image.py	100.00% <100.00%> (ø)
deepreg/loss/label.py	100.00% <100.00%> (ø)

---

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 2cddc38...531b681. Read the comment docs.

[kate-sann5100]

Nice work!