Releases: kundajelab/deeplift
Removed another superfluous print statement
v0.6.6.2-alpha version bumps
Removed batchnorm warning messages
Unit tests for batchnorm have been added for a while, but I hadn't removed the warning message.
Version on pypi
The version corresponding to what's on pypi.
Contains fix for conversion of PReLU layers.
Merge pull request #56 from kundajelab/prelu_fix PReLU conversion fix
Keras 2 compatible version, with genomics notebooks in
Keras 2 compatible version based off the master branch.
Tagging version before making keras2compat the master branch
Making a tagged version before I replace the master branch with v6 contents.
v0.6.2 for Keras 2 and tensorflow backend
@jisraeli @annashcherbina here is a tagged version that you should be able to use. It passes unit tests for both python 2 and 3.
v0.5.1-theano
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.
v0.4.0-alpha
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.
v0.3-alpha
Release for dragonn 0.1.2