eth-easl / modyn

Modyn is a research-platform for training ML models on dynamic datasets.
MIT License
22 stars 3 forks source link

Twin RHO Model Step 2: split the training set and train the twin model #552

Closed XianzheMa closed 1 week ago

XianzheMa commented 1 week ago

Per the title.

The major change is in file modyn/selector/internal/selector_strategies/downsampling_strategies/rho_loss_downsampling_strategy.py

codecov[bot] commented 1 week ago

Codecov Report

Attention: Patch coverage is 96.61017% with 2 lines in your changes missing coverage. Please review.

Project coverage is 82.98%. Comparing base (60d3baa) to head (3e9250a).

Files Patch % Lines
...ig/schema/pipeline/sampling/downsampling_config.py 66.66% 1 Missing :warning:
...pling_strategies/rho_loss_downsampling_strategy.py 98.07% 1 Missing :warning:
Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #552 +/- ## ========================================== + Coverage 82.93% 82.98% +0.04% ========================================== Files 221 221 Lines 10306 10342 +36 ========================================== + Hits 8547 8582 +35 - Misses 1759 1760 +1 ```

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

github-actions[bot] commented 1 week ago

Line Coverage: -% ( % to main) Branch Coverage: -% ( % to main)

MaxiBoether commented 1 week ago

Will review when 547 is merged and the branch is updated