⚗️✨♻️ Support bundled transforms

[dyollb]

What do these changes do?

This PR implements

• loading pre-processing transforms from the config file (using monai.bundle)
• implements loading yml (and json) config files
• adds tests to check/understand behavior of bundle.ConfigParser
• removes save_nifti branch during training, i.e. automatic predicting based on validation data
• default pre-processing/augmentation now moves data to GPU after CropForegroundd

Related issue/s

• 34

• 31

How to test

Checklist

• [x] Non-breaking change (fix or new feature that would not break existing functionality).
• [x] Breaking change (fix or new feature that would cause existing functionality to change).
• [x] Unit tests for the changes and run locally with the command pytest tests
• [x] Documentation reflects the changes

[codecov[bot]]

Codecov Report

Merging #36 (0a67c03) into main (5d0b862) will increase coverage by 1.16%. The diff coverage is 50.00%.

@@            Coverage Diff             @@
##             main      #36      +/-   ##
==========================================
+ Coverage   17.32%   18.48%   +1.16%     
==========================================
  Files          44       45       +1     
  Lines        2211     2229      +18     
  Branches      365      366       +1     
==========================================
+ Hits          383      412      +29     
+ Misses       1805     1794      -11     
  Partials       23       23              

Flag	Coverage Δ
unittests	18.48% <50.00%> (+1.16%)	:arrow_up:

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

Impacted Files	Coverage Δ
src/segmantic/util/json.py	71.42% <ø> (ø)
src/segmantic/seg/monai_unet.py	23.58% <14.81%> (+1.69%)	:arrow_up:
src/segmantic/commands/monai_unet_cli.py	67.56% <66.66%> (+9.67%)	:arrow_up:
src/segmantic/prepro/labels.py	88.88% <88.88%> (+0.17%)	:arrow_up:
src/segmantic/__init__.py	100.00% <100.00%> (ø)
src/segmantic/seg/dataset.py	83.87% <100.00%> (ø)
src/segmantic/util/cli.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 5d0b862...0a67c03. Read the comment docs.

[dyollb]

Thanks @pcrespov for your review!