✨ Refactor wrappers & PP, Add Checkpoint Ensembles, EMA, SWA, & SWAG, Add LaplaceApprox & ABNN

[o-laurent]

• Add Helmholtz tutorials
• Add ABNN
• Merge ✨ Add trajectory models including Snapshot Ensembles #101
• Merge ✨ Add a Laplace wrapper #96
• Enable choosing the post-processing method

[codecov]

Codecov Report

Attention: Patch coverage is 98.48024% with 10 lines in your changes missing coverage. Please review.

Project coverage is 99.04%. Comparing base (ff355d9) to head (2d84fe6).

Files	Patch %	Lines
torch_uncertainty/routines/pixel_regression.py	93.75%	0 Missing and 3 partials ⚠️
torch_uncertainty/models/wrappers/stochastic.py	95.00%	1 Missing and 1 partial ⚠️
...uncertainty/models/wrappers/checkpoint_ensemble.py	96.55%	0 Missing and 1 partial ⚠️
torch_uncertainty/post_processing/laplace.py	96.29%	0 Missing and 1 partial ⚠️
torch_uncertainty/routines/classification.py	98.83%	0 Missing and 1 partial ⚠️
torch_uncertainty/routines/regression.py	96.66%	0 Missing and 1 partial ⚠️
torch_uncertainty/routines/segmentation.py	96.29%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #98      +/-   ##
==========================================
+ Coverage   98.51%   99.04%   +0.52%     
==========================================
  Files         119      127       +8     
  Lines        5742     6103     +361     
  Branches      764      832      +68     
==========================================
+ Hits         5657     6045     +388     
+ Misses         45       21      -24     
+ Partials       40       37       -3     

Flag	Coverage Δ
cpu	99.04% <98.48%> (+0.52%)	⬆️
pytest	99.04% <98.48%> (+0.52%)	⬆️

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

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[alafage]

See comments