🔨 Rework for Probabilistic Regression & Pixel Regression

[alafage]

• Rework Distribution Layers to be classifiers returning distribution parameters in a dictionary.
• Update RegressionRoutine
• Update PixelRegressionRoutine
• Update Tutorials
• Update API Reference
• Fix DistributionNLL (loss / metric)
• Update BTS baseline
• Add tutorial for simple probabilistic regression
• Update existing tests
• Write tests

[codecov]

Codecov Report

Attention: Patch coverage is 93.10345% with 16 lines in your changes missing coverage. Please review.

Project coverage is 98.98%. Comparing base (86eec13) to head (9fde14f).
Report is 1 commits behind head on dev.

✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
torch_uncertainty/utils/distributions.py	50.00%	6 Missing and 2 partials ⚠️
torch_uncertainty/losses/bayesian.py	71.42%	1 Missing and 1 partial ⚠️
torch_uncertainty/losses/regression.py	71.42%	1 Missing and 1 partial ⚠️
...orch_uncertainty/models/wrappers/deep_ensembles.py	66.66%	1 Missing and 1 partial ⚠️
torch_uncertainty/routines/regression.py	93.75%	1 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##              dev     #125      +/-   ##
==========================================
- Coverage   99.21%   98.98%   -0.24%     
==========================================
  Files         142      142              
  Lines        6792     6828      +36     
  Branches      849      855       +6     
==========================================
+ Hits         6739     6759      +20     
- Misses         24       34      +10     
- Partials       29       35       +6     

Flag	Coverage Δ
cpu	98.98% <93.10%> (-0.24%)	⬇️
pytest	98.98% <93.10%> (-0.24%)	⬇️

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.