Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

🚀 Update to Lightning 2.0, Add Segmentation, & Rework Regression #85

Merged
merged 161 commits into from
Mar 28, 2024

Conversation

o-laurent
Copy link
Contributor

@o-laurent o-laurent commented Mar 22, 2024

⚡ Add Lightning 2.0 support and completely rework the CLI using lightning's config files

Regression
✨ Make RegressionRoutine fully functional and add proper probabilistic regression support
✨ Add distributions & improve probabilistic regression

Segmentation
✨ Add SegmentationRoutine
✨ Add Segformer Baseline & Models
✨ Add Camvid, Cityscapes & MUAD Datamodules
✨ Add mIoU

Depth Estimation
✨ Add Depth metrics

Others
✨ Improve result printing using TUTrainer
✨ Rework experiments
✨ Add Packed-Ensembles config files
✨ Add energy as OOD criterion
➖ Remove cli_test_helpers
🔧 Fix codecov
👕 Improve overall code quality
📖 Improve documentation
📚 Improve tutorials

Tasks for merging:

alafage and others added 30 commits November 30, 2023 16:24
- 🔨 Rework classification experiment folder
- 🔨 Only one Classification routine for single and ensemble models
@o-laurent o-laurent changed the title 🚀 Update to Lightning 2.0, Add Segmentation, Rework Regression 🚀 Update to Lightning 2.0, Add Segmentation & Depth Regression, Rework Regression Mar 25, 2024
@ENSTA-U2IS-AI ENSTA-U2IS-AI deleted a comment from codecov bot Mar 25, 2024
@o-laurent o-laurent changed the title 🚀 Update to Lightning 2.0, Add Segmentation & Depth Regression, Rework Regression 🚀 Update to Lightning 2.0, Add Segmentation & Depth Estimation, Rework Regression Mar 26, 2024
Copy link

codecov bot commented Mar 26, 2024

Codecov Report

Attention: Patch coverage is 96.76492% with 45 lines in your changes are missing coverage. Please review.

Project coverage is 99.02%. Comparing base (79ec8af) to head (06b37c3).

Files Patch % Lines
...h_uncertainty/models/segmentation/segformer/std.py 89.30% 15 Missing and 19 partials ⚠️
torch_uncertainty/routines/classification.py 97.26% 0 Missing and 4 partials ⚠️
torch_uncertainty/utils/cli.py 88.57% 0 Missing and 4 partials ⚠️
torch_uncertainty/utils/evaluation_loop.py 93.75% 1 Missing and 2 partials ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main      #85      +/-   ##
==========================================
+ Coverage   99.01%   99.02%   +0.01%     
==========================================
  Files          84      107      +23     
  Lines        4445     5018     +573     
  Branches      571      679     +108     
==========================================
+ Hits         4401     4969     +568     
+ Misses         20       17       -3     
- Partials       24       32       +8     
Flag Coverage Δ
cpu 99.02% <96.76%> (+0.01%) ⬆️
pytest 99.02% <96.76%> (+0.01%) ⬆️

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.

@o-laurent o-laurent linked an issue Mar 26, 2024 that may be closed by this pull request
5 tasks
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not that useful

@o-laurent o-laurent changed the title 🚀 Update to Lightning 2.0, Add Segmentation & Depth Estimation, Rework Regression 🚀 Update to Lightning 2.0, Add Segmentation, & Rework Regression Mar 28, 2024
@o-laurent o-laurent merged commit a59ff23 into main Mar 28, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
dependencies Pull requests that update a dependency file documentation Improvements or additions to documentation enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

🐛 The Grouping Loss test does not always pass ✨ Add support for Monocular depth estimation
2 participants