Interpretability Methods for tf.keras models with Tensorflow 2.x
Full Changelog: https://github.com/sicara/tf-explain/compare/v0.3.0...v0.3.1
Release includes:
In this release:
image_weight
parameter added to GradCAM to better handle visualizationsIn this release:
In this release:
Thanks to @ywolff for the contributions in this release.
In this release:
tf.function
decoratorFirst version of the package, with 2 different APIs:
.fit
and .fit_generator
methodsAvailable methods in this release are: