Uncertainty-Wizard is a plugin on top of tensorflow.keras, allowing to easily and efficiently create uncertainty-aware deep neural networks. Also useful if you want to train multiple small models in parallel.
DeviceAllocatorContextManagerV2
context manager.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.Minor fix regarding some quantifier aliases which were described in the docs, but not actually implemented.
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
New Feature:
DeepGini
as a point-prediction based quantifier. This is part of our most recent issta paper .Bugfix:
PredictiveEntropy
quantifierRelease Notes:
[Refactor]
uwiz.models.stochastic_utils.Broadcaster
oruwiz.models.stochastic_utils.DefaultBroadcaster
and pass it as broadcaster=...
when calling predict_quantified
.This release contains no functional changes, but various minor updates to the project description and docstrings.
Docs and Description Updates
Initial public release.
Note: This is not yet tested on tensorflow 2.4 (which has been released only a couple of days ago)