Public facing deeplift repo
Unit tests for batchnorm have been added for a while, but I hadn't removed the warning message.
The version corresponding to what's on pypi.
Keras 2 compatible version based off the master branch.
Making a tagged version before I replace the master branch with v6 contents.
@jisraeli @annashcherbina here is a tagged version that you should be able to use. It passes unit tests for both python 2 and 3.
Difference between 0.4.0 and 0.5.0 is functionality added to support separate treatment of positive and negative contributions for all activation functions (the "RevealCancel" rule - matches functionality in ICML submission). Difference between 0.5.1-theano and 0.5.0-theano (for which a release was not drafted) is that some support was added for border mode same and a cast to float32 was added to the integrated gradients function to account for cases where the supplied data might be uint8.
Theano backend. 1d convolutions and pooling added. Sequential model conversion tested with keras 0.2, 0.3 and 1.1.2, and support for keras models trained with tensorflow dimension ordering is in place. No keras functional API conversion yet.
Release for dragonn 0.1.2