🚀 Upgrade to Lightning 2.0

[alafage]

Start from TorchUncertainty 0.1.6:

• [x] Merge modifications from main

Transition to Lightning CLI:

• [x] rework classification experiment folder
• [x] rework regression experiment folder
• [x] create a segmentation experiment folder

Routine simplification:

• [x] ClassificationRoutine (add save_in_csv parameter to write the results in a csv file on_test_epoch_end())
• [x] RegressionRoutine
• [x] SegmentationRoutine

Baseline update:

• [x] ResNet
• [x] VGG
• [x] WideResNet
• [x] Deep Ensembles (classification)
• [x] MLP
• [x] Deep Ensembles (regression)
• [x] Handle ELBO Loss
• [x] Handle Normal Inverse Gamma (create a new torch distribution)

Datamodules update:

• [x] MNIST
• [x] CIFAR10
• [x] CIFAR100
• [x] TinyImageNet
• [x] ImageNet

New datamodules:

• [x] Cityscapes
• [x] MUAD

Major issues:

• [ ] Cross-validation using LightningCLI: a simple solution would be to set LightningCLI(run=False) and call the fit method of the trainer ourselves as in the previous cli_main(). -- Moved to later

Final steps:

• [x] Delete useless files
• [ ] Fix coverage
• [x] Complete classification tutorials overhaul
• [x] Evidential regression tutorial
• [ ] Fix all docstrings
• [x] Switch to 0.2.0

Dependencies:

• [x] Remove cli-test-helpers (#81 #82)

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 96.43161% with 42 lines in your changes are missing coverage. Please review.

Project coverage is 99.04%. Comparing base (b130292) to head (603c464). Report is 43 commits behind head on dev.

Files	Patch %	Lines
...h_uncertainty/models/segmentation/segformer/std.py	89.30%	15 Missing and 19 partials :warning:
torch_uncertainty/routines/classification.py	97.27%	0 Missing and 4 partials :warning:
torch_uncertainty/utils/cli.py	88.23%	0 Missing and 4 partials :warning:

Additional details and impacted files

```diff @@ Coverage Diff @@ ## dev #79 +/- ## ========================================== + Coverage 98.62% 99.04% +0.42% ========================================== Files 83 95 +12 Lines 4367 4833 +466 Branches 559 657 +98 ========================================== + Hits 4307 4787 +480 + Misses 25 16 -9 + Partials 35 30 -5 ``` | [Flag](https://app.codecov.io/gh/ENSTA-U2IS-AI/torch-uncertainty/pull/79/flags?src=pr&el=flags&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ENSTA-U2IS-AI) | Coverage Δ | | |---|---|---| | [cpu](https://app.codecov.io/gh/ENSTA-U2IS-AI/torch-uncertainty/pull/79/flags?src=pr&el=flag&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ENSTA-U2IS-AI) | `99.04% <96.43%> (+0.42%)` | :arrow_up: | | [pytest](https://app.codecov.io/gh/ENSTA-U2IS-AI/torch-uncertainty/pull/79/flags?src=pr&el=flag&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ENSTA-U2IS-AI) | `99.04% <96.43%> (+0.42%)` | :arrow_up: | Flags with carried forward coverage won't be shown. [Click here](https://docs.codecov.io/docs/carryforward-flags?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=ENSTA-U2IS-AI#carryforward-flags-in-the-pull-request-comment) to find out more.

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.