v0.4.0 - multi-gpu and result-by-alias

What's Changed

• 🐛 Multi-GPU ensembles are possible again. Just extend the DeviceAllocatorContextManagerV2 context manager.
• ✨ Add return_alias_dict=True when calling predict_quantified and the return value will be a dict of quantifier aliases pointing to (prediction, confidence_or_uncertainty) tuples.

v0.3.2 - Fix missing quantifier aliases

Minor fix regarding some quantifier aliases which were described in the docs, but not actually implemented.

v0.3.1 - Warn for dependency conflicts

There were some issues with recent tf versions, especially regarding experimental features. These are not fixed, but a corresponding warning is raised, explaining workarounds to users

v0.3.0 - DeepGini

New Feature:

• #92 Added DeepGini as a point-prediction based quantifier. This is part of our most recent issta paper .

Bugfix:

• #86 Added a missing alias to the PredictiveEntropy quantifier

v0.2.0

Release Notes:

• Allow model independent tasks on ensembles, i.e., tasks where no model is loaded or persisted. This can typically be helpful for pre- or postprocessing tasks which have to be conducted for every model, but are independent of said model. (#50)
• A context manager for ensembles that runs only on CPU, even if GPUs are available. (#52)
• Tasks on ensemble methods (create, consume, predict, predict_quantified, ...) can now be executed on a selected subset of models. There are many use-cases for this. For example, it can be used if you need to re-train only one model in an ensemble, or if you have multiple distinct machines create atomic models for the same ensemble at the same time, using a shared drive. (#65)
• Minor updates to documentation and code comments (#51, #73)

v0.1.3

[Refactor]

• Refactor broadcasting and aggregation logic of stochastic models into a separate class
  As a side effect, this allows broadcasting behavior to be overriden by users: Extend uwiz.models.stochastic_utils.Broadcaster oruwiz.models.stochastic_utils.DefaultBroadcaster and pass it as broadcaster=... when calling predict_quantified.

v0.1.2

This release contains no functional changes, but various minor updates to the project description and docstrings.

v0.1.1

Docs and Description Updates

v0.1.0

Initial public release.

Note: This is not yet tested on tensorflow 2.4 (which has been released only a couple of days ago)