github Trusted-AI/adversarial-robustness-toolbox 1.1.1
ART 1.1.1

latest releases: 1.20.1, 1.20.0, 1.19.2...
5 years ago

This release of ART v1.1.1 fixes two bugs in TensorFlowV2Classifier and KerasClassifier.

Added

[None]

Changed

[None]

Removed

[None]

Fixed

  • Fixed a bug in TensorFlowV2Classifier resulting in incorrect loss calculation for loss_gradients except for tensorflow.keras.losses.SparseCategoricalCrossentropy. (#279)
  • Fixed a bug in KerasClassifier that allowed predicting the model with wrong input data shapes without raising any exceptions. We have now added checks for input data shape or are using the model's predict method where possible. This bug did not affect any classifier evaluated with the correct input data shape expected by the model. (#283)

Don't miss a new adversarial-robustness-toolbox release

NewReleases is sending notifications on new releases.