refactoring Img Segm augmentation with albumentations

[Borda]

What does this PR do?

Fixes # (issue)

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes?
• If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

• Is this pull request ready for review? (if not, please submit in draft mode)

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[codecov]

Codecov Report

Merging #1313 (b468bf4) into master (c05a3ea) will decrease coverage by 0.57%.
The diff coverage is 92.85%.

❗ Current head b468bf4 differs from pull request most recent head f40c0a8. Consider uploading reports for the commit f40c0a8 to get more accurate results

@@            Coverage Diff             @@
##           master    #1313      +/-   ##
==========================================
- Coverage   92.86%   92.29%   -0.58%     
==========================================
  Files         287      287              
  Lines       12972    13053      +81     
==========================================
  Hits        12047    12047              
- Misses        925     1006      +81     

Flag	Coverage Δ
pytest	13.29% <0.00%> (?)
tpu	13.29% <0.00%> (?)
unittests	92.83% <92.85%> (-0.04%)	⬇️

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

Impacted Files	Coverage Δ
flash/core/utilities/imports.py	91.47% <ø> (ø)
flash/image/segmentation/output.py	81.94% <75.00%> (ø)
flash/core/data/transforms.py	91.07% <86.20%> (-5.42%)	⬇️
flash/core/data/utilities/collate.py	100.00% <100.00%> (ø)
flash/image/classification/input_transform.py	83.33% <100.00%> (-1.05%)	⬇️
...h/image/classification/integrations/learn2learn.py	55.55% <100.00%> (+0.76%)	⬆️
flash/image/instance_segmentation/data.py	100.00% <100.00%> (ø)
flash/image/segmentation/input.py	100.00% <100.00%> (ø)
flash/image/segmentation/input_transform.py	95.00% <100.00%> (-0.56%)	⬇️
flash/image/segmentation/model.py	94.31% <100.00%> (+0.27%)	⬆️
... and 39 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[krshrimali]

Apologies for the delay, @Borda - this PR is on my list for today and tomorrow to review and help land if all looks good! As always, appreciate the contributions here. <3

[Borda]

Apologies for the delay

no problem, take your time 🐰

[Borda]

@krshrimali @ethanwharris may pls get your help on this collision resolution... 🐰

[krshrimali]

Nice! Great work, thanks @ethanwharris and @Borda. 🔥 🚀